Ganitkevitch, Juri; Durme, Benjamin Van; Callison-Burch, Chris
Monolingual Distributional Similarity for Text-to-Text Generation Inproceedings
In: *SEM First Joint Conference on Lexical and Computational Semantics, Association for Computational Linguistics, Montreal, 2012.
@inproceedings{Ganitkevitch-etal:2012:StarSEM,
title = {Monolingual Distributional Similarity for Text-to-Text Generation},
author = {Juri Ganitkevitch and Benjamin Van Durme and Chris Callison-Burch},
year = {2012},
date = {2012-01-01},
booktitle = {*SEM First Joint Conference on Lexical and Computational Semantics},
publisher = {Association for Computational Linguistics},
address = {Montreal},
abstract = {Previous work on paraphrase extraction and application has relied on either parallel datasets, or on distributional similarity metrics over large text corpora. Our approach combines these two orthogonal sources of information and directly integrates them into our paraphrasing system’s log-linear model. We compare different distributional similarity feature-sets and show significant improvements in grammaticality and meaning retention on the example text-to-text generation task of sentence compression, achieving state-of-the-art quality.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Callison-Burch, Chris; Koehn, Philipp; Monz, Christof; Post, Matt; Soricut, Radu; Specia, Lucia
Findings of the 2012 Workshop on Statistical Machine Translation Inproceedings
In: Proceedings of the Seventh Workshop on Statistical Machine Translation, pp. 10–51, Association for Computational Linguistics, Montr'eal, Canada, 2012.
@inproceedings{callisonburch-EtAl:2012:WMT,
title = {Findings of the 2012 Workshop on Statistical Machine Translation},
author = {Chris Callison-Burch and Philipp Koehn and Christof Monz and Matt Post and Radu Soricut and Lucia Specia},
year = {2012},
date = {2012-01-01},
booktitle = {Proceedings of the Seventh Workshop on Statistical Machine Translation},
pages = {10--51},
publisher = {Association for Computational Linguistics},
address = {Montr'eal, Canada},
abstract = {This paper presents the results of the WMT12 shared tasks, which included a translation task, a task for machine translation evaluation metrics, and a task for run-time estimation of machine translation quality. We conducted a large-scale manual evaluation of 103 machine translation systems submitted by 34 teams. We used the ranking of these systems to mea- sure how strongly automatic metrics correlate with human judgments of translation quality for 12 evaluation metrics. We introduced a new quality estimation task this year, and evaluated submissions from 11 teams.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Zbib, Rabih; Malchiodi, Erika; Devlin, Jacob; Stallard, David; Matsoukas, Spyros; Schwartz, Richard; Makhoul, John; Zaidan, Omar; Callison-Burch, Chris
Machine Translation of Arabic Dialects Inproceedings
In: The 2012 Conference of the North American Chapter of the Association for Computational Linguistics, Association for Computational Linguistics, Montreal, 2012.
@inproceedings{Zbib-etal:2012:NAACLb,
title = {Machine Translation of Arabic Dialects},
author = {Rabih Zbib and Erika Malchiodi and Jacob Devlin and David Stallard and Spyros Matsoukas and Richard Schwartz and John Makhoul and Omar Zaidan and Chris Callison-Burch},
year = {2012},
date = {2012-01-01},
booktitle = {The 2012 Conference of the North American Chapter of the Association for Computational Linguistics},
publisher = {Association for Computational Linguistics},
address = {Montreal},
abstract = {Arabic dialects present many challenges for machine translation, not least of which is the lack of data resources. We use crowdsourcing to cheaply and quickly build Levantine-English and Egyptian-English parallel corpora, consisting of 1.1M words and 380k words, respectively. The dialect sentences are selected from a large corpus of Arabic web text, and translated using Mechanical Turk. We use this data to build Dialect Arabic MT systems. Small amounts of dialect data have a dramatic impact on the quality of translation. When translating Egyptian and Levantine test sets, our Dialect Arabic MT system performs 5.8 and 6.8 BLEU points higher than a Modern Standard Arabic MT system trained on a 150 million word Arabic-English parallel corpus -- over 100 times the amount of data as our dialect corpora.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Briesch, Doug; Hobbs, Reginald; Jaja, Claire; Kjersten, Brian; Voss, Clare
Training and Evaluating a Statistical Part of Speech Tagger for Natural Language Applications using Kepler Workflows Journal Article
In: Procedia Computer Science, pp. 1588 - 1594, 2012.
@article{Briesch20121588,
title = {Training and Evaluating a Statistical Part of Speech Tagger for Natural Language Applications using Kepler Workflows},
author = {Doug Briesch and Reginald Hobbs and Claire Jaja and Brian Kjersten and Clare Voss},
year = {2012},
date = {2012-01-01},
journal = {Procedia Computer Science},
pages = {1588 - 1594},
abstract = {A core technology of natural language processing (NLP) incorporated into many text processing applications is a part of speech (POS) tagger, a software component that labels words in text with syntactic tags such as noun, verb, adjective, etc. These tags may then be used within more complex tasks such as parsing, question answering, and machine translation (MT). In this paper we describe the phases of our work training and evaluating statistical POS taggers on Arabic texts and their English translations using Kepler workflows. While the original objectives for encapsulating our research code within Kepler workflows were driven by software engineering needs to document and verify the re usability of our software, our research benefitted as well: the ease of rapid retraining and testing enabled our researchers to detect reporting discrepancies, document their source, independently validating the correct results.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Napoles, Courtney; Gormley, Matt; Durme, Benjamin Van
Annotated Gigaword Inproceedings
In: AKBC-WEKEX Workshop at NAACL 2012, 2012.
@inproceedings{napoles-EtAl:2012:Agiga,
title = {Annotated Gigaword},
author = {Courtney Napoles and Matt Gormley and Benjamin Van Durme},
year = {2012},
date = {2012-01-01},
booktitle = {AKBC-WEKEX Workshop at NAACL 2012},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Kjersten, Brian; Durme, Benjamin Van
Space Efficiencies in Discourse Modeling via Conditional Random Sampling Inproceedings
In: 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 513-517, Association for Computational Linguistics, Montreal, Canada, 2012.
@inproceedings{KjerstenVanDurme2012,
title = {Space Efficiencies in Discourse Modeling via Conditional Random Sampling},
author = {Brian Kjersten and Benjamin Van Durme},
year = {2012},
date = {2012-01-01},
booktitle = {2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies},
pages = {513-517},
publisher = {Association for Computational Linguistics},
address = {Montreal, Canada},
abstract = {Recent exploratory efforts in discourse-level language modeling have relied heavily on calculating Pointwise Mutual Information (PMI), which involves significant computation when done over large collections. Prior work has required aggressive pruning or independence assumptions to compute scores on large collections. We show the method of Conditional Random Sampling, thus far an underutilized technique, to be a space-efficient means of representing the sufficient statistics in discourse that underly recent PMI-based work. This is demonstrated in the context of inducing Shankian script-like structures over news articles.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Filardo, Nathaniel; Eisner, Jason
A Flexible Solver for Finite Arithmetic Circuits Inproceedings
In: Technical Communications of the 28th International Conference on Logic Programming, ICLP 2012, 2012.
@inproceedings{filardo-eisner-2012-iclp,
title = {A Flexible Solver for Finite Arithmetic Circuits},
author = {Nathaniel Filardo and Jason Eisner},
year = {2012},
date = {2012-01-01},
booktitle = {Technical Communications of the 28th International Conference on Logic Programming, ICLP 2012},
abstract = {Arithmetic circuits arise in the context of weighted logic programming languages, such as Datalog with aggregation, or Dyna. A weighted logic program defines a generalized arithmetic circuit—the weighted version of a proof forest, with nodes having arbitrary rather than boolean values. In this paper, we focus on finite circuits. We present a flexible algorithm for efficiently textitquerying node values as they change under textitupdates to the circuit's inputs. Unlike traditional algorithms, ours is agnostic about which nodes are tabled (materialized), and can vary smoothly between the traditional strategies of forward and backward chaining. Our algorithm is designed to admit future generalizations, including cyclic and infinite circuits and propagation of delta updates.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Jiang, Jiarong; Teichert, Adam; Daumé, Hal; Eisner, Jason
Learned Prioritization for Trading Off Accuracy and Speed Inproceedings
In: ICML Workshop on Inferning: Interactions between Inference and Learning, 2012.
@inproceedings{jiang-et-al-2012-icmlw,
title = {Learned Prioritization for Trading Off Accuracy and Speed},
author = {Jiarong Jiang and Adam Teichert and Hal Daumé and Jason Eisner},
year = {2012},
date = {2012-01-01},
booktitle = {ICML Workshop on Inferning: Interactions between Inference and Learning},
abstract = {Users want natural language processing (NLP) systems to be both fast and accurate, but quality often comes at the cost of speed. The field has been manually exploring various speed-accuracy tradeoffs for particular problems or datasets. We aim to explore this space automatically, focusing here on the case of agenda-based syntactic parsing (Kay, 1986). Unfortunately, off-the-shelf reinforcement learning techniques fail to learn good policies: the state space is too large to explore naively. We propose a hybrid reinforcement/apprenticeship learning algorithm that, even with few inexpensive features, can automatically learn weights that achieve competitive accuracies at significant improvements in speed over state-of-the-art baselines.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
He, He; Daumé, Hal; Eisner, Jason
Cost-Sensitive Dynamic Feature Selection Inproceedings
In: ICML Workshop on Inferning: Interactions between Inference and Learning, 2012.
@inproceedings{he-et-al-2012-icmlw,
title = {Cost-Sensitive Dynamic Feature Selection},
author = {He He and Hal Daumé and Jason Eisner},
year = {2012},
date = {2012-01-01},
booktitle = {ICML Workshop on Inferning: Interactions between Inference and Learning},
abstract = {We present an instance-specific test-time dynamic feature selection algorithm. Our algorithm sequentially chooses features given previously selected features and their values. It stops the selection process to make a prediction according to a user-specified accuracy-cost trade-off. We cast the sequential decision-making problem as a Markov Decision Process and apply imitation learning techniques. We address the problem of learning and inference jointly in a simple multiclass classification setting. Experimental results on UCI datasets show that our approach achieves the same or higher accuracy using only a small fraction of features than static feature selection methods.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Stoyanov, Veselin; Eisner, Jason
Fast and Accurate Prediction via Evidence-Specific MRF Structure Inproceedings
In: ICML Workshop on Inferning: Interactions between Inference and Learning, 2012.
@inproceedings{stoyanov-eisner-2012-icmlw,
title = {Fast and Accurate Prediction via Evidence-Specific MRF Structure},
author = {Veselin Stoyanov and Jason Eisner},
year = {2012},
date = {2012-01-01},
booktitle = {ICML Workshop on Inferning: Interactions between Inference and Learning},
abstract = {We are interested in speeding up approximate inference in Markov Random Fields (MRFs). We present a new method that uses gates—binary random variables that determine which factors of the MRF to use. Which gates are open depends on the observed evidence; when many gates are closed, the MRF takes on a sparser and faster structure that omits "unnecessary" factors. We train parameters that control the gates, jointly with the ordinary MRF parameters, in order to locally minimize an objective that combines loss and runtime.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Paul, Michael; Eisner, Jason
Implicitly Intersecting Weighted Automata using Dual Decomposition Inproceedings
In: Proceedings of NAACL-HLT, pp. 232–242, 2012.
@inproceedings{paul-eisner-2012-naacl,
title = {Implicitly Intersecting Weighted Automata using Dual Decomposition},
author = {Michael Paul and Jason Eisner},
year = {2012},
date = {2012-01-01},
booktitle = {Proceedings of NAACL-HLT},
pages = {232--242},
abstract = {We propose an algorithm to find the best path through an intersection of arbitrarily many weighted automata, without actually performing the intersection. The algorithm is based on dual decomposition: the automata attempt to agree on a string by communicating about features of the string. We demonstrate the algorithm on the Steiner consensus string problem, both on synthetic data and on consensus decoding for speech recognition. This involves implicitly intersecting up to 100 automata.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Smith, Jason; Eisner, Jason
Unsupervised Learning on an Approximate Corpus Inproceedings
In: Proceedings of NAACL-HLT, pp. 131–141, 2012.
@inproceedings{smith-eisner-2012,
title = {Unsupervised Learning on an Approximate Corpus},
author = {Jason Smith and Jason Eisner},
year = {2012},
date = {2012-01-01},
booktitle = {Proceedings of NAACL-HLT},
pages = {131--141},
abstract = {Unsupervised learning techniques can take advantage of large amounts of unannotated text, but the largest text corpus (the Web) is not easy to use in its full form. Instead, we have statistics about this corpus in the form of n-gram counts (Brants and Franz, 2006). While n-gram counts do not directly provide sentences, a distribution over sentences can be estimated from them in the same way that textitn-gram language models are estimated. We treat this distribution over sentences as an approximate corpus and show how unsupervised learning can be performed on such a corpus using variational inference. We compare hidden Markov model (HMM) training on exact and approximate corpora of various sizes, measuring speed and accuracy on unsupervised part-of-speech tagging.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Stoyanov, Veselin; Eisner, Jason
Minimum-Risk Training of Approximate CRF-Based NLP Systems Inproceedings
In: Proceedings of NAACL-HLT, pp. 120–130, 2012.
@inproceedings{stoyanov-eisner-2012-naacl,
title = {Minimum-Risk Training of Approximate CRF-Based NLP Systems},
author = {Veselin Stoyanov and Jason Eisner},
year = {2012},
date = {2012-01-01},
booktitle = {Proceedings of NAACL-HLT},
pages = {120--130},
abstract = {Conditional Random Fields (CRFs) are a popular formalism for structured prediction in NLP. It is well known how to train CRFs with certain topologies that admit exact inference, such as linear-chain CRFs. Some NLP phenomena, however, suggest CRFs with more complex topologies. Should such models be used, considering that they make exact inference intractable? Stoyanov et al. (2011) re- cently argued for training parameters to minimize the task-specific loss of whatever approximate inference and decoding methods will be used at test time. We apply their method to three NLP problems, showing that (i) using more complex CRFs leads to improved performance, and that (ii) minimum-risk training learns more accurate models.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Sanchez-Vega, Francisco; Eisner, Jason; Younes, Laurent; Geman, Donald
Learning Multivariate Distributions by Competitive Assembly of Marginals Journal Article
In: IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012.
@article{sanchezvega-et-al-2012,
title = {Learning Multivariate Distributions by Competitive Assembly of Marginals},
author = {Francisco Sanchez-Vega and Jason Eisner and Laurent Younes and Donald Geman},
year = {2012},
date = {2012-01-01},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
abstract = {We present a new framework for learning high-dimensional multivariate probability distributions from estimated marginals. The approach is motivated by compositional models and Bayesian networks, and designed to adapt to small sample sizes. We start with a large, overlapping set of elementary statistical building blocks, or "primitives," which are low-dimensional marginal distributions learned from data. Each variable may appear in many primitives. Subsets of primitives are combined in a lego-like fashion to construct a probabilistic graphical model; only a small fraction of the primitives will participate in any valid construction. Since primitives can be precomputed, parameter estimation and structure search are separated. Model complexity is controlled by strong biases; we adapt the primitives to the amount of training data and impose rules which restrict the merging of them into allowable compositions. The likelihood of the data decomposes into a sum of local gains, one for each primitive in the final structure. We focus on a specific subclass of networks which are binary forests. Structure optimization corresponds to an integer linear program and the maximizing composition can be computed for reasonably large numbers of variables. Performance is evaluated using both synthetic data and real datasets from natural language processing and computational biology.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Gormley, Matt; Dredze, Mark; Durme, Benjamin Van; Eisner, Jason
Shared Components Topic Models Inproceedings
In: Proceedings of NAACL-HLT, pp. 783–792, 2012.
@inproceedings{gormley-et-al-2012-naacl,
title = {Shared Components Topic Models},
author = {Matt Gormley and Mark Dredze and Benjamin Van Durme and Jason Eisner},
year = {2012},
date = {2012-01-01},
booktitle = {Proceedings of NAACL-HLT},
pages = {783--792},
abstract = {With a few exceptions, extensions to latent Dirichlet allocation (LDA) have focused on the distribution over topics for each document. Much less attention has been given to the underlying structure of the topics themselves. As a result, most topic models generate topics independently from a single underlying distribution and require millions of parameters, in the form of multinomial distributions over the vocabulary. In this paper, we introduce the Shared Components Topic Model (SCTM), in which each topic is a normalized product of a smaller number of underlying component distributions. Our model learns these component distributions and the structure of how to combine subsets of them into topics. The SCTM can represent topics in a much more compact representation than LDA and achieves better perplexity with fewer parameters.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Bergsma, Shane; Post, Matt; Yarowsky, David
Stylometric Analysis of Scientific Articles Inproceedings
In: Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 327–337, Association for Computational Linguistics, Montr'eal, Canada, 2012.
@inproceedings{bergsma-post-yarowsky:2012:NAACL-HLT,
title = {Stylometric Analysis of Scientific Articles},
author = {Shane Bergsma and Matt Post and David Yarowsky},
year = {2012},
date = {2012-01-01},
booktitle = {Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies},
pages = {327--337},
publisher = {Association for Computational Linguistics},
address = {Montr'eal, Canada},
abstract = {We present an approach to automatically recover hidden attributes of scientific articles, such as whether the author is a native English speaker, whether the author is a male or a female, and whether the paper was published in a conference or workshop proceedings. We train classifiers to predict these attributes in computational linguistics papers. The classifiers perform well in this challenging domain, identifying non-native writing with 95% accuracy (over a baseline of 67%). We show the benefits of using syntactic features in stylometry; syntax leads to significant improvements over bag-of-words models on all three tasks, achieving 10% to 25% relative error reduction. We give a detailed analysis of which words and syntax most predict a particular attribute, and we show a strong correlation between our predictions and a paper’s number of citations.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Ferraro, Francis; Post, Matt; Durme, Benjamin Van
Judging Grammaticality with Count-Induced Tree Substitution Grammars Inproceedings
In: Proceedings of the Seventh Workshop on Building Educational Applications Using NLP, pp. 116–121, Association for Computational Linguistics, Montr'eal, Canada, 2012.
@inproceedings{ferraro-post-vandurme:2012:BEA,
title = {Judging Grammaticality with Count-Induced Tree Substitution Grammars},
author = {Francis Ferraro and Matt Post and Benjamin Van Durme},
year = {2012},
date = {2012-01-01},
booktitle = {Proceedings of the Seventh Workshop on Building Educational Applications Using NLP},
pages = {116--121},
publisher = {Association for Computational Linguistics},
address = {Montr'eal, Canada},
abstract = {Prior work has shown the utility of syntactic tree fragments as features in judging the grammaticality of text. To date such fragments have been extracted from derivations of Bayesian-induced Tree Substitution Grammars (TSGs). Evaluating on discriminative coarse and fine grammaticality classification tasks, we show that a simple, deterministic, count-based approach to fragment identification performs on par with the more complicated grammars of Post (2011). This represents a significant reduction in complexity for those interested in the use of such fragments in the development of systems for the educational domain.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Ferraro, Francis; Durme, Benjamin Van; Post, Matt
Toward Tree Substitution Grammars with Latent Annotations Inproceedings
In: Proceedings of the NAACL-HLT Workshop on the Induction of Linguistic Structure, pp. 23–30, Association for Computational Linguistics, Montr'eal, Canada, 2012.
@inproceedings{ferraro-vandurme-post:2012:WILS,
title = {Toward Tree Substitution Grammars with Latent Annotations},
author = {Francis Ferraro and Benjamin Van Durme and Matt Post},
year = {2012},
date = {2012-01-01},
booktitle = {Proceedings of the NAACL-HLT Workshop on the Induction of Linguistic Structure},
pages = {23--30},
publisher = {Association for Computational Linguistics},
address = {Montr'eal, Canada},
abstract = {We provide a model that extends the split-merge framework of Petrov et al. (2006) to jointly learn latent annotations and Tree Substitution Grammars (TSGs). We then conduct a variety of experiments with this model, first inducing grammars on a portion of the Penn Treebank and the Korean Treebank 2.0, and next experimenting with grammar refinement from a single nonterminal and from the Universal Part of Speech tagset. We present qualitative analysis showing promising signs across all experiments that our combined approach successfully provides for greater flexibility in grammar induction within the structured guidance provided by the treebank, leveraging the complementary natures of these two approaches.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Yao, Xuchen; Durme, Benjamin Van; Callison-Burch, Chris
Expectations of Word Sense in Parallel Corpora Inproceedings
In: NAACL, 2012.
@inproceedings{Yao2012NAACL,
title = {Expectations of Word Sense in Parallel Corpora},
author = {Xuchen Yao and Benjamin Van Durme and Chris Callison-Burch},
year = {2012},
date = {2012-01-01},
booktitle = {NAACL},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Yao, Xuchen; Bouma, Gosse; Zhang, Zhaonian
Semantics-based Question Generation and Implementation Journal Article
In: Dialogue and Discourse, Special Issue on Question Generation, pp. 11-42, 2012.
@article{Yao2012DDqg,
title = {Semantics-based Question Generation and Implementation},
author = {Xuchen Yao and Gosse Bouma and Zhaonian Zhang},
year = {2012},
date = {2012-01-01},
journal = {Dialogue and Discourse, Special Issue on Question Generation},
pages = {11-42},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
There are no upcoming events.