2018
|
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 Nature Digital Medicine, 1 (30), 2018. Abstract | BibTeX @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. |
Wood-Doughty, Zachary; Shpitser, Ilya; Dredze, Mark Challenges of Using Text Classifiers for Causal Inference Inproceedings Empirical Methods in Natural Language Processing (EMNLP), 2018. Abstract | BibTeX @inproceedings{Wood-Doughty:2018qe,
title = {Challenges of Using Text Classifiers for Causal Inference},
author = {Zachary Wood-Doughty and Ilya Shpitser and Mark Dredze},
year = {2018},
date = {2018-01-01},
booktitle = {Empirical Methods in Natural Language Processing (EMNLP)},
abstract = {Causal understanding is essential for many kinds of decision-making, but causal inference from observational data has typically only been applied to structured, low-dimensional datasets. While text classifiers produce low-dimensional outputs, their use in causal inference has not previously been studied. To facilitate causal analyses based on language data, we consider the role that text classifiers can play in causal inference through established modeling mechanisms from the causality literature on missing data and measurement error. We demonstrate how to conduct causal analyses using text classifiers on simulated and Yelp data, and discuss the opportunities and challenges of future work that uses text data in causal inference.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Causal understanding is essential for many kinds of decision-making, but causal inference from observational data has typically only been applied to structured, low-dimensional datasets. While text classifiers produce low-dimensional outputs, their use in causal inference has not previously been studied. To facilitate causal analyses based on language data, we consider the role that text classifiers can play in causal inference through established modeling mechanisms from the causality literature on missing data and measurement error. We demonstrate how to conduct causal analyses using text classifiers on simulated and Yelp data, and discuss the opportunities and challenges of future work that uses text data in causal inference. |
Sekara, Vedran; Rutherford, Alex; Mann, Gideon; Dredze, Mark; Adler, Natalia; 'i, Manuel Garc Trends in the Adoption of Corporate Child Labor Policies: An Analysis with Bloomberg Terminal ESG Data Inproceedings Bloomberg Data for Good Exchange, 2018. Abstract | BibTeX @inproceedings{Sekara:2018uo,
title = {Trends in the Adoption of Corporate Child Labor Policies: An Analysis with Bloomberg Terminal ESG Data},
author = {Vedran Sekara and Alex Rutherford and Gideon Mann and Mark Dredze and Natalia Adler and Manuel Garc 'i},
year = {2018},
date = {2018-01-01},
booktitle = {Bloomberg Data for Good Exchange},
abstract = {Over 150 million children worldwide are estimated to be engaged in some form of child labor, with nearly one in every four children between the ages of 5 and 14 engaged in potentially harmful work in the world's poorest countries. Child labor compromises children's physical, mental, social and educational development. It also reinforces cycles of poverty, negatively affecting the ecosystem necessary for business to thrive in a sustainable manner. Against a backdrop of multiple international and national laws against child labor, corporations also adopt policies on child labor. However, new methods of globally dispersed production have made this commitment to sustainability issues across supply chains more challenging. In this work we examine, through the lens of Bloomberg's environmental, social and governance (ESG) and financial data, trends in corporate child labor policies and their relationship to classic economic variables as a first step in understanding sustainability issues across global supply networks.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Over 150 million children worldwide are estimated to be engaged in some form of child labor, with nearly one in every four children between the ages of 5 and 14 engaged in potentially harmful work in the world's poorest countries. Child labor compromises children's physical, mental, social and educational development. It also reinforces cycles of poverty, negatively affecting the ecosystem necessary for business to thrive in a sustainable manner. Against a backdrop of multiple international and national laws against child labor, corporations also adopt policies on child labor. However, new methods of globally dispersed production have made this commitment to sustainability issues across supply chains more challenging. In this work we examine, through the lens of Bloomberg's environmental, social and governance (ESG) and financial data, trends in corporate child labor policies and their relationship to classic economic variables as a first step in understanding sustainability issues across global supply networks. |
Wood-Doughty, Zachary; Andrews, Nicholas; Dredze, Mark Convolutions Are All You Need (For Classifying Character Sequences) Inproceedings EMNLP Workshop on Noisy User-generated Text (W-NUT), 2018. Abstract | BibTeX @inproceedings{Wood-Doughty:2018qd,
title = {Convolutions Are All You Need (For Classifying Character Sequences)},
author = {Zachary Wood-Doughty and Nicholas Andrews and Mark Dredze},
year = {2018},
date = {2018-01-01},
booktitle = {EMNLP Workshop on Noisy User-generated Text (W-NUT)},
abstract = {While recurrent neural networks (RNNs) are widely used for text classification, they demonstrate poor performance and slow convergence when trained on long sequences. When text is modeled as characters instead of words, the longer sequences make RNNs a poor choice. Convolutional neural networks (CNNs), although somewhat less ubiquitous than RNNs, have an internal structure more appropriate for long-distance character dependencies. To better understand how CNNs and RNNs differ in handling long sequences, we use them for text classification tasks in several character-level social media datasets. The CNN models vastly outperform the RNN models in our experiments, suggesting that CNNs are superior to RNNs at learning to classify character-level data.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
While recurrent neural networks (RNNs) are widely used for text classification, they demonstrate poor performance and slow convergence when trained on long sequences. When text is modeled as characters instead of words, the longer sequences make RNNs a poor choice. Convolutional neural networks (CNNs), although somewhat less ubiquitous than RNNs, have an internal structure more appropriate for long-distance character dependencies. To better understand how CNNs and RNNs differ in handling long sequences, we use them for text classification tasks in several character-level social media datasets. The CNN models vastly outperform the RNN models in our experiments, suggesting that CNNs are superior to RNNs at learning to classify character-level data. |
Benton, Adrian; Dredze, Mark Using Author Embeddings to Improve Tweet Stance Classification Inproceedings EMNLP Workshop on Noisy User-generated Text (W-NUT), 2018. Abstract | BibTeX @inproceedings{Benton:2018dk,
title = {Using Author Embeddings to Improve Tweet Stance Classification},
author = {Adrian Benton and Mark Dredze},
year = {2018},
date = {2018-01-01},
booktitle = {EMNLP Workshop on Noisy User-generated Text (W-NUT)},
abstract = {Many social media classification tasks analyze the content of a message, but do not consider the context of the message. For example, in tweet stance classification -- where a tweet is categorized according to a view-point it espouses -- the expressed viewpoint depends on latent beliefs held by the user. In this paper we investigate whether incorporating knowledge about the author can improve tweet stance classification. Furthermore, since author information and embeddings are often unavailable for labeled training examples, we propose a semi-supervised pre-training method to predict user embeddings. Although the neural stance classifiers we learn are often outperformed by a baseline SVM, author embedding pre-training yields improvements over a non-pre-trained neural network on four out of five domains in the SemEval 2016 6A tweet stance classification task. In a tweet gun control stance classification dataset, improvements from pre-training are only apparent when training data is limited.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Many social media classification tasks analyze the content of a message, but do not consider the context of the message. For example, in tweet stance classification -- where a tweet is categorized according to a view-point it espouses -- the expressed viewpoint depends on latent beliefs held by the user. In this paper we investigate whether incorporating knowledge about the author can improve tweet stance classification. Furthermore, since author information and embeddings are often unavailable for labeled training examples, we propose a semi-supervised pre-training method to predict user embeddings. Although the neural stance classifiers we learn are often outperformed by a baseline SVM, author embedding pre-training yields improvements over a non-pre-trained neural network on four out of five domains in the SemEval 2016 6A tweet stance classification task. In a tweet gun control stance classification dataset, improvements from pre-training are only apparent when training data is limited. |
Rouhizadeh, Masoud; Hatef, Elham; Dredze, Mark; Chute, Christopher; Kharrazi, Hadi Identifying Social Determinants of Health from Clinical Notes: A Rule-Based Approach Inproceedings AMIA Natural Language Processing Working Group Pre-Symposium, 2018. BibTeX @inproceedings{Rouhizadeh:2018fq,
title = {Identifying Social Determinants of Health from Clinical Notes: A Rule-Based Approach},
author = {Masoud Rouhizadeh and Elham Hatef and Mark Dredze and Christopher Chute and Hadi Kharrazi},
year = {2018},
date = {2018-01-01},
booktitle = {AMIA Natural Language Processing Working Group Pre-Symposium},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
'i, Moro-Velázquez Laureano Gómez-Garc J-A; Godino-Llorente, Juan Ignacio; Rusz, Jan; Skodda, Sabine; Arroyave, Orozco J R; Noth, Elmar; Dehak, Najim Study of the automatic detection of Parkison's Disease based on speaker recognition technologies and allophonic distillation Inproceedings Engineering in Medicine and Biology Society (EMBC),2018 40th Annual International Conference of the IEEE., pp. 1404–1407, 2018. BibTeX @inproceedings{moro2018study,
title = {Study of the automatic detection of Parkison's Disease based on speaker recognition technologies and allophonic distillation},
author = {J-A Moro-Velázquez Laureano Gómez-Garc{'i}a and Juan Ignacio Godino-Llorente and Jan Rusz and Sabine Skodda and J R Orozco Arroyave and Elmar Noth and Najim Dehak},
year = {2018},
date = {2018-01-01},
booktitle = {Engineering in Medicine and Biology Society (EMBC),2018 40th Annual International Conference of the IEEE.},
pages = {1404--1407},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Moro-Velazquez, Laureano; Gomez-Garcia, Jorge Andres; Godino-Llorente, Juan Ignacio; Villalba, Jesus; Orozco-Arroyave, Juan Rafael; Dehak, Najim Analysis of speaker recognition methodologies and the influence of kinetic changes to automatically detect Parkinson's Disease Journal Article Applied Soft Computing, 62 , pp. 649–666, 2018. BibTeX @article{moro2018analysis,
title = {Analysis of speaker recognition methodologies and the influence of kinetic changes to automatically detect Parkinson's Disease},
author = {Laureano Moro-Velazquez and Jorge Andres Gomez-Garcia and Juan Ignacio Godino-Llorente and Jesus Villalba and Juan Rafael Orozco-Arroyave and Najim Dehak},
year = {2018},
date = {2018-01-01},
journal = {Applied Soft Computing},
volume = {62},
pages = {649--666},
publisher = {Elsevier},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
|
Cotterell, Ryan; Kirov, Christo; Hulden, Mans; Eisner, Jason Quantifying the Trade-off Between Two Types of
Morphological Complexity Inproceedings Proceedings of the Society for Computation in
Linguistics (SCiL), Salt Lake City, 2018. Links | BibTeX @inproceedings{cotterell-et-al-2018-scil,
title = {Quantifying the Trade-off Between Two Types of
Morphological Complexity},
author = {Ryan Cotterell and Christo Kirov and Mans Hulden and Jason Eisner},
url = {http://cs.jhu.edu/~jason/papers/#cotterell-et-al-2018-scil},
year = {2018},
date = {2018-01-01},
booktitle = {Proceedings of the Society for Computation in
Linguistics (SCiL)},
volume = {1},
number = {30},
address = {Salt Lake City},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Wang, Dingquan; Eisner, Jason Predicting Fine-Grained Syntactic Typology from
Surface Features Inproceedings Proceedings of the Society for Computation in
Linguistics (SCiL), Salt Lake City, 2018. Links | BibTeX @inproceedings{wang-eisner-2018-scil,
title = {Predicting Fine-Grained Syntactic Typology from
Surface Features},
author = {Dingquan Wang and Jason Eisner},
url = {http://cs.jhu.edu/~jason/papers/#wang-eisner-2018-scil},
year = {2018},
date = {2018-01-01},
booktitle = {Proceedings of the Society for Computation in
Linguistics (SCiL)},
volume = {1},
number = {39},
address = {Salt Lake City},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Eisner, Jason Probabilistically Modeling Surface Patterns Using
Latent Structure Miscellaneous Invited talk at the 1st Annual Meeting of the Society
for Computation in Linguistics (SCiL), 2018. Links | BibTeX @misc{eisner-2018-scil,
title = {Probabilistically Modeling Surface Patterns Using
Latent Structure},
author = {Jason Eisner},
url = {http://cs.jhu.edu/~jason/papers/#eisner-2018-scil},
year = {2018},
date = {2018-01-01},
address = {Salt Lake City},
howpublished = {Invited talk at the 1st Annual Meeting of the Society
for Computation in Linguistics (SCiL)},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
|
Eisner, Jason; Filardo, Nathaniel Wesley Treating Machine Learning Algorithms as Declaratively
Specified Circuits Inproceedings Proceedings of the SysML Conference, Palo Alto, 2018. Links | BibTeX @inproceedings{filardo-eisner-2018-sysml,
title = {Treating Machine Learning Algorithms as Declaratively
Specified Circuits},
author = {Jason Eisner and Nathaniel Wesley Filardo},
url = {http://cs.jhu.edu/~jason/papers/#filardo-eisner-2018-sysml},
year = {2018},
date = {2018-01-01},
booktitle = {Proceedings of the SysML Conference},
address = {Palo Alto},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Mielke, Sebastian J; Eisner, Jason Spell Once, Summon Anywhere: A Two-Level
Open-Vocabulary Language Model Journal Article Computing Research Repository, 2018. Links | BibTeX @article{mielke-eisner-2018-arxiv,
title = {Spell Once, Summon Anywhere: A Two-Level
Open-Vocabulary Language Model},
author = {Sebastian J Mielke and Jason Eisner},
url = {http://cs.jhu.edu/~jason/papers/#mielke-eisner-2018-arxiv},
year = {2018},
date = {2018-01-01},
journal = {Computing Research Repository},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
|
Eisner, Jason Discrete Latent Variables in NLP: Good, Bad, and
Indifferent Miscellaneous Invited talk at ACL Workshop on Relevance of
Linguistic Structure in Neural Architectures for NLP, 2018. Links | BibTeX @misc{eisner-2018-relsnnlp,
title = {Discrete Latent Variables in NLP: Good, Bad, and
Indifferent},
author = {Jason Eisner},
url = {http://cs.jhu.edu/~jason/papers/#eisner-2018-relsnnlp},
year = {2018},
date = {2018-01-01},
address = {Melbourne},
howpublished = {Invited talk at ACL Workshop on Relevance of
Linguistic Structure in Neural Architectures for NLP},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
|
Wang, Dingquan; Eisner, Jason Synthetic Data Made to Order: The Case of Parsing Inproceedings Proceedings of the Conference on Empirical Methods in
Natural Language Processing (EMNLP), Brussels, 2018. Links | BibTeX @inproceedings{wang-eisner-2018-emnlp,
title = {Synthetic Data Made to Order: The Case of Parsing},
author = {Dingquan Wang and Jason Eisner},
url = {http://cs.jhu.edu/~jason/papers/#wang-eisner-2018-emnlp},
year = {2018},
date = {2018-01-01},
booktitle = {Proceedings of the Conference on Empirical Methods in
Natural Language Processing (EMNLP)},
address = {Brussels},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Mccree, Alan; Snyder, David; Sell, Gregory; Garcia-Romero, Daniel Language Recognition for Telephone and Video Speech: The JHU HLTCOE Submission for NIST LRE17 Inproceedings Proc. Odyssey 2018 The Speaker and Language Recognition Workshop, pp. 68–73, 2018. BibTeX @inproceedings{mccree2018language,
title = {Language Recognition for Telephone and Video Speech: The JHU HLTCOE Submission for NIST LRE17},
author = {Alan Mccree and David Snyder and Gregory Sell and Daniel Garcia-Romero},
year = {2018},
date = {2018-01-01},
booktitle = {Proc. Odyssey 2018 The Speaker and Language Recognition Workshop},
pages = {68--73},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Sell, Gregory; Duh, Kevin; Snyder, David; Etter, Dave; Garcia-Romero, Daniel Audio-Visual Person Recognition in Multimedia Data From the Iarpa Janus Program Inproceedings 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 3031–3035, IEEE 2018. BibTeX @inproceedings{sell2018audio,
title = {Audio-Visual Person Recognition in Multimedia Data From the Iarpa Janus Program},
author = {Gregory Sell and Kevin Duh and David Snyder and Dave Etter and Daniel Garcia-Romero},
year = {2018},
date = {2018-01-01},
booktitle = {2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
pages = {3031--3035},
organization = {IEEE},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Zhu, Yingke; Ko, Tom; Snyder, David; Mak, Brian; Povey, Daniel Self-Attentive Speaker Embeddings for Text-Independent Speaker Verification Inproceedings Proc. Interspeech 2018, pp. 3573–3577, 2018. Links | BibTeX @inproceedings{Zhu2018b,
title = {Self-Attentive Speaker Embeddings for Text-Independent Speaker Verification},
author = {Yingke Zhu and Tom Ko and David Snyder and Brian Mak and Daniel Povey},
url = {http://www.danielpovey.com/files/2018_interspeech_xvector_attention.pdf},
doi = {10.21437/Interspeech.2018-1158},
year = {2018},
date = {2018-01-01},
booktitle = {Proc. Interspeech 2018},
pages = {3573--3577},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Silnova, Anna; Brümmer, Niko; Garcia-Romero, Daniel; Snyder, David; Burget, Lukáš Fast Variational Bayes for Heavy-tailed PLDA Applied to i-vectors and x-vectors Inproceedings Proc. Interspeech 2018, pp. 72–76, 2018. Links | BibTeX @inproceedings{Silnova2018,
title = {Fast Variational Bayes for Heavy-tailed PLDA Applied to i-vectors and x-vectors},
author = {Anna Silnova and Niko Brümmer and Daniel Garcia-Romero and David Snyder and Lukáš Burget},
url = {http://dx.doi.org/10.21437/Interspeech.2018-2128},
doi = {10.21437/Interspeech.2018-2128},
year = {2018},
date = {2018-01-01},
booktitle = {Proc. Interspeech 2018},
pages = {72--76},
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 Proc. Interspeech 2018, pp. 2808–2812, 2018. Links | BibTeX @inproceedings{Sell2018b,
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://www.danielpovey.com/files/2018_interspeech_dihard.pdf},
doi = {10.21437/Interspeech.2018-1893},
year = {2018},
date = {2018-01-01},
booktitle = {Proc. Interspeech 2018},
pages = {2808--2812},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Snyder, David; Garcia-Romero, Daniel; McCree, Alan; Sell, Gregory; Povey, Daniel; Khudanpur, Sanjeev Spoken language recognition using x-vectors Inproceedings Odyssey: The Speaker and Language Recognition Workshop, Les Sables d’Olonne, 2018. Links | BibTeX @inproceedings{snyder2018spokenb,
title = {Spoken language recognition using x-vectors},
author = {David Snyder and Daniel Garcia-Romero and Alan McCree and Gregory Sell and Daniel Povey and Sanjeev Khudanpur},
url = {http://www.danielpovey.com/files/2018_odyssey_xvector_lid.pdf},
year = {2018},
date = {2018-01-01},
booktitle = {Odyssey: The Speaker and Language Recognition Workshop, Les Sables d’Olonne},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Snyder, D; Garcia-Romero, D; Sell, G; Povey, D; Khudanpur, S X-vectors: Robust DNN Embeddings for Speaker Recognition Inproceedings 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE 2018. Links | BibTeX @inproceedings{snyder2018xvector,
title = {X-vectors: Robust DNN Embeddings for Speaker Recognition},
author = {D Snyder and D Garcia-Romero and G Sell and D Povey and S Khudanpur},
url = {http://www.danielpovey.com/files/2018_icassp_xvectors.pdf},
year = {2018},
date = {2018-01-01},
booktitle = {2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
organization = {IEEE},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Subramanian, Aswin Shanmugam; Chen, Szu-Jui; Watanabe, Shinji Student-Teacher Learning for BLSTM Mask-based Speech Enhancement Inproceedings Proc. Interspeech 2018, pp. 3249–3253, 2018. Links | BibTeX @inproceedings{Subramanian2018,
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}
}
|
Cheng, Gaofeng; Povey, Daniel; Huang, Lu; Xu, Ji; Khudanpur, Sanjeev; Yan, Yonghong Output-Gate Projected Gated Recurrent Unit for Speech Recognition Journal Article Proc. Interspeech 2018, pp. 1793–1797, 2018. BibTeX @article{cheng2018output,
title = {Output-Gate Projected Gated Recurrent Unit for Speech Recognition},
author = {Gaofeng Cheng and Daniel Povey and Lu Huang and Ji Xu and Sanjeev Khudanpur and Yonghong Yan},
year = {2018},
date = {2018-01-01},
journal = {Proc. Interspeech 2018},
pages = {1793--1797},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
|
Sarma, Mousmita; Ghahremani, Pegah; Povey, Daniel; Goel, Nagendra Kumar; Sarma, Kandarpa Kumar; Dehak, Najim Emotion Identification from raw speech signals using DNNs Journal Article Proc. Interspeech 2018, pp. 3097–3101, 2018. BibTeX @article{sarma2018emotion,
title = {Emotion Identification from raw speech signals using DNNs},
author = {Mousmita Sarma and Pegah Ghahremani and Daniel Povey and Nagendra Kumar Goel and Kandarpa Kumar Sarma and Najim Dehak},
year = {2018},
date = {2018-01-01},
journal = {Proc. Interspeech 2018},
pages = {3097--3101},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
|
Sell, Gregory; Snyder, David; McCree, Alan; Garcia-Romero, Daniel; 'u, Jes; Maciejewski, Matthew; Manohar, Vimal; Dehak, Najim; Povey, Daniel; Watanabe, Shinji; others, Diarization is Hard: Some Experiences and Lessons Learned for the JHU Team in the Inaugural DIHARD Challenge Journal Article Proc. Interspeech 2018, pp. 2808–2812, 2018. BibTeX @article{sell2018diarization,
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 Jes{'u}s Villalba and Matthew Maciejewski and Vimal Manohar and Najim Dehak and Daniel Povey and Shinji Watanabe and others},
year = {2018},
date = {2018-01-01},
journal = {Proc. Interspeech 2018},
pages = {2808--2812},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
|
Ghahremani, Pegah; Nidadavolu, Phani Sankar; Chen, Nanxin; 'u, Jes; Povey, Daniel; Khudanpur, Sanjeev; Dehak, Najim End-to-End Deep Neural Network Age Estimation Journal Article Proc. Interspeech 2018, pp. 277–281, 2018. BibTeX @article{ghahremani2018end,
title = {End-to-End Deep Neural Network Age Estimation},
author = {Pegah Ghahremani and Phani Sankar Nidadavolu and Nanxin Chen and Jes{'u}s Villalba and Daniel Povey and Sanjeev Khudanpur and Najim Dehak},
year = {2018},
date = {2018-01-01},
journal = {Proc. Interspeech 2018},
pages = {277--281},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
|
Ghahremani, Pegah; Hadian, Hossein; Lv, Hang; Povey, Daniel; Khudanpur, Sanjeev Acoustic Modeling from Frequency Domain Representations of Speech Journal Article Proc. Interspeech 2018, pp. 1596–1600, 2018. BibTeX @article{ghahremani2018acoustic,
title = {Acoustic Modeling from Frequency Domain Representations of Speech},
author = {Pegah Ghahremani and Hossein Hadian and Hang Lv and Daniel Povey and Sanjeev Khudanpur},
year = {2018},
date = {2018-01-01},
journal = {Proc. Interspeech 2018},
pages = {1596--1600},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
|
Li, Ke; Xu, Hainan; Wang, Yiming; Povey, Daniel; Khudanpur, Sanjeev Recurrent Neural Network Language Model Adaptation for Conversational Speech Recognition Journal Article Proc. Interspeech 2018, pp. 3373–3377, 2018. BibTeX @article{li2018recurrent,
title = {Recurrent Neural Network Language Model Adaptation for Conversational Speech Recognition},
author = {Ke Li and Hainan Xu and Yiming Wang and Daniel Povey and Sanjeev Khudanpur},
year = {2018},
date = {2018-01-01},
journal = {Proc. Interspeech 2018},
pages = {3373--3377},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
|
Zhu, Yingke; Ko, Tom; Snyder, David; Mak, Brian; Povey, Daniel Self-Attentive Speaker Embeddings for Text-Independent Speaker Verification Journal Article Proc. Interspeech 2018, pp. 3573–3577, 2018. BibTeX @article{zhu2018self,
title = {Self-Attentive Speaker Embeddings for Text-Independent Speaker Verification},
author = {Yingke Zhu and Tom Ko and David Snyder and Brian Mak and Daniel Povey},
year = {2018},
date = {2018-01-01},
journal = {Proc. Interspeech 2018},
pages = {3573--3577},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
|
Povey, Daniel; Cheng, Gaofeng; Wang, Yiming; Li, Ke; Xu, Hainan; Yarmohamadi, Mahsa; Khudanpur, Sanjeev Semi-orthogonal low-rank matrix factorization for deep neural networks Journal Article INTERSPEECH (2018, submitted), 2018. BibTeX @article{povey2018semi,
title = {Semi-orthogonal low-rank matrix factorization for deep neural networks},
author = {Daniel Povey and Gaofeng Cheng and Yiming Wang and Ke Li and Hainan Xu and Mahsa Yarmohamadi and Sanjeev Khudanpur},
year = {2018},
date = {2018-01-01},
journal = {INTERSPEECH (2018, submitted)},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
|
Chen, Zhehuai; Luitjens, Justin; Xu, Hainan; Wang, Yiming; Povey, Daniel; Khudanpur, Sanjeev A GPU-based WFST Decoder with Exact Lattice Generation Journal Article arXiv preprint arXiv:1804.03243, 2018. BibTeX @article{chen2018gpu,
title = {A GPU-based WFST Decoder with Exact Lattice Generation},
author = {Zhehuai Chen and Justin Luitjens and Hainan Xu and Yiming Wang and Daniel Povey and Sanjeev Khudanpur},
year = {2018},
date = {2018-01-01},
journal = {arXiv preprint arXiv:1804.03243},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
|
Snyder, David; Garcia-Romero, Daniel; McCree, Alan; Sell, Gregory; Povey, Daniel; Khudanpur, Sanjeev Spoken language recognition using x-vectors Inproceedings Odyssey: The Speaker and Language Recognition Workshop, Les Sables d’Olonne, 2018. BibTeX @inproceedings{snyder2018spoken,
title = {Spoken language recognition using x-vectors},
author = {David Snyder and Daniel Garcia-Romero and Alan McCree and Gregory Sell and Daniel Povey and Sanjeev Khudanpur},
year = {2018},
date = {2018-01-01},
booktitle = {Odyssey: The Speaker and Language Recognition Workshop, Les Sables d’Olonne},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Manohar, Vimal; Hadian, Hossein; Povey, Daniel; Khudanpur, Sanjeev Semi-supervised training of acoustic models using lattice-free MMI Inproceedings 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4844–4848, IEEE 2018. BibTeX @inproceedings{manohar2018semi,
title = {Semi-supervised training of acoustic models using lattice-free MMI},
author = {Vimal Manohar and Hossein Hadian and Daniel Povey and Sanjeev Khudanpur},
year = {2018},
date = {2018-01-01},
booktitle = {2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
pages = {4844--4848},
organization = {IEEE},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Snyder, David; Garcia-Romero, Daniel; Sell, Gregory; Povey, Daniel; Khudanpur, Sanjeev X-vectors: Robust DNN embeddings for speaker recognition Journal Article Submitted to ICASSP, 2018. BibTeX @article{snyder2018x,
title = {X-vectors: Robust DNN embeddings for speaker recognition},
author = {David Snyder and Daniel Garcia-Romero and Gregory Sell and Daniel Povey and Sanjeev Khudanpur},
year = {2018},
date = {2018-01-01},
journal = {Submitted to ICASSP},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
|
Povey, Daniel; Hadian, Hossein; Ghahremani, Pegah; Li, Ke; Khudanpur, Sanjeev A Time-Restricted Self-Attention Layer for ASR Journal Article 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5874-5878, 2018. BibTeX @article{Povey2018ATS,
title = {A Time-Restricted Self-Attention Layer for ASR},
author = {Daniel Povey and Hossein Hadian and Pegah Ghahremani and Ke Li and Sanjeev Khudanpur},
year = {2018},
date = {2018-01-01},
journal = {2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
pages = {5874-5878},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
|
Hadian, Hossein; Sameti, Hossein; Povey, Daniel; Khudanpur, Sanjeev End-to-end Speech Recognition Using Lattice-free MMI 2018. BibTeX @unknown{unknownb,
title = {End-to-end Speech Recognition Using Lattice-free MMI},
author = {Hossein Hadian and Hossein Sameti and Daniel Povey and Sanjeev Khudanpur},
year = {2018},
date = {2018-01-01},
pages = {12-16},
keywords = {},
pubstate = {published},
tppubtype = {unknown}
}
|
2017
|
Wang, Dingquan; Peng, Nanyun; Duh, Kevin A Multi-task Learning Approach to Adapting Bilingual Word Embeddings for Cross-lingual Named Entity Recognition Inproceedings Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pp. 383–388, Asian Federation of Natural Language Processing, 2017. Links | BibTeX @inproceedings{wang17multitask,
title = {A Multi-task Learning Approach to Adapting Bilingual Word Embeddings for Cross-lingual Named Entity Recognition},
author = {Dingquan Wang and Nanyun Peng and Kevin Duh},
url = {http://www.aclweb.org/anthology/I17-2065},
year = {2017},
date = {2017-11-01},
booktitle = {Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers)},
pages = {383--388},
publisher = {Asian Federation of Natural Language Processing},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Cotterell, Ryan; Duh, Kevin Low-Resource Named Entity Recognition with Cross-lingual, Character-Level Neural Conditional Random Fields Inproceedings Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pp. 91–96, Asian Federation of Natural Language Processing, 2017. Links | BibTeX @inproceedings{cotterell17ner,
title = {Low-Resource Named Entity Recognition with Cross-lingual, Character-Level Neural Conditional Random Fields},
author = {Ryan Cotterell and Kevin Duh},
url = {http://www.aclweb.org/anthology/I17-2016},
year = {2017},
date = {2017-11-01},
booktitle = {Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers)},
pages = {91--96},
publisher = {Asian Federation of Natural Language Processing},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Khayrallah, Huda; Kumar, Gaurav; Duh, Kevin; Post, Matt; Koehn, Philipp Neural Lattice Search for Domain Adaptation in Machine Translation Inproceedings Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pp. 20–25, Asian Federation of Natural Language Processing, 2017. Links | BibTeX @inproceedings{khayrallah17adapt,
title = {Neural Lattice Search for Domain Adaptation in Machine Translation},
author = {Huda Khayrallah and Gaurav Kumar and Kevin Duh and Matt Post and Philipp Koehn},
url = {http://www.aclweb.org/anthology/I17-2004},
year = {2017},
date = {2017-11-01},
booktitle = {Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers)},
pages = {20--25},
publisher = {Asian Federation of Natural Language Processing},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
White, Aaron Steven; Rastogi, Pushpendre; Duh, Kevin; Durme, Benjamin Van Inference is Everything: Recasting Semantic Resources into a Unified Evaluation Framework Inproceedings Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pp. 996–1005, Asian Federation of Natural Language Processing, 2017. Links | BibTeX @inproceedings{white17inference,
title = {Inference is Everything: Recasting Semantic Resources into a Unified Evaluation Framework},
author = {Aaron Steven White and Pushpendre Rastogi and Kevin Duh and Benjamin Van Durme},
url = {http://www.aclweb.org/anthology/I17-1100},
year = {2017},
date = {2017-11-01},
booktitle = {Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)},
pages = {996--1005},
publisher = {Asian Federation of Natural Language Processing},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Shen, Yelong; Liu, Xiaodong; Duh, Kevin; Gao, Jianfeng An Empirical Analysis of Multiple-Turn Reasoning Strategies in Reading Comprehension Tasks Inproceedings Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pp. 957–966, Asian Federation of Natural Language Processing, 2017. Links | BibTeX @inproceedings{shen17reasoning,
title = {An Empirical Analysis of Multiple-Turn Reasoning Strategies in Reading Comprehension Tasks},
author = {Yelong Shen and Xiaodong Liu and Kevin Duh and Jianfeng Gao},
url = {http://www.aclweb.org/anthology/I17-1096},
year = {2017},
date = {2017-11-01},
booktitle = {Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)},
pages = {957--966},
publisher = {Asian Federation of Natural Language Processing},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Zhang, Sheng; Duh, Kevin; Durme, Benjamin Van Selective Decoding for Cross-lingual Open Information Extraction Inproceedings Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pp. 832–842, Asian Federation of Natural Language Processing, 2017. Links | BibTeX @inproceedings{zhang17selective,
title = {Selective Decoding for Cross-lingual Open Information Extraction},
author = {Sheng Zhang and Kevin Duh and Benjamin Van Durme},
url = {http://www.aclweb.org/anthology/I17-1084},
year = {2017},
date = {2017-11-01},
booktitle = {Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)},
pages = {832--842},
publisher = {Asian Federation of Natural Language Processing},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Ding, Shuoyang; Khayrallah, Huda; Koehn, Philipp; Post, Matt; Kumar, Gaurav; Duh, Kevin The JHU Machine Translation Systems for WMT 2017 Inproceedings Proceedings of the Second Conference on Machine Translation, pp. 276–282, Association for Computational Linguistics, Copenhagen, Denmark, 2017. Links | BibTeX @inproceedings{ding-EtAl:2017:WMT,
title = {The JHU Machine Translation Systems for WMT 2017},
author = {Shuoyang Ding and Huda Khayrallah and Philipp Koehn and Matt Post and Gaurav Kumar and Kevin Duh},
url = {http://www.aclweb.org/anthology/W17-4724},
year = {2017},
date = {2017-09-01},
booktitle = {Proceedings of the Second Conference on Machine Translation},
pages = {276--282},
publisher = {Association for Computational Linguistics},
address = {Copenhagen, Denmark},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Nadejde, Maria; Reddy, Siva; Sennrich, Rico; Dwojak, Tomasz; Junczys-Dowmunt, Marcin; Koehn, Philipp; Birch, Alexandra Predicting Target Language CCG Supertags Improves Neural Machine Translation Inproceedings Proceedings of the Second Conference on Machine Translation, pp. 68–79, Association for Computational Linguistics, Copenhagen, Denmark, 2017. Links | BibTeX @inproceedings{nadejde-EtAl:2017:WMT,
title = {Predicting Target Language CCG Supertags Improves Neural Machine Translation},
author = {Maria Nadejde and Siva Reddy and Rico Sennrich and Tomasz Dwojak and Marcin Junczys-Dowmunt and Philipp Koehn and Alexandra Birch},
url = {http://www.aclweb.org/anthology/W17-4707},
year = {2017},
date = {2017-09-01},
booktitle = {Proceedings of the Second Conference on Machine Translation},
pages = {68--79},
publisher = {Association for Computational Linguistics},
address = {Copenhagen, Denmark},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Bojar, Ondřej; Chatterjee, Rajen; Federmann, Christian; Graham, Yvette; Haddow, Barry; Huang, Shujian; Huck, Matthias; Koehn, Philipp; Liu, Qun; Logacheva, Varvara; Monz, Christof; Negri, Matteo; Post, Matt; Rubino, Raphael; Specia, Lucia; Turchi, Marco Findings of the 2017 Conference on Machine Translation (WMT17) Inproceedings Proceedings of the Second Conference on Machine Translation, pp. 169–214, Association for Computational Linguistics, Copenhagen, Denmark, 2017. Links | BibTeX @inproceedings{bojar-EtAl:2017:WMT1,
title = {Findings of the 2017 Conference on Machine Translation (WMT17)},
author = {Ondřej Bojar and Rajen Chatterjee and Christian Federmann and Yvette Graham and Barry Haddow and Shujian Huang and Matthias Huck and Philipp Koehn and Qun Liu and Varvara Logacheva and Christof Monz and Matteo Negri and Matt Post and Raphael Rubino and Lucia Specia and Marco Turchi},
url = {http://www.aclweb.org/anthology/W17-4717},
year = {2017},
date = {2017-09-01},
booktitle = {Proceedings of the Second Conference on Machine Translation},
pages = {169--214},
publisher = {Association for Computational Linguistics},
address = {Copenhagen, Denmark},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Xu, Hainan; Koehn, Philipp Zipporah: a Fast and Scalable Data Cleaning System for Noisy Web-Crawled Parallel Corpora Inproceedings Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pp. 2935–2940, Association for Computational Linguistics, Copenhagen, Denmark, 2017. Abstract | Links | BibTeX @inproceedings{xu-koehn:2017:EMNLP2017,
title = {Zipporah: a Fast and Scalable Data Cleaning System for Noisy Web-Crawled Parallel Corpora},
author = {Hainan Xu and Philipp Koehn},
url = {https://www.aclweb.org/anthology/D17-1318},
year = {2017},
date = {2017-09-01},
booktitle = {Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing},
pages = {2935--2940},
publisher = {Association for Computational Linguistics},
address = {Copenhagen, Denmark},
abstract = {We introduce Zipporah, a fast and scalable data cleaning system. We propose a
novel type of bag-of-words translation feature, and train logistic regression
models to classify good data and synthetic noisy data in the proposed feature
space. The trained model is used to score parallel sentences in the data pool
for selection. As shown in experiments, Zipporah selects a high-quality
parallel corpus from a large, mixed quality data pool. In particular, for one
noisy dataset, Zipporah achieves a 2.1 BLEU score improvement with using 1/5 of
the data over using the entire corpus.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
We introduce Zipporah, a fast and scalable data cleaning system. We propose a
novel type of bag-of-words translation feature, and train logistic regression
models to classify good data and synthetic noisy data in the proposed feature
space. The trained model is used to score parallel sentences in the data pool
for selection. As shown in experiments, Zipporah selects a high-quality
parallel corpus from a large, mixed quality data pool. In particular, for one
noisy dataset, Zipporah achieves a 2.1 BLEU score improvement with using 1/5 of
the data over using the entire corpus. |
Renduchintala, Adithya; Koehn, Philipp; Eisner, Jason Knowledge Tracing in Sequential Learning of Inflected Vocabulary Inproceedings Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017), pp. 238–247, Association for Computational Linguistics, Vancouver, Canada, 2017. Abstract | Links | BibTeX @inproceedings{renduchintala-koehn-eisner:2017:CoNLL,
title = {Knowledge Tracing in Sequential Learning of Inflected Vocabulary},
author = {Adithya Renduchintala and Philipp Koehn and Jason Eisner},
url = {http://aclweb.org/anthology/K17-1025},
year = {2017},
date = {2017-08-01},
booktitle = {Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017)},
pages = {238--247},
publisher = {Association for Computational Linguistics},
address = {Vancouver, Canada},
abstract = {We present a feature-rich knowledge tracing method that captures a student's
acquisition and retention of knowledge during a foreign language phrase
learning task. We model the student's behavior as making predictions under a
log-linear model, and adopt a neural gating mechanism to model how the student
updates their log-linear parameters in response to feedback. The gating
mechanism allows the model to learn complex patterns of retention and
acquisition for each feature, while the log-linear parameterization results in
an interpretable knowledge state. We collect human data and evaluate several
versions of the model.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
We present a feature-rich knowledge tracing method that captures a student's
acquisition and retention of knowledge during a foreign language phrase
learning task. We model the student's behavior as making predictions under a
log-linear model, and adopt a neural gating mechanism to model how the student
updates their log-linear parameters in response to feedback. The gating
mechanism allows the model to learn complex patterns of retention and
acquisition for each feature, while the log-linear parameterization results in
an interpretable knowledge state. We collect human data and evaluate several
versions of the model. |
Koehn, Philipp; Knowles, Rebecca Six Challenges for Neural Machine Translation Inproceedings Proceedings of the First Workshop on Neural Machine Translation, pp. 28–39, Association for Computational Linguistics, Vancouver, 2017. Abstract | Links | BibTeX @inproceedings{koehn-knowles:2017:NMT,
title = {Six Challenges for Neural Machine Translation},
author = {Philipp Koehn and Rebecca Knowles},
url = {http://www.aclweb.org/anthology/W17-3204},
year = {2017},
date = {2017-08-01},
booktitle = {Proceedings of the First Workshop on Neural Machine Translation},
pages = {28--39},
publisher = {Association for Computational Linguistics},
address = {Vancouver},
abstract = {We explore six challenges for neural machine translation: domain mismatch,
amount of training data, rare words, long sentences, word alignment, and beam
search. We show both deficiencies and improvements over the quality of
phrase-based statistical machine translation.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
We explore six challenges for neural machine translation: domain mismatch,
amount of training data, rare words, long sentences, word alignment, and beam
search. We show both deficiencies and improvements over the quality of
phrase-based statistical machine translation. |
Sakaguchi, Keisuke; Post, Matt; Durme, Benjamin Van Error-repair Dependency Parsing for Ungrammatical Texts Inproceedings Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pp. 189–195, Association for Computational Linguistics, Vancouver, Canada, 2017. Abstract | Links | BibTeX @inproceedings{sakaguchi-post-vandurme:2017:Short,
title = {Error-repair Dependency Parsing for Ungrammatical Texts},
author = {Keisuke Sakaguchi and Matt Post and Benjamin Van Durme},
url = {http://aclweb.org/anthology/P17-2030},
year = {2017},
date = {2017-07-01},
booktitle = {Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)},
pages = {189--195},
publisher = {Association for Computational Linguistics},
address = {Vancouver, Canada},
abstract = {We propose a new dependency parsing scheme which jointly parses a sentence and
repairs grammatical errors by extending the non-directional transition-based
formalism of Goldberg and Elhadad (2010) with three additional actions:
SUBSTITUTE, DELETE, INSERT. Because these actions may cause an infinite loop in
derivation, we also introduce simple constraints that ensure the parser
termination. We evaluate our model with respect to dependency accuracy and
grammaticality improvements for ungrammatical sentences, demonstrating the
robustness and applicability of our scheme.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
We propose a new dependency parsing scheme which jointly parses a sentence and
repairs grammatical errors by extending the non-directional transition-based
formalism of Goldberg and Elhadad (2010) with three additional actions:
SUBSTITUTE, DELETE, INSERT. Because these actions may cause an infinite loop in
derivation, we also introduce simple constraints that ensure the parser
termination. We evaluate our model with respect to dependency accuracy and
grammaticality improvements for ungrammatical sentences, demonstrating the
robustness and applicability of our scheme. |
