1345 entries « ‹ 1 of 68
› » 1.
Moriya, T; Tanaka, T; Shinozaki, T; Watanabe, S; Duh, K
Evolution-Strategy-Based Automation of System Development for High-Performance Speech Recognition Journal Article
In: IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 27, no. 1, pp. 77-88, 2019, ISSN: 2329-9290.
@article{8470178,
title = {Evolution-Strategy-Based Automation of System Development for High-Performance Speech Recognition},
author = {T Moriya and T Tanaka and T Shinozaki and S Watanabe and K Duh},
doi = {10.1109/TASLP.2018.2871755},
issn = {2329-9290},
year = {2019},
date = {2019-01-01},
journal = {IEEE/ACM Transactions on Audio, Speech, and Language Processing},
volume = {27},
number = {1},
pages = {77-88},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
2.
Gómez-Garc'ia, JA; Moro-Velázquez, L; Godino-Llorente, JI
On the design of automatic voice condition analysis systems. Part II: Review of speaker recognition techniques and study on the effects of different variability factors Journal Article
In: Biomedical Signal Processing and Control, vol. 48, pp. 128–143, 2019.
@article{gomez2019design,
title = {On the design of automatic voice condition analysis systems. Part II: Review of speaker recognition techniques and study on the effects of different variability factors},
author = {JA Gómez-Garc{'i}a and L Moro-Velázquez and JI Godino-Llorente},
url = {https://www.sciencedirect.com/science/article/pii/S1746809418302416},
year = {2019},
date = {2019-01-01},
journal = {Biomedical Signal Processing and Control},
volume = {48},
pages = {128--143},
publisher = {Elsevier},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
3.
Moro-Velazquez, Laureano; Gomez-Garcia, Jorge Andres; Godino-Llorente, Juan Ignacio; Villalba, Jesus; Rusz, Jan; Shattuck-Hufnagel, Stephanie; Dehak, Najim
A forced Gaussians based methodology for the differential evaluation of Parkinson's Disease by means of speech processing Journal Article
In: Biomedical Signal Processing and Control, vol. 48, pp. 205–220, 2019.
@article{moro2018forced,
title = {A forced Gaussians based methodology for the differential evaluation of Parkinson's Disease by means of speech processing},
author = {Laureano Moro-Velazquez and Jorge Andres Gomez-Garcia and Juan Ignacio Godino-Llorente and Jesus Villalba and Jan Rusz and Stephanie Shattuck-Hufnagel and Najim Dehak},
url = {https://doi.org/10.1016/j.bspc.2018.10.020},
year = {2019},
date = {2019-01-01},
journal = {Biomedical Signal Processing and Control},
volume = {48},
pages = {205--220},
publisher = {Elsevier},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
4.
Khayrallah, Huda; Xu, Hainan; Koehn, Philipp
The JHU Parallel Corpus Filtering Systems for WMT 2018 Inproceedings
In: Proceedings of the Third Conference on Machine Translation: Shared Task Papers, pp. 896–899, Association for Computational Linguistics, Belgium, Brussels, 2018.
@inproceedings{khayrallah-xu-koehn:2018:WMT,
title = {The JHU Parallel Corpus Filtering Systems for WMT 2018},
author = {Huda Khayrallah and Hainan Xu and Philipp Koehn},
url = {http://www.aclweb.org/anthology/W18-6479},
year = {2018},
date = {2018-10-01},
booktitle = {Proceedings of the Third Conference on Machine Translation: Shared Task Papers},
pages = {896--899},
publisher = {Association for Computational Linguistics},
address = {Belgium, Brussels},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
5.
Koehn, Philipp; Duh, Kevin; Thompson, Brian
The JHU Machine Translation Systems for WMT 2018 Inproceedings
In: Proceedings of the Third Conference on Machine Translation: Shared Task Papers, pp. 438–444, Association for Computational Linguistics, Belgium, Brussels, 2018.
@inproceedings{koehn-duh-thompson:2018:WMT,
title = {The JHU Machine Translation Systems for WMT 2018},
author = {Philipp Koehn and Kevin Duh and Brian Thompson},
url = {http://www.aclweb.org/anthology/W18-6417},
year = {2018},
date = {2018-10-01},
booktitle = {Proceedings of the Third Conference on Machine Translation: Shared Task Papers},
pages = {438--444},
publisher = {Association for Computational Linguistics},
address = {Belgium, Brussels},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
6.
Koehn, Philipp; Khayrallah, Huda; Heafield, Kenneth; Forcada, Mikel L
Findings of the WMT 2018 Shared Task on Parallel Corpus Filtering Inproceedings
In: Proceedings of the Third Conference on Machine Translation: Shared Task Papers, pp. 726–739, Association for Computational Linguistics, Belgium, Brussels, 2018.
@inproceedings{koehn-EtAl:2018:WMT,
title = {Findings of the WMT 2018 Shared Task on Parallel Corpus Filtering},
author = {Philipp Koehn and Huda Khayrallah and Kenneth Heafield and Mikel L Forcada},
url = {http://www.aclweb.org/anthology/W18-6453},
year = {2018},
date = {2018-10-01},
booktitle = {Proceedings of the Third Conference on Machine Translation: Shared Task Papers},
pages = {726--739},
publisher = {Association for Computational Linguistics},
address = {Belgium, Brussels},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
7.
Bojar, Ondřej; Federmann, Christian; Fishel, Mark; Graham, Yvette; Haddow, Barry; Koehn, Philipp; Monz, Christof
Findings of the 2018 Conference on Machine Translation (WMT18) Inproceedings
In: Proceedings of the Third Conference on Machine Translation: Shared Task Papers, pp. 272–303, Association for Computational Linguistics, Belgium, Brussels, 2018.
@inproceedings{bojar-EtAl:2018:WMT1,
title = {Findings of the 2018 Conference on Machine Translation (WMT18)},
author = {Ondřej Bojar and Christian Federmann and Mark Fishel and Yvette Graham and Barry Haddow and Philipp Koehn and Christof Monz},
url = {http://www.aclweb.org/anthology/W18-6401},
year = {2018},
date = {2018-10-01},
booktitle = {Proceedings of the Third Conference on Machine Translation: Shared Task Papers},
pages = {272--303},
publisher = {Association for Computational Linguistics},
address = {Belgium, Brussels},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
8.
Thompson, Brian; Khayrallah, Huda; Anastasopoulos, Antonios; McCarthy, Arya D; Duh, Kevin; Marvin, Rebecca; McNamee, Paul; Gwinnup, Jeremy; Anderson, Tim; Koehn, Philipp
Freezing Subnetworks to Analyze Domain Adaptation in Neural Machine Translation Inproceedings
In: Proceedings of the Third Conference on Machine Translation: Research Papers, pp. 124–132, Association for Computational Linguistics, Belgium, Brussels, 2018.
@inproceedings{thompson-EtAl:2018:WMT,
title = {Freezing Subnetworks to Analyze Domain Adaptation in Neural Machine Translation},
author = {Brian Thompson and Huda Khayrallah and Antonios Anastasopoulos and Arya D McCarthy and Kevin Duh and Rebecca Marvin and Paul McNamee and Jeremy Gwinnup and Tim Anderson and Philipp Koehn},
url = {http://www.aclweb.org/anthology/W18-6313},
year = {2018},
date = {2018-10-01},
booktitle = {Proceedings of the Third Conference on Machine Translation: Research Papers},
pages = {124--132},
publisher = {Association for Computational Linguistics},
address = {Belgium, Brussels},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
9.
Cotterell, Ryan; Kirov, Christo; Sylak-Glassman, John; Walther, Géraldine; Vylomova, Ekaterina; McCarthy, Arya D; Kann, Katharina; Mielke, Sebastian; Nicolai, Garrett; Silfverberg, Miikka; Yarowsky, David; Eisner, Jason; Hulden, Mans
The CoNLL--SIGMORPHON 2018 Shared Task: Universal Morphological Reinflection Inproceedings
In: Proceedings of the CoNLL--SIGMORPHON 2018 Shared Task: Universal Morphological Reinflection, Association for Computational Linguistics, Brussels, Belgium, 2018.
@inproceedings{cotterell-EtAl:2018c,
title = {The CoNLL--SIGMORPHON 2018 Shared Task: Universal Morphological Reinflection},
author = {Ryan Cotterell and Christo Kirov and John Sylak-Glassman and Géraldine Walther and Ekaterina Vylomova and Arya D McCarthy and Katharina Kann and Sebastian Mielke and Garrett Nicolai and Miikka Silfverberg and David Yarowsky and Jason Eisner and Mans Hulden},
year = {2018},
date = {2018-10-01},
booktitle = {Proceedings of the CoNLL--SIGMORPHON 2018 Shared Task: Universal Morphological Reinflection},
publisher = {Association for Computational Linguistics},
address = {Brussels, Belgium},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
10.
Khayrallah, Huda; Koehn, Philipp
On the Impact of Various Types of Noise on Neural Machine Translation Inproceedings
In: Proceedings of the 2nd Workshop on Neural Machine Translation and Generation, pp. 74–83, Association for Computational Linguistics, Melbourne, Australia, 2018.
@inproceedings{khayrallah-koehn:2018:WNMT2018,
title = {On the Impact of Various Types of Noise on Neural Machine Translation},
author = {Huda Khayrallah and Philipp Koehn},
url = {http://www.aclweb.org/anthology/W18-2709},
year = {2018},
date = {2018-07-01},
booktitle = {Proceedings of the 2nd Workshop on Neural Machine Translation and Generation},
pages = {74--83},
publisher = {Association for Computational Linguistics},
address = {Melbourne, Australia},
abstract = {We examine how various types of noise in the parallel training data impact the quality of neural machine translation systems. We create five types of artificial noise and analyze how they degrade performance in neural and statistical machine translation. We find that neural models are generally more harmed by noise than statistical models. For one especially egregious type of noise they learn to just copy the input sentence.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
We examine how various types of noise in the parallel training data impact the quality of neural machine translation systems. We create five types of artificial noise and analyze how they degrade performance in neural and statistical machine translation. We find that neural models are generally more harmed by noise than statistical models. For one especially egregious type of noise they learn to just copy the input sentence.
11.
Kothur, Sachith Sri Ram; Knowles, Rebecca; Koehn, Philipp
Document-Level Adaptation for Neural Machine Translation Inproceedings
In: Proceedings of the 2nd Workshop on Neural Machine Translation and Generation, pp. 64–73, Association for Computational Linguistics, Melbourne, Australia, 2018.
@inproceedings{kothur-knowles-koehn:2018:WNMT2018,
title = {Document-Level Adaptation for Neural Machine Translation},
author = {Sachith Sri Ram Kothur and Rebecca Knowles and Philipp Koehn},
url = {http://www.aclweb.org/anthology/W18-2708},
year = {2018},
date = {2018-07-01},
booktitle = {Proceedings of the 2nd Workshop on Neural Machine Translation and Generation},
pages = {64--73},
publisher = {Association for Computational Linguistics},
address = {Melbourne, Australia},
abstract = {It is common practice to adapt machine translation systems to novel domains, but even a well-adapted system may be able to perform better on a particular document if it were to learn from a translator's corrections within the document itself. We focus on adaptation within a single document -- appropriate for an interactive translation scenario where a model adapts to a human translator's input over the course of a document. We propose two methods: single-sentence adaptation (which performs online adaptation one sentence at a time) and dictionary adaptation (which specifically addresses the issue of translating novel words). Combining the two models results in improvements over both approaches individually, and over baseline systems, even on short documents. On WMT news test data, we observe an improvement of +1.8 BLEU points and +23.3% novel word translation accuracy and on EMEA data (descriptions of medications) we observe an improvement of +2.7 BLEU points and +49.2% novel word translation accuracy.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
It is common practice to adapt machine translation systems to novel domains, but even a well-adapted system may be able to perform better on a particular document if it were to learn from a translator's corrections within the document itself. We focus on adaptation within a single document -- appropriate for an interactive translation scenario where a model adapts to a human translator's input over the course of a document. We propose two methods: single-sentence adaptation (which performs online adaptation one sentence at a time) and dictionary adaptation (which specifically addresses the issue of translating novel words). Combining the two models results in improvements over both approaches individually, and over baseline systems, even on short documents. On WMT news test data, we observe an improvement of +1.8 BLEU points and +23.3% novel word translation accuracy and on EMEA data (descriptions of medications) we observe an improvement of +2.7 BLEU points and +49.2% novel word translation accuracy.
12.
Hoang, Vu Cong Duy; Koehn, Philipp; Haffari, Gholamreza; Cohn, Trevor
Iterative Back-Translation for Neural Machine Translation Inproceedings
In: Proceedings of the 2nd Workshop on Neural Machine Translation and Generation, pp. 18–24, Association for Computational Linguistics, Melbourne, Australia, 2018.
@inproceedings{hoang-EtAl:2018:WNMT20181,
title = {Iterative Back-Translation for Neural Machine Translation},
author = {Vu Cong Duy Hoang and Philipp Koehn and Gholamreza Haffari and Trevor Cohn},
url = {http://www.aclweb.org/anthology/W18-2703},
year = {2018},
date = {2018-07-01},
booktitle = {Proceedings of the 2nd Workshop on Neural Machine Translation and Generation},
pages = {18--24},
publisher = {Association for Computational Linguistics},
address = {Melbourne, Australia},
abstract = {We present iterative back-translation, a method for generating increasingly better synthetic parallel data from monolingual data to train neural machine translation systems. Our proposed method is very simple yet effective and highly applicable in practice. We demonstrate improvements in neural machine translation quality in both high and low resourced scenarios, including the best reported BLEU scores for the WMT 2017 German↔English tasks.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
We present iterative back-translation, a method for generating increasingly better synthetic parallel data from monolingual data to train neural machine translation systems. Our proposed method is very simple yet effective and highly applicable in practice. We demonstrate improvements in neural machine translation quality in both high and low resourced scenarios, including the best reported BLEU scores for the WMT 2017 German↔English tasks.
13.
Wolf-Sonkin, Lawrence; Naradowsky, Jason; Mielke, Sebastian J; Cotterell, Ryan
A Structured Variational Autoencoder for Contextual Morphological Inflection Inproceedings
In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 2631–2641, Association for Computational Linguistics, Melbourne, Australia, 2018.
@inproceedings{wolf-sonkin-EtAl:2018:Long,
title = {A Structured Variational Autoencoder for Contextual Morphological Inflection},
author = {Lawrence Wolf-Sonkin and Jason Naradowsky and Sebastian J Mielke and Ryan Cotterell},
url = {http://www.aclweb.org/anthology/P18-1245},
year = {2018},
date = {2018-07-01},
booktitle = {Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
pages = {2631--2641},
publisher = {Association for Computational Linguistics},
address = {Melbourne, Australia},
abstract = {Statistical morphological inflectors are typically trained on fully supervised, type-level data. One remaining open research question is the following: How can we effectively exploit raw, token-level data to improve their performance? To this end, we introduce a novel generative latent-variable model for the semi-supervised learning of inflection generation. To enable posterior inference over the latent variables, we derive an efficient variational inference procedure based on the wake-sleep algorithm. We experiment on 23 languages, using the Universal Dependencies corpora in a simulated low-resource setting, and find improvements of over 10% absolute accuracy in some cases.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Statistical morphological inflectors are typically trained on fully supervised, type-level data. One remaining open research question is the following: How can we effectively exploit raw, token-level data to improve their performance? To this end, we introduce a novel generative latent-variable model for the semi-supervised learning of inflection generation. To enable posterior inference over the latent variables, we derive an efficient variational inference procedure based on the wake-sleep algorithm. We experiment on 23 languages, using the Universal Dependencies corpora in a simulated low-resource setting, and find improvements of over 10% absolute accuracy in some cases.
14.
Cotterell, Ryan; Mielke, Sebastian J; Eisner, Jason; Roark, Brian
Are All Languages Equally Hard to Language-Model? Inproceedings
In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pp. 536–541, Association for Computational Linguistics, New Orleans, Louisiana, 2018.
@inproceedings{cotterell-EtAl:2018:N18-21,
title = {Are All Languages Equally Hard to Language-Model?},
author = {Ryan Cotterell and Sebastian J Mielke and Jason Eisner and Brian Roark},
url = {http://www.aclweb.org/anthology/N18-2085},
year = {2018},
date = {2018-06-01},
booktitle = {Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)},
pages = {536--541},
publisher = {Association for Computational Linguistics},
address = {New Orleans, Louisiana},
abstract = {For general modeling methods applied to diverse languages, a natural question is: how well should we expect our models to work on languages with differing typological profiles? In this work, we develop an evaluation framework for fair cross-linguistic comparison of language models, using translated text so that all models are asked to predict approximately the same information. We then conduct a study on 21 languages, demonstrating that in some languages, the textual expression of the information is harder to predict with both n-gram and LSTM language models. We show complex inflectional morphology to be a cause of performance differences among languages.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
For general modeling methods applied to diverse languages, a natural question is: how well should we expect our models to work on languages with differing typological profiles? In this work, we develop an evaluation framework for fair cross-linguistic comparison of language models, using translated text so that all models are asked to predict approximately the same information. We then conduct a study on 21 languages, demonstrating that in some languages, the textual expression of the information is harder to predict with both n-gram and LSTM language models. We show complex inflectional morphology to be a cause of performance differences among languages.
15.
Cotterell, Ryan; Kirov, Christo; Mielke, Sebastian J; Eisner, Jason
Unsupervised Disambiguation of Syncretism in Inflected Lexicons Inproceedings
In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pp. 548–553, Association for Computational Linguistics, New Orleans, Louisiana, 2018.
@inproceedings{cotterell-EtAl:2018:N18-22,
title = {Unsupervised Disambiguation of Syncretism in Inflected Lexicons},
author = {Ryan Cotterell and Christo Kirov and Sebastian J Mielke and Jason Eisner},
url = {http://www.aclweb.org/anthology/N18-2087},
year = {2018},
date = {2018-06-01},
booktitle = {Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)},
pages = {548--553},
publisher = {Association for Computational Linguistics},
address = {New Orleans, Louisiana},
abstract = {Lexical ambiguity makes it difficult to compute useful statistics of a corpus. A given word form might represent any of several morphological feature bundles. One can, however, use unsupervised learning (as in EM) to fit a model that probabilistically disambiguates word forms. We present such an approach, which employs a neural network to smoothly model a prior distribution over feature bundles (even rare ones). Although this basic model does not consider a token’s context, that very property allows it to operate on a simple list of unigram type counts, partitioning each count among different analyses of that unigram. We discuss evaluation metrics for this novel task and report results on 5 languages.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Lexical ambiguity makes it difficult to compute useful statistics of a corpus. A given word form might represent any of several morphological feature bundles. One can, however, use unsupervised learning (as in EM) to fit a model that probabilistically disambiguates word forms. We present such an approach, which employs a neural network to smoothly model a prior distribution over feature bundles (even rare ones). Although this basic model does not consider a token’s context, that very property allows it to operate on a simple list of unigram type counts, partitioning each count among different analyses of that unigram. We discuss evaluation metrics for this novel task and report results on 5 languages.
16.
Lin, Chu-Cheng; Eisner, Jason
Neural Particle Smoothing for Sampling from
Conditional Sequence Models Inproceedings
In: Proceedings of the 2018 Conference of the North
American Chapter of the Association for Computational
Linguistics: Human Language Technologies (NAACL-HLT), pp. 929–941, New Orleans, 2018.
@inproceedings{lin-eisner-2018-naacl,
title = {Neural Particle Smoothing for Sampling from
Conditional Sequence Models},
author = {Chu-Cheng Lin and Jason Eisner},
url = {http://cs.jhu.edu/~jason/papers/#lin-eisner-2018-naacl},
year = {2018},
date = {2018-06-01},
booktitle = {Proceedings of the 2018 Conference of the North
American Chapter of the Association for Computational
Linguistics: Human Language Technologies (NAACL-HLT)},
pages = {929--941},
address = {New Orleans},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
17.
Kirov, Christo; Cotterell, Ryan; Sylak-Glassman, John; Walther, Géraldine; Vylomova, Ekaterina; Xia, Patrick; Faruqui, Manaal; Mielke, Sebastian; McCarthy, Arya D; Kübler, Sandra; Yarowsky, David; Eisner, Jason; Hulden, Mans
UniMorph 2.0: Universal Morphology Inproceedings
In: chair), Nicoletta Calzolari (Conference; Choukri, Khalid; Cieri, Christopher; Declerck, Thierry; Goggi, Sara; Hasida, Koiti; Isahara, Hitoshi; Maegaard, Bente; Mariani, Joseph; Mazo, Hélène; Moreno, Asuncion; Odijk, Jan; Piperidis, Stelios; Tokunaga, Takenobu (Ed.): Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), European Language Resources Association (ELRA), Miyazaki, Japan, 2018, ISBN: 979-10-95546-00-9.
@inproceedings{KIROV18.789,
title = {UniMorph 2.0: Universal Morphology},
author = {Christo Kirov and Ryan Cotterell and John Sylak-Glassman and Géraldine Walther and Ekaterina Vylomova and Patrick Xia and Manaal Faruqui and Sebastian Mielke and Arya D McCarthy and Sandra Kübler and David Yarowsky and Jason Eisner and Mans Hulden},
editor = {Nicoletta Calzolari (Conference chair) and Khalid Choukri and Christopher Cieri and Thierry Declerck and Sara Goggi and Koiti Hasida and Hitoshi Isahara and Bente Maegaard and Joseph Mariani and Hélène Mazo and Asuncion Moreno and Jan Odijk and Stelios Piperidis and Takenobu Tokunaga},
isbn = {979-10-95546-00-9},
year = {2018},
date = {2018-05-01},
booktitle = {Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)},
publisher = {European Language Resources Association (ELRA)},
address = {Miyazaki, Japan},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
18.
Xu, Hainan; Li, Ke; Wang, Yiming; Wang, Jian; Kang, Shiyin; Chen, Xie; Povey, Daniel; Khudanpur, Sanjeev
NEURAL NETWORK LANGUAGE MODELING WITH LETTER-BASED FEATURES AND IMPORTANCE SAMPLING Journal Article
In: 2018.
@article{xuneural,
title = {NEURAL NETWORK LANGUAGE MODELING WITH LETTER-BASED FEATURES AND IMPORTANCE SAMPLING},
author = {Hainan Xu and Ke Li and Yiming Wang and Jian Wang and Shiyin Kang and Xie Chen and Daniel Povey and Sanjeev Khudanpur},
year = {2018},
date = {2018-04-15},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
19.
Ochiai, T; Watanabe, S; Katagiri, S; Hori, T; Hershey, J
Speaker Adaptation for Multichannel End-to-End Speech Recognition Inproceedings
In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6707-6711, 2018, ISSN: 2379-190X.
@inproceedings{8462161,
title = {Speaker Adaptation for Multichannel End-to-End Speech Recognition},
author = {T Ochiai and S Watanabe and S Katagiri and T Hori and J Hershey},
doi = {10.1109/ICASSP.2018.8462161},
issn = {2379-190X},
year = {2018},
date = {2018-04-01},
booktitle = {2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
pages = {6707-6711},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
20.
Seki, H; Watanabe, S; Hori, T; Roux, J L; Hershey, J R
An End-to-End Language-Tracking Speech Recognizer for Mixed-Language Speech Inproceedings
In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4919-4923, 2018, ISSN: 2379-190X.
@inproceedings{8462180,
title = {An End-to-End Language-Tracking Speech Recognizer for Mixed-Language Speech},
author = {H Seki and S Watanabe and T Hori and J L Roux and J R Hershey},
doi = {10.1109/ICASSP.2018.8462180},
issn = {2379-190X},
year = {2018},
date = {2018-04-01},
booktitle = {2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
pages = {4919-4923},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
1345 entries « ‹ 1 of 68
› »
1345 entries « ‹ 1 of 27
› » 2019
Moriya, T; Tanaka, T; Shinozaki, T; Watanabe, S; Duh, K
Evolution-Strategy-Based Automation of System Development for High-Performance Speech Recognition Journal Article
In: IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 27, no. 1, pp. 77-88, 2019, ISSN: 2329-9290.
@article{8470178,
title = {Evolution-Strategy-Based Automation of System Development for High-Performance Speech Recognition},
author = {T Moriya and T Tanaka and T Shinozaki and S Watanabe and K Duh},
doi = {10.1109/TASLP.2018.2871755},
issn = {2329-9290},
year = {2019},
date = {2019-01-01},
journal = {IEEE/ACM Transactions on Audio, Speech, and Language Processing},
volume = {27},
number = {1},
pages = {77-88},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Gómez-Garc'ia, JA; Moro-Velázquez, L; Godino-Llorente, JI
On the design of automatic voice condition analysis systems. Part II: Review of speaker recognition techniques and study on the effects of different variability factors Journal Article
In: Biomedical Signal Processing and Control, vol. 48, pp. 128–143, 2019.
@article{gomez2019design,
title = {On the design of automatic voice condition analysis systems. Part II: Review of speaker recognition techniques and study on the effects of different variability factors},
author = {JA Gómez-Garc{'i}a and L Moro-Velázquez and JI Godino-Llorente},
url = {https://www.sciencedirect.com/science/article/pii/S1746809418302416},
year = {2019},
date = {2019-01-01},
journal = {Biomedical Signal Processing and Control},
volume = {48},
pages = {128--143},
publisher = {Elsevier},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Moro-Velazquez, Laureano; Gomez-Garcia, Jorge Andres; Godino-Llorente, Juan Ignacio; Villalba, Jesus; Rusz, Jan; Shattuck-Hufnagel, Stephanie; Dehak, Najim
A forced Gaussians based methodology for the differential evaluation of Parkinson's Disease by means of speech processing Journal Article
In: Biomedical Signal Processing and Control, vol. 48, pp. 205–220, 2019.
@article{moro2018forced,
title = {A forced Gaussians based methodology for the differential evaluation of Parkinson's Disease by means of speech processing},
author = {Laureano Moro-Velazquez and Jorge Andres Gomez-Garcia and Juan Ignacio Godino-Llorente and Jesus Villalba and Jan Rusz and Stephanie Shattuck-Hufnagel and Najim Dehak},
url = {https://doi.org/10.1016/j.bspc.2018.10.020},
year = {2019},
date = {2019-01-01},
journal = {Biomedical Signal Processing and Control},
volume = {48},
pages = {205--220},
publisher = {Elsevier},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
2018
Khayrallah, Huda; Xu, Hainan; Koehn, Philipp
The JHU Parallel Corpus Filtering Systems for WMT 2018 Inproceedings
In: Proceedings of the Third Conference on Machine Translation: Shared Task Papers, pp. 896–899, Association for Computational Linguistics, Belgium, Brussels, 2018.
@inproceedings{khayrallah-xu-koehn:2018:WMT,
title = {The JHU Parallel Corpus Filtering Systems for WMT 2018},
author = {Huda Khayrallah and Hainan Xu and Philipp Koehn},
url = {http://www.aclweb.org/anthology/W18-6479},
year = {2018},
date = {2018-10-01},
booktitle = {Proceedings of the Third Conference on Machine Translation: Shared Task Papers},
pages = {896--899},
publisher = {Association for Computational Linguistics},
address = {Belgium, Brussels},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Koehn, Philipp; Duh, Kevin; Thompson, Brian
The JHU Machine Translation Systems for WMT 2018 Inproceedings
In: Proceedings of the Third Conference on Machine Translation: Shared Task Papers, pp. 438–444, Association for Computational Linguistics, Belgium, Brussels, 2018.
@inproceedings{koehn-duh-thompson:2018:WMT,
title = {The JHU Machine Translation Systems for WMT 2018},
author = {Philipp Koehn and Kevin Duh and Brian Thompson},
url = {http://www.aclweb.org/anthology/W18-6417},
year = {2018},
date = {2018-10-01},
booktitle = {Proceedings of the Third Conference on Machine Translation: Shared Task Papers},
pages = {438--444},
publisher = {Association for Computational Linguistics},
address = {Belgium, Brussels},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Koehn, Philipp; Khayrallah, Huda; Heafield, Kenneth; Forcada, Mikel L
Findings of the WMT 2018 Shared Task on Parallel Corpus Filtering Inproceedings
In: Proceedings of the Third Conference on Machine Translation: Shared Task Papers, pp. 726–739, Association for Computational Linguistics, Belgium, Brussels, 2018.
@inproceedings{koehn-EtAl:2018:WMT,
title = {Findings of the WMT 2018 Shared Task on Parallel Corpus Filtering},
author = {Philipp Koehn and Huda Khayrallah and Kenneth Heafield and Mikel L Forcada},
url = {http://www.aclweb.org/anthology/W18-6453},
year = {2018},
date = {2018-10-01},
booktitle = {Proceedings of the Third Conference on Machine Translation: Shared Task Papers},
pages = {726--739},
publisher = {Association for Computational Linguistics},
address = {Belgium, Brussels},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Bojar, Ondřej; Federmann, Christian; Fishel, Mark; Graham, Yvette; Haddow, Barry; Koehn, Philipp; Monz, Christof
Findings of the 2018 Conference on Machine Translation (WMT18) Inproceedings
In: Proceedings of the Third Conference on Machine Translation: Shared Task Papers, pp. 272–303, Association for Computational Linguistics, Belgium, Brussels, 2018.
@inproceedings{bojar-EtAl:2018:WMT1,
title = {Findings of the 2018 Conference on Machine Translation (WMT18)},
author = {Ondřej Bojar and Christian Federmann and Mark Fishel and Yvette Graham and Barry Haddow and Philipp Koehn and Christof Monz},
url = {http://www.aclweb.org/anthology/W18-6401},
year = {2018},
date = {2018-10-01},
booktitle = {Proceedings of the Third Conference on Machine Translation: Shared Task Papers},
pages = {272--303},
publisher = {Association for Computational Linguistics},
address = {Belgium, Brussels},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Thompson, Brian; Khayrallah, Huda; Anastasopoulos, Antonios; McCarthy, Arya D; Duh, Kevin; Marvin, Rebecca; McNamee, Paul; Gwinnup, Jeremy; Anderson, Tim; Koehn, Philipp
Freezing Subnetworks to Analyze Domain Adaptation in Neural Machine Translation Inproceedings
In: Proceedings of the Third Conference on Machine Translation: Research Papers, pp. 124–132, Association for Computational Linguistics, Belgium, Brussels, 2018.
@inproceedings{thompson-EtAl:2018:WMT,
title = {Freezing Subnetworks to Analyze Domain Adaptation in Neural Machine Translation},
author = {Brian Thompson and Huda Khayrallah and Antonios Anastasopoulos and Arya D McCarthy and Kevin Duh and Rebecca Marvin and Paul McNamee and Jeremy Gwinnup and Tim Anderson and Philipp Koehn},
url = {http://www.aclweb.org/anthology/W18-6313},
year = {2018},
date = {2018-10-01},
booktitle = {Proceedings of the Third Conference on Machine Translation: Research Papers},
pages = {124--132},
publisher = {Association for Computational Linguistics},
address = {Belgium, Brussels},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Cotterell, Ryan; Kirov, Christo; Sylak-Glassman, John; Walther, Géraldine; Vylomova, Ekaterina; McCarthy, Arya D; Kann, Katharina; Mielke, Sebastian; Nicolai, Garrett; Silfverberg, Miikka; Yarowsky, David; Eisner, Jason; Hulden, Mans
The CoNLL--SIGMORPHON 2018 Shared Task: Universal Morphological Reinflection Inproceedings
In: Proceedings of the CoNLL--SIGMORPHON 2018 Shared Task: Universal Morphological Reinflection, Association for Computational Linguistics, Brussels, Belgium, 2018.
@inproceedings{cotterell-EtAl:2018c,
title = {The CoNLL--SIGMORPHON 2018 Shared Task: Universal Morphological Reinflection},
author = {Ryan Cotterell and Christo Kirov and John Sylak-Glassman and Géraldine Walther and Ekaterina Vylomova and Arya D McCarthy and Katharina Kann and Sebastian Mielke and Garrett Nicolai and Miikka Silfverberg and David Yarowsky and Jason Eisner and Mans Hulden},
year = {2018},
date = {2018-10-01},
booktitle = {Proceedings of the CoNLL--SIGMORPHON 2018 Shared Task: Universal Morphological Reinflection},
publisher = {Association for Computational Linguistics},
address = {Brussels, Belgium},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Khayrallah, Huda; Koehn, Philipp
On the Impact of Various Types of Noise on Neural Machine Translation Inproceedings
In: Proceedings of the 2nd Workshop on Neural Machine Translation and Generation, pp. 74–83, Association for Computational Linguistics, Melbourne, Australia, 2018.
@inproceedings{khayrallah-koehn:2018:WNMT2018,
title = {On the Impact of Various Types of Noise on Neural Machine Translation},
author = {Huda Khayrallah and Philipp Koehn},
url = {http://www.aclweb.org/anthology/W18-2709},
year = {2018},
date = {2018-07-01},
booktitle = {Proceedings of the 2nd Workshop on Neural Machine Translation and Generation},
pages = {74--83},
publisher = {Association for Computational Linguistics},
address = {Melbourne, Australia},
abstract = {We examine how various types of noise in the parallel training data impact the quality of neural machine translation systems. We create five types of artificial noise and analyze how they degrade performance in neural and statistical machine translation. We find that neural models are generally more harmed by noise than statistical models. For one especially egregious type of noise they learn to just copy the input sentence.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
We examine how various types of noise in the parallel training data impact the quality of neural machine translation systems. We create five types of artificial noise and analyze how they degrade performance in neural and statistical machine translation. We find that neural models are generally more harmed by noise than statistical models. For one especially egregious type of noise they learn to just copy the input sentence.
Kothur, Sachith Sri Ram; Knowles, Rebecca; Koehn, Philipp
Document-Level Adaptation for Neural Machine Translation Inproceedings
In: Proceedings of the 2nd Workshop on Neural Machine Translation and Generation, pp. 64–73, Association for Computational Linguistics, Melbourne, Australia, 2018.
@inproceedings{kothur-knowles-koehn:2018:WNMT2018,
title = {Document-Level Adaptation for Neural Machine Translation},
author = {Sachith Sri Ram Kothur and Rebecca Knowles and Philipp Koehn},
url = {http://www.aclweb.org/anthology/W18-2708},
year = {2018},
date = {2018-07-01},
booktitle = {Proceedings of the 2nd Workshop on Neural Machine Translation and Generation},
pages = {64--73},
publisher = {Association for Computational Linguistics},
address = {Melbourne, Australia},
abstract = {It is common practice to adapt machine translation systems to novel domains, but even a well-adapted system may be able to perform better on a particular document if it were to learn from a translator's corrections within the document itself. We focus on adaptation within a single document -- appropriate for an interactive translation scenario where a model adapts to a human translator's input over the course of a document. We propose two methods: single-sentence adaptation (which performs online adaptation one sentence at a time) and dictionary adaptation (which specifically addresses the issue of translating novel words). Combining the two models results in improvements over both approaches individually, and over baseline systems, even on short documents. On WMT news test data, we observe an improvement of +1.8 BLEU points and +23.3% novel word translation accuracy and on EMEA data (descriptions of medications) we observe an improvement of +2.7 BLEU points and +49.2% novel word translation accuracy.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
It is common practice to adapt machine translation systems to novel domains, but even a well-adapted system may be able to perform better on a particular document if it were to learn from a translator's corrections within the document itself. We focus on adaptation within a single document -- appropriate for an interactive translation scenario where a model adapts to a human translator's input over the course of a document. We propose two methods: single-sentence adaptation (which performs online adaptation one sentence at a time) and dictionary adaptation (which specifically addresses the issue of translating novel words). Combining the two models results in improvements over both approaches individually, and over baseline systems, even on short documents. On WMT news test data, we observe an improvement of +1.8 BLEU points and +23.3% novel word translation accuracy and on EMEA data (descriptions of medications) we observe an improvement of +2.7 BLEU points and +49.2% novel word translation accuracy.
Hoang, Vu Cong Duy; Koehn, Philipp; Haffari, Gholamreza; Cohn, Trevor
Iterative Back-Translation for Neural Machine Translation Inproceedings
In: Proceedings of the 2nd Workshop on Neural Machine Translation and Generation, pp. 18–24, Association for Computational Linguistics, Melbourne, Australia, 2018.
@inproceedings{hoang-EtAl:2018:WNMT20181,
title = {Iterative Back-Translation for Neural Machine Translation},
author = {Vu Cong Duy Hoang and Philipp Koehn and Gholamreza Haffari and Trevor Cohn},
url = {http://www.aclweb.org/anthology/W18-2703},
year = {2018},
date = {2018-07-01},
booktitle = {Proceedings of the 2nd Workshop on Neural Machine Translation and Generation},
pages = {18--24},
publisher = {Association for Computational Linguistics},
address = {Melbourne, Australia},
abstract = {We present iterative back-translation, a method for generating increasingly better synthetic parallel data from monolingual data to train neural machine translation systems. Our proposed method is very simple yet effective and highly applicable in practice. We demonstrate improvements in neural machine translation quality in both high and low resourced scenarios, including the best reported BLEU scores for the WMT 2017 German↔English tasks.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
We present iterative back-translation, a method for generating increasingly better synthetic parallel data from monolingual data to train neural machine translation systems. Our proposed method is very simple yet effective and highly applicable in practice. We demonstrate improvements in neural machine translation quality in both high and low resourced scenarios, including the best reported BLEU scores for the WMT 2017 German↔English tasks.
Wolf-Sonkin, Lawrence; Naradowsky, Jason; Mielke, Sebastian J; Cotterell, Ryan
A Structured Variational Autoencoder for Contextual Morphological Inflection Inproceedings
In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 2631–2641, Association for Computational Linguistics, Melbourne, Australia, 2018.
@inproceedings{wolf-sonkin-EtAl:2018:Long,
title = {A Structured Variational Autoencoder for Contextual Morphological Inflection},
author = {Lawrence Wolf-Sonkin and Jason Naradowsky and Sebastian J Mielke and Ryan Cotterell},
url = {http://www.aclweb.org/anthology/P18-1245},
year = {2018},
date = {2018-07-01},
booktitle = {Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
pages = {2631--2641},
publisher = {Association for Computational Linguistics},
address = {Melbourne, Australia},
abstract = {Statistical morphological inflectors are typically trained on fully supervised, type-level data. One remaining open research question is the following: How can we effectively exploit raw, token-level data to improve their performance? To this end, we introduce a novel generative latent-variable model for the semi-supervised learning of inflection generation. To enable posterior inference over the latent variables, we derive an efficient variational inference procedure based on the wake-sleep algorithm. We experiment on 23 languages, using the Universal Dependencies corpora in a simulated low-resource setting, and find improvements of over 10% absolute accuracy in some cases.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Statistical morphological inflectors are typically trained on fully supervised, type-level data. One remaining open research question is the following: How can we effectively exploit raw, token-level data to improve their performance? To this end, we introduce a novel generative latent-variable model for the semi-supervised learning of inflection generation. To enable posterior inference over the latent variables, we derive an efficient variational inference procedure based on the wake-sleep algorithm. We experiment on 23 languages, using the Universal Dependencies corpora in a simulated low-resource setting, and find improvements of over 10% absolute accuracy in some cases.
Cotterell, Ryan; Mielke, Sebastian J; Eisner, Jason; Roark, Brian
Are All Languages Equally Hard to Language-Model? Inproceedings
In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pp. 536–541, Association for Computational Linguistics, New Orleans, Louisiana, 2018.
@inproceedings{cotterell-EtAl:2018:N18-21,
title = {Are All Languages Equally Hard to Language-Model?},
author = {Ryan Cotterell and Sebastian J Mielke and Jason Eisner and Brian Roark},
url = {http://www.aclweb.org/anthology/N18-2085},
year = {2018},
date = {2018-06-01},
booktitle = {Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)},
pages = {536--541},
publisher = {Association for Computational Linguistics},
address = {New Orleans, Louisiana},
abstract = {For general modeling methods applied to diverse languages, a natural question is: how well should we expect our models to work on languages with differing typological profiles? In this work, we develop an evaluation framework for fair cross-linguistic comparison of language models, using translated text so that all models are asked to predict approximately the same information. We then conduct a study on 21 languages, demonstrating that in some languages, the textual expression of the information is harder to predict with both n-gram and LSTM language models. We show complex inflectional morphology to be a cause of performance differences among languages.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
For general modeling methods applied to diverse languages, a natural question is: how well should we expect our models to work on languages with differing typological profiles? In this work, we develop an evaluation framework for fair cross-linguistic comparison of language models, using translated text so that all models are asked to predict approximately the same information. We then conduct a study on 21 languages, demonstrating that in some languages, the textual expression of the information is harder to predict with both n-gram and LSTM language models. We show complex inflectional morphology to be a cause of performance differences among languages.
Cotterell, Ryan; Kirov, Christo; Mielke, Sebastian J; Eisner, Jason
Unsupervised Disambiguation of Syncretism in Inflected Lexicons Inproceedings
In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pp. 548–553, Association for Computational Linguistics, New Orleans, Louisiana, 2018.
@inproceedings{cotterell-EtAl:2018:N18-22,
title = {Unsupervised Disambiguation of Syncretism in Inflected Lexicons},
author = {Ryan Cotterell and Christo Kirov and Sebastian J Mielke and Jason Eisner},
url = {http://www.aclweb.org/anthology/N18-2087},
year = {2018},
date = {2018-06-01},
booktitle = {Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)},
pages = {548--553},
publisher = {Association for Computational Linguistics},
address = {New Orleans, Louisiana},
abstract = {Lexical ambiguity makes it difficult to compute useful statistics of a corpus. A given word form might represent any of several morphological feature bundles. One can, however, use unsupervised learning (as in EM) to fit a model that probabilistically disambiguates word forms. We present such an approach, which employs a neural network to smoothly model a prior distribution over feature bundles (even rare ones). Although this basic model does not consider a token’s context, that very property allows it to operate on a simple list of unigram type counts, partitioning each count among different analyses of that unigram. We discuss evaluation metrics for this novel task and report results on 5 languages.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Lexical ambiguity makes it difficult to compute useful statistics of a corpus. A given word form might represent any of several morphological feature bundles. One can, however, use unsupervised learning (as in EM) to fit a model that probabilistically disambiguates word forms. We present such an approach, which employs a neural network to smoothly model a prior distribution over feature bundles (even rare ones). Although this basic model does not consider a token’s context, that very property allows it to operate on a simple list of unigram type counts, partitioning each count among different analyses of that unigram. We discuss evaluation metrics for this novel task and report results on 5 languages.
Lin, Chu-Cheng; Eisner, Jason
Neural Particle Smoothing for Sampling from
Conditional Sequence Models Inproceedings
In: Proceedings of the 2018 Conference of the North
American Chapter of the Association for Computational
Linguistics: Human Language Technologies (NAACL-HLT), pp. 929–941, New Orleans, 2018.
@inproceedings{lin-eisner-2018-naacl,
title = {Neural Particle Smoothing for Sampling from
Conditional Sequence Models},
author = {Chu-Cheng Lin and Jason Eisner},
url = {http://cs.jhu.edu/~jason/papers/#lin-eisner-2018-naacl},
year = {2018},
date = {2018-06-01},
booktitle = {Proceedings of the 2018 Conference of the North
American Chapter of the Association for Computational
Linguistics: Human Language Technologies (NAACL-HLT)},
pages = {929--941},
address = {New Orleans},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Kirov, Christo; Cotterell, Ryan; Sylak-Glassman, John; Walther, Géraldine; Vylomova, Ekaterina; Xia, Patrick; Faruqui, Manaal; Mielke, Sebastian; McCarthy, Arya D; Kübler, Sandra; Yarowsky, David; Eisner, Jason; Hulden, Mans
UniMorph 2.0: Universal Morphology Inproceedings
In: chair), Nicoletta Calzolari (Conference; Choukri, Khalid; Cieri, Christopher; Declerck, Thierry; Goggi, Sara; Hasida, Koiti; Isahara, Hitoshi; Maegaard, Bente; Mariani, Joseph; Mazo, Hélène; Moreno, Asuncion; Odijk, Jan; Piperidis, Stelios; Tokunaga, Takenobu (Ed.): Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), European Language Resources Association (ELRA), Miyazaki, Japan, 2018, ISBN: 979-10-95546-00-9.
@inproceedings{KIROV18.789,
title = {UniMorph 2.0: Universal Morphology},
author = {Christo Kirov and Ryan Cotterell and John Sylak-Glassman and Géraldine Walther and Ekaterina Vylomova and Patrick Xia and Manaal Faruqui and Sebastian Mielke and Arya D McCarthy and Sandra Kübler and David Yarowsky and Jason Eisner and Mans Hulden},
editor = {Nicoletta Calzolari (Conference chair) and Khalid Choukri and Christopher Cieri and Thierry Declerck and Sara Goggi and Koiti Hasida and Hitoshi Isahara and Bente Maegaard and Joseph Mariani and Hélène Mazo and Asuncion Moreno and Jan Odijk and Stelios Piperidis and Takenobu Tokunaga},
isbn = {979-10-95546-00-9},
year = {2018},
date = {2018-05-01},
booktitle = {Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)},
publisher = {European Language Resources Association (ELRA)},
address = {Miyazaki, Japan},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Xu, Hainan; Li, Ke; Wang, Yiming; Wang, Jian; Kang, Shiyin; Chen, Xie; Povey, Daniel; Khudanpur, Sanjeev
NEURAL NETWORK LANGUAGE MODELING WITH LETTER-BASED FEATURES AND IMPORTANCE SAMPLING Journal Article
In: 2018.
@article{xuneural,
title = {NEURAL NETWORK LANGUAGE MODELING WITH LETTER-BASED FEATURES AND IMPORTANCE SAMPLING},
author = {Hainan Xu and Ke Li and Yiming Wang and Jian Wang and Shiyin Kang and Xie Chen and Daniel Povey and Sanjeev Khudanpur},
year = {2018},
date = {2018-04-15},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Ochiai, T; Watanabe, S; Katagiri, S; Hori, T; Hershey, J
Speaker Adaptation for Multichannel End-to-End Speech Recognition Inproceedings
In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6707-6711, 2018, ISSN: 2379-190X.
@inproceedings{8462161,
title = {Speaker Adaptation for Multichannel End-to-End Speech Recognition},
author = {T Ochiai and S Watanabe and S Katagiri and T Hori and J Hershey},
doi = {10.1109/ICASSP.2018.8462161},
issn = {2379-190X},
year = {2018},
date = {2018-04-01},
booktitle = {2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
pages = {6707-6711},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Seki, H; Watanabe, S; Hori, T; Roux, J L; Hershey, J R
An End-to-End Language-Tracking Speech Recognizer for Mixed-Language Speech Inproceedings
In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4919-4923, 2018, ISSN: 2379-190X.
@inproceedings{8462180,
title = {An End-to-End Language-Tracking Speech Recognizer for Mixed-Language Speech},
author = {H Seki and S Watanabe and T Hori and J L Roux and J R Hershey},
doi = {10.1109/ICASSP.2018.8462180},
issn = {2379-190X},
year = {2018},
date = {2018-04-01},
booktitle = {2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
pages = {4919-4923},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Settle, S; Roux, J L; Hori, T; Watanabe, S; Hershey, J R
End-to-End Multi-Speaker Speech Recognition Inproceedings
In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4819-4823, 2018, ISSN: 2379-190X.
@inproceedings{8461893,
title = {End-to-End Multi-Speaker Speech Recognition},
author = {S Settle and J L Roux and T Hori and S Watanabe and J R Hershey},
doi = {10.1109/ICASSP.2018.8461893},
issn = {2379-190X},
year = {2018},
date = {2018-04-01},
booktitle = {2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
pages = {4819-4823},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Knowles, Rebecca; Ortega, John; title of for in Koeh, Philipp Comparison Machine Translation Paradigms Use Black-Box Fuzzy-Match Repair = A
Inproceedings
In: Proceedings of the AMTA 2018 Workshop on Translation Quality Estimation and Automatic Post-Editing, pp. 249–255, Association for Machine Translation in the Americas, Boston, MA, 2018.
@inproceedings{Knowles-Ortega-Koeh:2018:AMTA,
author = {Rebecca Knowles and John Ortega and Philipp} Comparison Machine Translation Paradigms Use Black-Box Fuzzy-Match Repair = {A title of for in Koeh},
url = {http://www.aclweb.org/anthology/W18-2108},
year = {2018},
date = {2018-03-01},
booktitle = {Proceedings of the AMTA 2018 Workshop on Translation Quality Estimation and Automatic Post-Editing},
pages = {249--255},
publisher = {Association for Machine Translation in the Americas},
address = {Boston, MA},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Knowles, Rebecca; title for Koehn, Philipp Lightweight Word-Level Confidence Estimation Neural Interactive Translation Prediction =
Inproceedings
In: Proceedings of the AMTA 2018 Workshop on Translation Quality Estimation and Automatic Post-Editing, pp. 35–40, Association for Machine Translation in the Americas, Boston, MA, 2018.
@inproceedings{Knowles-Koehn:2018:AMTA,
author = {Rebecca Knowles and Philipp} {Lightweight Word-Level Confidence Estimation Neural Interactive Translation Prediction = title for Koehn},
url = {http://www.aclweb.org/anthology/W18-2102},
year = {2018},
date = {2018-03-01},
booktitle = {Proceedings of the AMTA 2018 Workshop on Translation Quality Estimation and Automatic Post-Editing},
pages = {35--40},
publisher = {Association for Machine Translation in the Americas},
address = {Boston, MA},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Marvin, Rebecca; title of Koehn, Philipp Exploring Word Sense Disambiguation Abilities Neural Machine Translation Systems (Non-archival Extended Abstract) =
Inproceedings
In: Proceedings of the 13th Conference of the Association for Machine Translation in the Americas (Volume 1: Research Papers), pp. 125–131, Association for Machine Translation in the Americas, Boston, MA, 2018.
@inproceedings{Marvin-Koehn:2018:AMTA,
author = {Rebecca Marvin and Philipp} {Exploring Word Sense Disambiguation Abilities Neural Machine Translation Systems (Non-archival Extended Abstract) = title of Koehn},
url = {http://www.aclweb.org/anthology/W18-1812},
year = {2018},
date = {2018-03-01},
booktitle = {Proceedings of the 13th Conference of the Association for Machine Translation in the Americas (Volume 1: Research Papers)},
pages = {125--131},
publisher = {Association for Machine Translation in the Americas},
address = {Boston, MA},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Wu, Shijie; Shapiro, Pamela; Cotterell, Ryan
Hard Non-Monotonic Attention for Character-Level Transduction Inproceedings
In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 4425–4438, Brussels, Belgium, 2018.
@inproceedings{D18-1473,
title = {Hard Non-Monotonic Attention for Character-Level Transduction},
author = {Shijie Wu and Pamela Shapiro and Ryan Cotterell},
url = {http://aclweb.org/anthology/D18-1473},
year = {2018},
date = {2018-01-01},
booktitle = {Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing},
pages = {4425--4438},
address = {Brussels, Belgium},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
McCarthy, Arya D; Silfverberg, Miikka; Cotterell, Ryan; Hulden, Mans; Yarowsky, David
Marrying Universal Dependencies and Universal Morphology Inproceedings
In: Proceedings of the Second Workshop on Universal Dependencies (UDW 2018), pp. 91–101, Brussels, Belgium, 2018.
@inproceedings{W18-6011,
title = {Marrying Universal Dependencies and Universal Morphology},
author = {Arya D McCarthy and Miikka Silfverberg and Ryan Cotterell and Mans Hulden and David Yarowsky},
url = {http://aclweb.org/anthology/W18-6011},
year = {2018},
date = {2018-01-01},
booktitle = {Proceedings of the Second Workshop on Universal Dependencies (UDW 2018)},
pages = {91--101},
address = {Brussels, Belgium},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Subramanian, Aswin Shanmugam; Chen, Szu-Jui; Watanabe, Shinji
Student-Teacher Learning for BLSTM Mask-based Speech Enhancement Inproceedings
In: Proc. Interspeech 2018, pp. 3249–3253, 2018.
@inproceedings{Subramanian2018b,
title = {Student-Teacher Learning for BLSTM Mask-based Speech Enhancement},
author = {Aswin Shanmugam Subramanian and Szu-Jui Chen and Shinji Watanabe},
url = {http://dx.doi.org/10.21437/Interspeech.2018-2440},
doi = {10.21437/Interspeech.2018-2440},
year = {2018},
date = {2018-01-01},
booktitle = {Proc. Interspeech 2018},
pages = {3249--3253},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Sell, Gregory; Snyder, David; McCree, Alan; Garcia-Romero, Daniel; Villalba, Jesús; Maciejewski, Matthew; Manohar, Vimal; Dehak, Najim; Povey, Daniel; Watanabe, Shinji; Khudanpur, Sanjeev
Diarization is Hard: Some Experiences and Lessons Learned for the JHU Team in the Inaugural DIHARD Challenge Inproceedings
In: Proc. Interspeech 2018, pp. 2808–2812, 2018.
@inproceedings{Sell2018d,
title = {Diarization is Hard: Some Experiences and Lessons Learned for the JHU Team in the Inaugural DIHARD Challenge},
author = {Gregory Sell and David Snyder and Alan McCree and Daniel Garcia-Romero and Jesús Villalba and Matthew Maciejewski and Vimal Manohar and Najim Dehak and Daniel Povey and Shinji Watanabe and Sanjeev Khudanpur},
url = {http://dx.doi.org/10.21437/Interspeech.2018-1893},
doi = {10.21437/Interspeech.2018-1893},
year = {2018},
date = {2018-01-01},
booktitle = {Proc. Interspeech 2018},
pages = {2808--2812},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Delcroix, Marc; Watanabe, Shinji; Ogawa, Atsunori; Karita, Shigeki; Nakatani, Tomohiro
Auxiliary Feature Based Adaptation of End-to-end ASR Systems Inproceedings
In: Proc. Interspeech 2018, pp. 2444–2448, 2018.
@inproceedings{Delcroix2018,
title = {Auxiliary Feature Based Adaptation of End-to-end ASR Systems},
author = {Marc Delcroix and Shinji Watanabe and Atsunori Ogawa and Shigeki Karita and Tomohiro Nakatani},
url = {http://dx.doi.org/10.21437/Interspeech.2018-1438},
doi = {10.21437/Interspeech.2018-1438},
year = {2018},
date = {2018-01-01},
booktitle = {Proc. Interspeech 2018},
pages = {2444--2448},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Renduchintala, Adithya; Ding, Shuoyang; Wiesner, Matthew; Watanabe, Shinji
Multi-Modal Data Augmentation for End-to-end ASR Inproceedings
In: Proc. Interspeech 2018, pp. 2394–2398, 2018.
@inproceedings{Renduchintala2018,
title = {Multi-Modal Data Augmentation for End-to-end ASR},
author = {Adithya Renduchintala and Shuoyang Ding and Matthew Wiesner and Shinji Watanabe},
url = {http://dx.doi.org/10.21437/Interspeech.2018-2456},
doi = {10.21437/Interspeech.2018-2456},
year = {2018},
date = {2018-01-01},
booktitle = {Proc. Interspeech 2018},
pages = {2394--2398},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Watanabe, Shinji; Hori, Takaaki; Karita, Shigeki; Hayashi, Tomoki; Nishitoba, Jiro; Unno, Yuya; Soplin, Nelson Enrique Yalta; Heymann, Jahn; Wiesner, Matthew; Chen, Nanxin; Renduchintala, Adithya; Ochiai, Tsubasa
ESPnet: End-to-End Speech Processing Toolkit Inproceedings
In: Proc. Interspeech 2018, pp. 2207–2211, 2018.
@inproceedings{Watanabe2018,
title = {ESPnet: End-to-End Speech Processing Toolkit},
author = {Shinji Watanabe and Takaaki Hori and Shigeki Karita and Tomoki Hayashi and Jiro Nishitoba and Yuya Unno and Nelson Enrique Yalta Soplin and Jahn Heymann and Matthew Wiesner and Nanxin Chen and Adithya Renduchintala and Tsubasa Ochiai},
url = {http://dx.doi.org/10.21437/Interspeech.2018-1456},
doi = {10.21437/Interspeech.2018-1456},
year = {2018},
date = {2018-01-01},
booktitle = {Proc. Interspeech 2018},
pages = {2207--2211},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Frederiksen, Peter Sibbern; Villalba, Jesús; Watanabe, Shinji; Tan, Zheng-Hua; Dehak, Najim
Effectiveness of Single-Channel BLSTM Enhancement for Language Identification Inproceedings
In: Proc. Interspeech 2018, pp. 1823–1827, 2018.
@inproceedings{Frederiksen2018,
title = {Effectiveness of Single-Channel BLSTM Enhancement for Language Identification},
author = {Peter Sibbern Frederiksen and Jesús Villalba and Shinji Watanabe and Zheng-Hua Tan and Najim Dehak},
url = {http://dx.doi.org/10.21437/Interspeech.2018-2458},
doi = {10.21437/Interspeech.2018-2458},
year = {2018},
date = {2018-01-01},
booktitle = {Proc. Interspeech 2018},
pages = {1823--1827},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Chen, Szu-Jui; Subramanian, Aswin Shanmugam; Xu, Hainan; Watanabe, Shinji
Building State-of-the-art Distant Speech Recognition Using the CHiME-4 Challenge with a Setup of Speech Enhancement Baseline Inproceedings
In: Proc. Interspeech 2018, pp. 1571–1575, 2018.
@inproceedings{Chen2018b,
title = {Building State-of-the-art Distant Speech Recognition Using the CHiME-4 Challenge with a Setup of Speech Enhancement Baseline},
author = {Szu-Jui Chen and Aswin Shanmugam Subramanian and Hainan Xu and Shinji Watanabe},
url = {http://dx.doi.org/10.21437/Interspeech.2018-1262},
doi = {10.21437/Interspeech.2018-1262},
year = {2018},
date = {2018-01-01},
booktitle = {Proc. Interspeech 2018},
pages = {1571--1575},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Barker, Jon; Watanabe, Shinji; Vincent, Emmanuel; Trmal, Jan
The Fifth 'CHiME' Speech Separation and Recognition Challenge: Dataset, Task and Baselines Inproceedings
In: Proc. Interspeech 2018, pp. 1561–1565, 2018.
@inproceedings{Barker2018,
title = {The Fifth 'CHiME' Speech Separation and Recognition Challenge: Dataset, Task and Baselines},
author = {Jon Barker and Shinji Watanabe and Emmanuel Vincent and Jan Trmal},
url = {http://dx.doi.org/10.21437/Interspeech.2018-1768},
doi = {10.21437/Interspeech.2018-1768},
year = {2018},
date = {2018-01-01},
booktitle = {Proc. Interspeech 2018},
pages = {1561--1565},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Hayashi, Tomoki; Watanabe, Shinji; Toda, Tomoki; Takeda, Kazuya
Multi-Head Decoder for End-to-End Speech Recognition Inproceedings
In: Proc. Interspeech 2018, pp. 801–805, 2018.
@inproceedings{Hayashi2018,
title = {Multi-Head Decoder for End-to-End Speech Recognition},
author = {Tomoki Hayashi and Shinji Watanabe and Tomoki Toda and Kazuya Takeda},
url = {http://dx.doi.org/10.21437/Interspeech.2018-1655},
doi = {10.21437/Interspeech.2018-1655},
year = {2018},
date = {2018-01-01},
booktitle = {Proc. Interspeech 2018},
pages = {801--805},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Karita, Shigeki; Watanabe, Shinji; Iwata, Tomoharu; Ogawa, Atsunori; Delcroix, Marc
Semi-Supervised End-to-End Speech Recognition Inproceedings
In: Proc. Interspeech 2018, pp. 2–6, 2018.
@inproceedings{Karita2018,
title = {Semi-Supervised End-to-End Speech Recognition},
author = {Shigeki Karita and Shinji Watanabe and Tomoharu Iwata and Atsunori Ogawa and Marc Delcroix},
url = {http://dx.doi.org/10.21437/Interspeech.2018-1746},
doi = {10.21437/Interspeech.2018-1746},
year = {2018},
date = {2018-01-01},
booktitle = {Proc. Interspeech 2018},
pages = {2--6},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Seki, Hiroshi; Hori, Takaaki; Watanabe, Shinji; Roux, Jonathan Le; Hershey, John R
Inproceedings
In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 2620–2630, Melbourne, Australia, 2018.
@inproceedings{P18-1244,
author = {Hiroshi Seki and Takaaki Hori and Shinji Watanabe and Jonathan Le Roux and John R Hershey},
url = {http://aclweb.org/anthology/P18-1244},
year = {2018},
date = {2018-01-01},
booktitle = {Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
pages = {2620--2630},
address = {Melbourne, Australia},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Watanabe, Shinji; Virtanen, Tuomas; Kolossa, Dorothea
Application of Source Separation to Robust Speech Analysis and Recognition Book Chapter
In: Audio Source Separation and Speech Enhancement, Chapter 17, pp. 377-411, Wiley-Blackwell, 2018, ISBN: 9781119279860.
@inbook{doi:10.1002/9781119279860.ch17,
title = {Application of Source Separation to Robust Speech Analysis and Recognition},
author = {Shinji Watanabe and Tuomas Virtanen and Dorothea Kolossa},
url = {https://onlinelibrary.wiley.com/doi/abs/10.1002/9781119279860.ch17},
doi = {10.1002/9781119279860.ch17},
isbn = {9781119279860},
year = {2018},
date = {2018-01-01},
booktitle = {Audio Source Separation and Speech Enhancement},
pages = {377-411},
publisher = {Wiley-Blackwell},
chapter = {17},
abstract = {Summary This chapter describes applications of source separation techniques to robust speech analysis and recognition, including automatic speech recognition, speaker/language identification, emotion and paralinguistic analysis, and audiovisual analysis. These are the most successful applications in audio and speech processing with various commercial products. However, the robustness against noise or non-target speech still remains a challenging issue, and source separation and speech enhancement techniques are gathering large attention in the community. This chapter systematically describes how source separation and speech enhancement techniques are applied to improve the robustness of these applications.},
keywords = {},
pubstate = {published},
tppubtype = {inbook}
}
Summary This chapter describes applications of source separation techniques to robust speech analysis and recognition, including automatic speech recognition, speaker/language identification, emotion and paralinguistic analysis, and audiovisual analysis. These are the most successful applications in audio and speech processing with various commercial products. However, the robustness against noise or non-target speech still remains a challenging issue, and source separation and speech enhancement techniques are gathering large attention in the community. This chapter systematically describes how source separation and speech enhancement techniques are applied to improve the robustness of these applications.
Wood-Doughty, Zach; Shpitser, Ilya; Dredze, Mark
Challenges of Using Text Classifiers for Causal Inference Inproceedings
In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 4586–4598, 2018.
@inproceedings{wood2018challenges,
title = {Challenges of Using Text Classifiers for Causal Inference},
author = {Zach Wood-Doughty and Ilya Shpitser and Mark Dredze},
year = {2018},
date = {2018-01-01},
booktitle = {Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing},
pages = {4586--4598},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Chen, Tao; Dredze, Mark
Vaccine Images on Twitter: What is Shared and Why Journal Article
In: Journal of Medical Internet Research (JMIR), 2018.
@article{Chen:2018tg,
title = {Vaccine Images on Twitter: What is Shared and Why},
author = {Tao Chen and Mark Dredze},
year = {2018},
date = {2018-01-01},
journal = {Journal of Medical Internet Research (JMIR)},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Benton, Adrian; Dredze, Mark
Deep Dirichlet Multinomial Regression Inproceedings
In: North American Chapter of the Association for Computational Linguistics (NAACL), 2018.
@inproceedings{Benton:2018dn,
title = {Deep Dirichlet Multinomial Regression},
author = {Adrian Benton and Mark Dredze},
year = {2018},
date = {2018-01-01},
booktitle = {North American Chapter of the Association for Computational Linguistics (NAACL)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Caputi, Theodore L; Leas, Eric C; Dredze, Mark; Ayers, John W
Online Sales of Marijuana: An Unrecognized Public Health Dilemma Journal Article
In: American Journal of Preventive Medicine (AJPM), 2018.
@article{Caputi:2018dk,
title = {Online Sales of Marijuana: An Unrecognized Public Health Dilemma},
author = {Theodore L Caputi and Eric C Leas and Mark Dredze and John W Ayers},
year = {2018},
date = {2018-01-01},
journal = {American Journal of Preventive Medicine (AJPM)},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Wood-Doughty, Zachary; Andrews, Nicholas; Marvin, Rebecca; Dredze, Mark
Predicting Twitter User Demographics from Names Alone Inproceedings
In: NAACL Workshop on Computational Modeling of People's Opinions, Personality, and Emotions in Social Media, 2018.
@inproceedings{Wood-Doughty:2018:peoples1,
title = {Predicting Twitter User Demographics from Names Alone},
author = {Zachary Wood-Doughty and Nicholas Andrews and Rebecca Marvin and Mark Dredze},
year = {2018},
date = {2018-01-01},
booktitle = {NAACL Workshop on Computational Modeling of People's Opinions, Personality, and Emotions in Social Media},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Wood-Doughty, Zachary; Mahajan, Praateek; Dredze, Mark
Johns Hopkins or johnny-hopkins: Classifying Individuals versus Organizations on Twitter Inproceedings
In: NAACL Workshop on Computational Modeling of People's Opinions, Personality, and Emotions in Social Media, 2018.
@inproceedings{Wood-Doughty:2018:peoples2,
title = {Johns Hopkins or johnny-hopkins: Classifying Individuals versus Organizations on Twitter},
author = {Zachary Wood-Doughty and Praateek Mahajan and Mark Dredze},
year = {2018},
date = {2018-01-01},
booktitle = {NAACL Workshop on Computational Modeling of People's Opinions, Personality, and Emotions in Social Media},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Hammond, Alexis S; Paul, Michael J; Hobelmann, Gregory J; Koratana, Animesh R; Dredze, Mark; Chisolm, Margaret S
Perceived Attitudes About Substance Use in Anonymous Social Media Posts Near College Campuses Journal Article
In: Journal of Medical Internet Research Mental Health (JMIR MH), 2018.
@article{hammond:2018lq,
title = {Perceived Attitudes About Substance Use in Anonymous Social Media Posts Near College Campuses},
author = {Alexis S Hammond and Michael J Paul and Gregory J Hobelmann and Animesh R Koratana and Mark Dredze and Margaret S Chisolm},
year = {2018},
date = {2018-01-01},
journal = {Journal of Medical Internet Research Mental Health (JMIR MH)},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Wolfe, Travis; Carrell, Annabelle; Dredze, Mark; Durme, Benjamin Van
Summarizing Entities using Distantly Supervised Information Extractors Inproceedings
In: SIGIR Workshop on Knowledge Graphs and Semantics for Text Retrieval, Analysis, and Understanding (KG4IR), 2018.
@inproceedings{Wolfe:2018il,
title = {Summarizing Entities using Distantly Supervised Information Extractors},
author = {Travis Wolfe and Annabelle Carrell and Mark Dredze and Benjamin Van Durme},
year = {2018},
date = {2018-01-01},
booktitle = {SIGIR Workshop on Knowledge Graphs and Semantics for Text Retrieval, Analysis, and Understanding (KG4IR)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Zhou, Yuchen; Dredze, Mark; Broniatowski, David A; Adler, William
Gab: The Alt-Right Social Media Platform Inproceedings
In: International Conference on Social Computing, Behavioral-Cultural Modeling & Prediction and Behavior Representation in Modeling and Simulation (SBP-BRiMS), 2018.
@inproceedings{Zhou:2018uk,
title = {Gab: The Alt-Right Social Media Platform},
author = {Yuchen Zhou and Mark Dredze and David A Broniatowski and William Adler},
year = {2018},
date = {2018-01-01},
booktitle = {International Conference on Social Computing, Behavioral-Cultural Modeling & Prediction and Behavior Representation in Modeling and Simulation (SBP-BRiMS)},
abstract = {This study proposes the use of Gab as a vehicle for political science research regarding modern American politics and the Alt-Right population. We collect several million Gab messages posted on Gab web- site from August 2016 to February 2018. We conduct a preliminary analysis of Gab platform related to site use, growth and topics, which shows that Gab is a reasonable resource for Alt-Right study.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
This study proposes the use of Gab as a vehicle for political science research regarding modern American politics and the Alt-Right population. We collect several million Gab messages posted on Gab web- site from August 2016 to February 2018. We conduct a preliminary analysis of Gab platform related to site use, growth and topics, which shows that Gab is a reasonable resource for Alt-Right study.
Smith, Katherine; Weiger, Caitlin; Fields, Errol; Cohen, Joanna E; Moran, Meghan; Dredze, Mark
Conducting public health surveillance research on consumer product websites Inproceedings
In: American Public Health Association (APHA), 2018.
@inproceedings{Smith:2018jl,
title = {Conducting public health surveillance research on consumer product websites},
author = {Katherine Smith and Caitlin Weiger and Errol Fields and Joanna E Cohen and Meghan Moran and Mark Dredze},
year = {2018},
date = {2018-01-01},
booktitle = {American Public Health Association (APHA)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Lama, Yuki; Chen, Tao; Dredze, Mark; Jamison, Amelia M; Quinn, Sandra C; Broniatowski, David A
Discordance Between Human Papillomavirus Twitter Images and Disparities in Human Papillomavirus Risk and Disease in the United States: Mixed-Methods Analysis Journal Article
In: Journal of Medical Internet Research (JMIR), 2018.
@article{Lama:2018ss,
title = {Discordance Between Human Papillomavirus Twitter Images and Disparities in Human Papillomavirus Risk and Disease in the United States: Mixed-Methods Analysis},
author = {Yuki Lama and Tao Chen and Mark Dredze and Amelia M Jamison and Sandra C Quinn and David A Broniatowski},
year = {2018},
date = {2018-01-01},
journal = {Journal of Medical Internet Research (JMIR)},
abstract = {Background: Racial and ethnic minorities are disproportionately affected by human papillomavirus (HPV)-related cancer, many of which could have been prevented with vaccination. Yet, the initiation and completion rates of HPV vaccination remain low among these populations. Given the importance of social media platforms for health communication, we examined US-based HPV images on Twitter. We explored inconsistencies between the demographics represented in HPV images and the populations that experience the greatest burden of HPV-related disease.
Objective: The objective of our study was to observe whether HPV images on Twitter reflect the actual burden of disease by select demographics and determine to what extent Twitter accounts utilized images that reflect the burden of disease in their health communication messages.
Methods: We identified 456 image tweets about HPV that contained faces posted by US users between November 11, 2014 and August 8, 2016. We identified images containing at least one human face and utilized Face++ software to automatically extract the gender, age, and race of each face. We manually annotated the source accounts of these tweets into 3 types as follows: government (38/298, 12.8%), organizations (161/298, 54.0%), and individual (99/298, 33.2%) and topics (news, health, and other) to examine how images varied by message source.
Results: Findings reflected the racial demographics of the US population but not the disease burden (795/1219, 65.22% white faces; 140/1219, 11.48% black faces; 71/1219, 5.82% Asian faces; and 213/1219, 17.47% racially ambiguous faces). Gender disparities were evident in the image faces; 71.70% (874/1219) represented female faces, whereas only 27.89% (340/1219) represented male faces. Among the 11-26 years age group recommended to receive HPV vaccine, HPV images contained more female-only faces (214/616, 34.3%) than males (37/616, 6.0%); the remainder of images included both male and female faces (365/616, 59.3%). Gender and racial disparities were present across different image sources. Faces from government sources were more likely to depict females (n=44) compared with males (n=16). Of male faces, 80% (12/15) of youth and 100% (1/1) of adults were white. News organization sources depicted high proportions of white faces (28/38, 97% of female youth and 12/12, 100% of adult males). Face++ identified fewer faces compared with manual annotation because of limitations with detecting multiple, small, or blurry faces. Nonetheless, Face++ achieved a high degree of accuracy with respect to gender, race, and age compared with manual annotation.
Conclusions: This study reveals critical differences between the demographics reflected in HPV images and the actual burden of disease. Racial minorities are less likely to appear in HPV images despite higher rates of HPV incidence. Health communication efforts need to represent populations at risk better if we seek to reduce disparities in HPV infection.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Background: Racial and ethnic minorities are disproportionately affected by human papillomavirus (HPV)-related cancer, many of which could have been prevented with vaccination. Yet, the initiation and completion rates of HPV vaccination remain low among these populations. Given the importance of social media platforms for health communication, we examined US-based HPV images on Twitter. We explored inconsistencies between the demographics represented in HPV images and the populations that experience the greatest burden of HPV-related disease.
Objective: The objective of our study was to observe whether HPV images on Twitter reflect the actual burden of disease by select demographics and determine to what extent Twitter accounts utilized images that reflect the burden of disease in their health communication messages.
Methods: We identified 456 image tweets about HPV that contained faces posted by US users between November 11, 2014 and August 8, 2016. We identified images containing at least one human face and utilized Face++ software to automatically extract the gender, age, and race of each face. We manually annotated the source accounts of these tweets into 3 types as follows: government (38/298, 12.8%), organizations (161/298, 54.0%), and individual (99/298, 33.2%) and topics (news, health, and other) to examine how images varied by message source.
Results: Findings reflected the racial demographics of the US population but not the disease burden (795/1219, 65.22% white faces; 140/1219, 11.48% black faces; 71/1219, 5.82% Asian faces; and 213/1219, 17.47% racially ambiguous faces). Gender disparities were evident in the image faces; 71.70% (874/1219) represented female faces, whereas only 27.89% (340/1219) represented male faces. Among the 11-26 years age group recommended to receive HPV vaccine, HPV images contained more female-only faces (214/616, 34.3%) than males (37/616, 6.0%); the remainder of images included both male and female faces (365/616, 59.3%). Gender and racial disparities were present across different image sources. Faces from government sources were more likely to depict females (n=44) compared with males (n=16). Of male faces, 80% (12/15) of youth and 100% (1/1) of adults were white. News organization sources depicted high proportions of white faces (28/38, 97% of female youth and 12/12, 100% of adult males). Face++ identified fewer faces compared with manual annotation because of limitations with detecting multiple, small, or blurry faces. Nonetheless, Face++ achieved a high degree of accuracy with respect to gender, race, and age compared with manual annotation.
Conclusions: This study reveals critical differences between the demographics reflected in HPV images and the actual burden of disease. Racial minorities are less likely to appear in HPV images despite higher rates of HPV incidence. Health communication efforts need to represent populations at risk better if we seek to reduce disparities in HPV infection.
Ayers, John W; Caputi, Theodore L; Nebeker, Camille; Dredze, Mark
Don't quote me: reverse identification of research participants in social media studies Journal Article
In: Nature Digital Medicine, vol. 1, no. 30, 2018.
@article{Ayers:2018eb,
title = {Don't quote me: reverse identification of research participants in social media studies},
author = {John W Ayers and Theodore L Caputi and Camille Nebeker and Mark Dredze},
year = {2018},
date = {2018-01-01},
journal = {Nature Digital Medicine},
volume = {1},
number = {30},
abstract = {We investigated if participants in social media surveillance studies could be reverse identified by reviewing all articles published on PubMed in 2015 or 2016 with the words ``Twitter'' and either ``read,'' ``coded,'' or ``content'' in the title or abstract. Seventy-two percent (95% CI: 63--80) of articles quoted at least one participant's tweet and searching for the quoted content led to the participant 84% (95% CI: 74--91) of the time. Twenty-one percent (95% CI: 13--29) of articles disclosed a participant's Twitter username thereby making the participant immediately identifiable. Only one article reported obtaining consent to disclose identifying information and institutional review board (IRB) involvement was mentioned in only 40% (95% CI: 31--50) of articles, of which 17% (95% CI: 10--25) received IRB-approval and 23% (95% CI:16--32) were deemed exempt. Biomedical publications are routinely including identifiable information by quoting tweets or revealing usernames which, in turn, violates ICMJE ethical standards governing scientific ethics, even though said content is scientifically unnecessary. We propose that authors convey aggregate findings without revealing participants' identities, editors refuse to publish reports that reveal a participant's identity, and IRBs attend to these privacy issues when reviewing studies involving social media data. These strategies together will ensure participants are protected going forward.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
We investigated if participants in social media surveillance studies could be reverse identified by reviewing all articles published on PubMed in 2015 or 2016 with the words ``Twitter'' and either ``read,'' ``coded,'' or ``content'' in the title or abstract. Seventy-two percent (95% CI: 63--80) of articles quoted at least one participant's tweet and searching for the quoted content led to the participant 84% (95% CI: 74--91) of the time. Twenty-one percent (95% CI: 13--29) of articles disclosed a participant's Twitter username thereby making the participant immediately identifiable. Only one article reported obtaining consent to disclose identifying information and institutional review board (IRB) involvement was mentioned in only 40% (95% CI: 31--50) of articles, of which 17% (95% CI: 10--25) received IRB-approval and 23% (95% CI:16--32) were deemed exempt. Biomedical publications are routinely including identifiable information by quoting tweets or revealing usernames which, in turn, violates ICMJE ethical standards governing scientific ethics, even though said content is scientifically unnecessary. We propose that authors convey aggregate findings without revealing participants' identities, editors refuse to publish reports that reveal a participant's identity, and IRBs attend to these privacy issues when reviewing studies involving social media data. These strategies together will ensure participants are protected going forward.
1345 entries « ‹ 1 of 27
› »