diff --git a/.gitIgnore b/.gitIgnore new file mode 100644 index 0000000000000000000000000000000000000000..6f36a75f603946b3c0e44b66c347b21cb7922379 --- /dev/null +++ b/.gitIgnore @@ -0,0 +1,6 @@ +*.aux +*.out +*.log +*.blg +*.pdf +*.bbl \ No newline at end of file diff --git a/emnlp.bib b/emnlp.bib new file mode 100644 index 0000000000000000000000000000000000000000..3013cf01648263d259129bdcb0b8e8b95212a56e --- /dev/null +++ b/emnlp.bib @@ -0,0 +1,556 @@ +@inproceedings{SocherEtAl2011:PoolRAE, + title={Dynamic pooling and unfolding recursive autoencoders for paraphrase detection}, + author={Socher, Richard and Huang, Eric H and Pennin, Jeffrey and Manning, Christopher D and Ng, Andrew Y}, + booktitle={Advances in Neural Information Processing Systems}, + pages={801--809}, + year={2011} +} + +@inproceedings{mikolov2013distributed, +title={Distributed representations of words and phrases and their compositionality}, +author={Mikolov, Tomas and Sutskever, Ilya and Chen, Kai and Corrado, Greg S and Dean, Jeff}, +booktitle={Advances in Neural Information Processing Systems}, +pages={3111--3119}, +year={2013} +} + +@article{chang2011libsvm, +title={LIBSVM: a library for support vector machines}, +author={Chang, Chih-Chung and Lin, Chih-Jen}, +journal={ACM Transactions on Intelligent Systems and Technology (TIST)}, +volume={2}, +number={3}, +pages={27}, +year={2011}, +publisher={ACM} +} + +@inproceedings{baroni2010nouns, +title={Nouns are vectors, adjectives are matrices: Representing adjective-noun constructions in semantic space}, +author={Baroni, Marco and Zamparelli, Roberto}, +booktitle={Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing}, +pages={1183--1193}, +year={2010}, +organization={Association for Computational Linguistics} +} + +@article{androutsopoulos2010survey, +title={A survey of paraphrasing and textual entailment methods}, +author={Androutsopoulos, Ion and Malakasiotis, Prodromos}, +journal={Journal of Artificial Intelligence Research}, +pages={135--187}, +year={2010} +} + +@inproceedings{zanzotto2010estimating, +title={Estimating linear models for compositional distributional semantics}, +author={Zanzotto, Fabio Massimo and Korkontzelos, Ioannis and Fallucchi, Francesca and Manandhar, Suresh}, +booktitle={Proceedings of the 23rd International Conference on Computational Linguistics}, +pages={1263--1271}, +year={2010}, +organization={Association for Computational Linguistics} +} + +@inproceedings{socher2010learning, +title={Learning continuous phrase representations and syntactic parsing with recursive neural networks}, +author={Socher, Richard and Manning, Christopher D and Ng, Andrew Y}, +booktitle={Proceedings of the NIPS-2010 Deep Learning and Unsupervised Feature Learning Workshop}, +pages={1--9}, +year={2010} +} + +@article{deerwester1990indexing, +title={Indexing by latent semantic analysis}, +author={Deerwester, Scott C. and Dumais, Susan T and Landauer, Thomas K. and Furnas, George W. and Harshman, Richard A.}, +journal={JAsIs}, +volume={41}, +number={6}, +pages={391--407}, +year={1990} +} + + +@inproceedings{bansal2014tailoring, +title={Tailoring continuous word representations for dependency parsing}, +author={Bansal, Mohit and Gimpel, Kevin and Livescu, Karen}, +booktitle={Proceedings of the Annual Meeting of the Association for Computational Linguistics}, +year={2014} +} + + +@article{bengio2003neural, +title={A neural probabilistic language model}, +author={Bengio, Yoshua and Ducharme, R{\'e}jean and Vincent, Pascal and Janvin, Christian}, +journal={The Journal of Machine Learning Research}, +volume={3}, +pages={1137--1155}, +year={2003}, +publisher={JMLR. org} +} + +@inproceedings{collobert2008unified, + title={A unified architecture for natural language processing: Deep neural networks with multitask learning}, + author={Collobert, Ronan and Weston, Jason}, + booktitle={Proceedings of the 25th international conference on Machine learning}, + pages={160--167}, + year={2008}, + organization={ACM} +} + +@inproceedings{yu2014improving, +title={Improving lexical embeddings with semantic knowledge}, +author={Yu, Mo and Dredze, Mark}, +booktitle={Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics}, +volume={2}, +pages={545--550}, +year={2014} +} + + +@book{firth1957synopsis, +title={A Synopsis of Linguistic Theory, 1930-1955}, +author={Firth, J.R.}, +url={http://books.google.com/books?id=T8LDtgAACAAJ}, +year={1957} +} + +@inproceedings{bannard2005paraphrasing, +title={Paraphrasing with bilingual parallel corpora}, +author={Bannard, Colin and Callison-Burch, Chris}, +booktitle={Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics}, +pages={597--604}, +year={2005}, +organization={Association for Computational Linguistics} +} + + +@InProceedings{yu-14, + author = {Yu, Mo and Dredze, Mark}, + title = {Improving Lexical Embeddings with Semantic Knowledge}, + booktitle = {Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)}, + month = {June}, + year = {2014}, + address = {Baltimore, Maryland}, + publisher = {Association for Computational Linguistics}, + pages = {545--550}, + url = {http://www.aclweb.org/anthology/P14-2089} +} + +@article{TACL586, + author = {Mo Yu and Mark Dredze}, + title = {Learning Composition Models for Phrase Embeddings}, + journal = {Transactions of the Association for Computational Linguistics}, + volume = {3}, + year = {2015}, + pages = {227--242} +} + +@inproceedings{hermann2013role, +title={The Role of Syntax in Vector Space Models of Compositional Semantics.}, +author={Hermann, Karl Moritz and Blunsom, Phil}, +booktitle={ACL (1)}, +pages={894--904}, +year={2013} +} + + +@article{do2009robust, +title={Robust, light-weight approaches to compute lexical similarity}, +author={Do, Quang and Roth, Dan and Sammons, Mark and Tu, Yuancheng and Vydiswaran, V}, +journal={Computer Science Research and Technical Reports, University of Illinois}, +year={2009} +} + + +@InProceedings{denkowski:lavie:meteor-wmt:2014, +author = {Michael Denkowski and Alon Lavie}, +title = {Meteor Universal: Language Specific Translation Evaluation for Any Target Language}, +booktitle = {Proceedings of the EACL 2014 Workshop on Statistical Machine Translation}, +year = {2014}, +} + + +@INPROCEEDINGS{Turian10wordrepresentations, + author = {Joseph Turian and Département D’informatique Et and Recherche Opérationnelle (diro and Université De Montréal and Lev Ratinov and Yoshua Bengio}, + title = {Word representations: A simple and general method for semisupervised learning}, + booktitle = {In ACL}, + year = {2010}, + pages = {384--394} +} + +@article{marelli2014semeval, + title={Semeval-2014 task 1: Evaluation of compositional distributional semantic models on full sentences through semantic relatedness and textual entailment}, + author={Marelli, Marco and Bentivogli, Luisa and Baroni, Marco and Bernardi, Raffaella and Menini, Stefano and Zamparelli, Roberto}, + journal={SemEval-2014}, + year={2014} +} + +@inproceedings{baroni2014don, +title={Don’t count, predict! A systematic comparison of context-counting vs. context-predicting semantic vectors}, +author={Baroni, Marco and Dinu, Georgiana and Kruszewski, Germ{\'a}n}, +booktitle={Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics}, +volume={1}, +year={2014} +} + +@incollection{dagan2006pascal, + title={The PASCAL recognising textual entailment challenge}, + author={Dagan, Ido and Glickman, Oren and Magnini, Bernardo}, + booktitle={Machine learning challenges. evaluating predictive uncertainty, visual object classification, and recognising tectual entailment}, + pages={177--190}, + year={2006}, + publisher={Springer} +} + +@inproceedings{yao2013semi, + title={Semi-Markov Phrase-Based Monolingual Alignment.}, + author={Yao, Xuchen and Van Durme, Benjamin and Callison-Burch, Chris and Clark, Peter}, + booktitle={EMNLP}, + pages={590--600}, + year={2013} +} + + +@InProceedings{hashimoto2014, +author = {Hashimoto, Kazuma and Stenetorp, Pontus and Miwa, Makoto +and Tsuruoka, Yoshimasa}, +title = {Jointly Learning Word Representations and +Composition Functions Using Predicate-Argument Structures}, +booktitle = {Proceedings of the 2014 Conference on Empirical Methods +in Natural Language Processing}, +publisher = {Association for Computational Linguistics}, +address = {Doha, Qatar}, +year = {2014}, +month = {October}, +day = {26}, +pdf_url = {http://pontus.stenetorp.se/res/pdf/hashimoto2014jointly.pdf}, +} + +@inproceedings{mitchell2008vector, +title={Vector-based Models of Semantic Composition.}, +author={Mitchell, Jeff and Lapata, Mirella}, +booktitle={ACL}, +pages={236--244}, +year={2008}, +organization={Citeseer} +} + + +@article{Mitchell:Lapata:2010, + author = {Mitchell, Jeff and Lapata, Mirella}, + title = {Composition in Distributional Models of Semantics}, + journal = {Cognitive Science}, + year = {2010}, + volume = {34}, + number = {8}, + pages = {1388--1439} + } + +@inproceedings{Blacoe2012, +author = {Blacoe, William and Lapata, Mirella}, +title = {A Comparison of Vector-based Representations for Semantic Composition}, +booktitle = {Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning}, +series = {EMNLP-CoNLL '12}, +year = {2012}, +location = {Jeju Island, Korea}, +pages = {546--556}, +numpages = {11}, +url = {http://dl.acm.org/citation.cfm?id=2390948.2391011}, +acmid = {2391011}, +publisher = {Association for Computational Linguistics}, +address = {Stroudsburg, PA, USA}, +} + +@article{HillRK14, +author = {Felix Hill and +Roi Reichart and +Anna Korhonen}, +title = {SimLex-999: Evaluating Semantic Models with (Genuine) Similarity Estimation}, +journal = {CoRR}, +volume = {abs/1408.3456}, +year = {2014}, +url = {http://arxiv.org/abs/1408.3456}, +timestamp = {Fri, 12 Sep 2014 12:44:21 +0200}, +biburl = {http://dblp.uni-trier.de/rec/bib/journals/corr/HillRK14}, +bibsource = {dblp computer science bibliography, http://dblp.org} +} + +@article{hill-14, + title={Not All Neural Embeddings are Born Equal}, + author={Hill, Felix and Cho, KyungHyun and Jean, Sebastien and Devin, Coline and Bengio, Yoshua}, + journal={arXiv preprint arXiv:1410.0718}, + year={2014} +} + +@inproceedings{GanitkevitchDC13, + added-at = {2013-11-11T00:00:00.000+0100}, + author = {Ganitkevitch, Juri and Durme, Benjamin Van and Callison-Burch, Chris}, + biburl = {http://www.bibsonomy.org/bibtex/223ca9e4d4cf7f52eb91bc77eeb04621f/dblp}, + booktitle = {HLT-NAACL}, + ee = {http://aclweb.org/anthology//N/N13/N13-1092.pdf}, + interhash = {a38fdffa6b4a71f7c80980e1ebb0038d}, + intrahash = {23ca9e4d4cf7f52eb91bc77eeb04621f}, + keywords = {dblp}, + pages = {758-764}, + publisher = {The Association for Computational Linguistics}, + timestamp = {2013-11-11T00:00:00.000+0100}, + title = {PPDB: The Paraphrase Database.}, + url = {http://dblp.uni-trier.de/db/conf/naacl/naacl2013.html#GanitkevitchDC13}, + year = 2013 +} + +@article{SocherKLMN14, + author = {Richard Socher and + Andrej Karpathy and + Quoc V. Le and + Christopher D. Manning and + Andrew Y. Ng}, + title = {Grounded Compositional Semantics for Finding and Describing Images + with Sentences}, + journal = {{TACL}}, + year = {2014}, + volume = {2}, + pages = {207--218}, + url = {http://www.transacl.org/wp-content/uploads/2014/04/52.pdf}, + timestamp = {Sat, 06 Sep 2014 17:27:02 +0200}, + biburl = {http://dblp.uni-trier.de/rec/bib/journals/tacl/SocherKLMN14}, + bibsource = {dblp computer science bibliography, http://dblp.org} +} + +@article{Duchi, + author = {Duchi, John and Hazan, Elad and Singer, Yoram}, + title = {Adaptive Subgradient Methods for Online Learning and Stochastic Optimization}, + journal = {J. Mach. Learn. Res.}, + issue_date = {2/1/2011}, + volume = {12}, + month = jul, + year = {2011}, + issn = {1532-4435}, + pages = {2121--2159}, + numpages = {39}, + url = {http://dl.acm.org/citation.cfm?id=1953048.2021068}, + acmid = {2021068}, + publisher = {JMLR.org}, +} + +@inproceedings{agirre2009study, + title={A study on similarity and relatedness using distributional and WordNet-based approaches}, + author={Agirre, Eneko and Alfonseca, Enrique and Hall, Keith and Kravalova, Jana and Pa{\c{s}}ca, Marius and Soroa, Aitor}, + booktitle={Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics}, + pages={19--27}, + year={2009}, + organization={Association for Computational Linguistics} +} + +@inproceedings{finkelstein2001placing, + title={Placing search in context: The concept revisited}, + author={Finkelstein, Lev and Gabrilovich, Evgeniy and Matias, Yossi and Rivlin, Ehud and Solan, Zach and Wolfman, Gadi and Ruppin, Eytan}, + booktitle={Proceedings of the 10th international conference on World Wide Web}, + pages={406--414}, + year={2001}, + organization={ACM} +} + +@article{steiger1980tests, +title={Tests for comparing elements of a correlation matrix.}, +author={Steiger, James H}, +journal={Psychological Bulletin}, +volume={87}, +number={2}, +pages={245}, +year={1980}, +publisher={American Psychological Association} +} + +@inproceedings{berant2014semantic, +title={Semantic parsing via paraphrasing}, +author={Berant, Jonathan and Liang, Percy}, +booktitle={Proceedings of ACL}, +year={2014} +} + + +@article{mikolov2013efficient, + title={Efficient estimation of word representations in vector space}, + author={Mikolov, Tomas and Chen, Kai and Corrado, Greg and Dean, Jeffrey}, + journal={arXiv preprint arXiv:1301.3781}, + year={2013} +} + +@InProceedings{marton-09, + author = {Marton, Yuval and Callison-Burch, Chris and Resnik, Philip}, + title = {Improved Statistical Machine Translation Using Monolingually-Derived Paraphrases}, + booktitle = {Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing}, + month = {August}, + year = {2009}, + address = {Singapore}, + publisher = {Association for Computational Linguistics}, + pages = {381--390}, + url = {http://www.aclweb.org/anthology/D/D09/D09-1040} +} + +@InProceedings{rastogi2014augmenting, + author = {Rastogi, Pushpendre and Van Durme, Benjamin}, + title = {Augmenting {FrameNet} Via {PPDB}}, + booktitle = {Proceedings of the Second Workshop on EVENTS: Definition, Detection, Coreference, and Representation}, + month = {June}, + year = {2014}, + address = {Baltimore, Maryland, USA}, + publisher = {Association for Computational Linguistics}, + pages = {1--5}, + url = {http://www.aclweb.org/anthology/W14-2901} +} + +@article{seaghdha2014probabilistic, +title={Probabilistic Distributional Semantics with Latent Variable Models}, +author={S{\'e}aghdha, Diarmuid {\'O} and Korhonen, Anna}, +year={2014}, +publisher={MIT Press} +} + + +@article{bjerva2014meaning, + title={The Meaning Factory: Formal Semantics for Recognizing Textual Entailment and Determining Semantic Similarity}, + author={Bjerva, Johannes and Bos, Johan and van der Goot, Rob and Nissim, Malvina}, + journal={SemEval 2014}, + pages={642}, + year={2014} +} + +@InProceedings{kim-14, + author = {Kim, Yoon}, + title = {Convolutional Neural Networks for Sentence Classification}, + booktitle = {Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, + month = {October}, + year = {2014}, + address = {Doha, Qatar}, + publisher = {Association for Computational Linguistics}, + pages = {1746--1751}, + url = {http://www.aclweb.org/anthology/D14-1181} +} + +@InProceedings{socher-13, + author = {Socher, Richard and Perelygin, Alex and Wu, Jean and Chuang, Jason and Manning, Christopher D. and Ng, Andrew and Potts, Christopher}, + title = {Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank}, + booktitle = {Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing}, + month = {October}, + year = {2013}, + address = {Seattle, Washington, USA}, + publisher = {Association for Computational Linguistics}, + pages = {1631--1642}, + url = {http://www.aclweb.org/anthology/D13-1170} +} + +@InProceedings{rinaldi-03, + author = {Fabio Rinaldi and James Dowdall and Kaarel Kaljurand and Michael Hess and Diego Moll\'{a}}, + title = {Exploiting Paraphrases in a Question Answering System}, + booktitle = {Proceedings of the Second International Workshop on Paraphrasing}, + month = {July}, + year = {2003}, + address = {Sapporo, Japan}, + publisher = {Association for Computational Linguistics}, + pages = {25--32}, + url = {http://www.aclweb.org/anthology/W03-1604}, + doi = {10.3115/1118984.1118988} +} + +@InProceedings{fader-13, + author = {Fader, Anthony and Zettlemoyer, Luke and Etzioni, Oren}, + title = {Paraphrase-Driven Learning for Open Question Answering}, + booktitle = {Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, + month = {August}, + year = {2013}, + address = {Sofia, Bulgaria}, + publisher = {Association for Computational Linguistics}, + pages = {1608--1618}, + url = {http://www.aclweb.org/anthology/P13-1158} +} + +@inproceedings{bosma-06, + author = {Bosma, Wauter and Callison-Burch, Chris}, + title = {Paraphrase Substitution for Recognizing Textual Entailment}, + booktitle = {Proceedings of the 7th International Conference on Cross-Language Evaluation Forum: Evaluation of Multilingual and Multi-modal Information Retrieval}, + series = {CLEF'06}, + year = {2007}, + isbn = {3-540-74998-5, 978-3-540-74998-1}, + location = {Alicante, Spain}, + pages = {502--509}, + numpages = {8}, + url = {http://dl.acm.org/citation.cfm?id=2393955.2394025}, + acmid = {2394025}, + publisher = {Springer-Verlag}, + address = {Berlin, Heidelberg}, +} + +@inproceedings{faruqui-14, +title={Retrofitting Word Vectors to Semantic Lexicons}, +author={Manaal Faruqui and Jesse Dodge and Sujay Jauhar and Chris Dyer and Ed Hovy and Noah A. Smith}, +booktitle={Proc. of Deep Learning and Representation Learning Workshop, NIPS}, +year={2014} +} + +@InProceedings{faruqui-15, + author = {Faruqui, Manaal and Dodge, Jesse and Jauhar, Sujay Kumar and Dyer, Chris and Hovy, Eduard and Smith, Noah A.}, + title = {Retrofitting Word Vectors to Semantic Lexicons}, + booktitle = {Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies}, + year = {2015}, + pages = {1606--1615}, +} + +@InProceedings{PavlickEtAl-2015:ACL:Semantics, + author = {Ellie Pavlick and Johan Bos and Malvina Nissim and Charley Beller and Benjamin Van Durme and Chris Callison-Burch}, + title = {Adding Semantics to Data-Driven Paraphrasing}, + booktitle = {Association for Computational Linguistics}, + year = {2015}, +} + +@inproceedings{dolan-05, + title={Automatically constructing a corpus of sentential paraphrases}, + author={Dolan, William B and Brockett, Chris}, + booktitle={Proc. of IWP}, + year={2005} +} + + +@inproceedings{dolan-04, + author = {Dolan, Bill and Quirk, Chris and Brockett, Chris}, + title = {Unsupervised Construction of Large Paraphrase Corpora: Exploiting Massively Parallel News Sources }, + booktitle = {Proceedings of Coling 2004 }, + editor = {}, + year = 2004, + month = {Aug 23--Aug 27}, + address = {Geneva, Switzerland}, + publisher = {COLING}, + pages = {350--356} +} + +@inproceedings{quirk-04, + author = {Quirk, Chris and Brockett, Chris and Dolan, William}, + title = {Monolingual Machine Translation for Paraphrase Generation }, + booktitle = {Proceedings of EMNLP 2004}, + editor = {Dekang Lin and Dekai Wu}, + year = 2004, + month = {July}, + address = {Barcelona, Spain}, + publisher = {Association for Computational Linguistics}, + pages = {142--149} +} + +@InProceedings{manning-EtAl:2014:P14-5, +author = {Manning, Christopher D. and Surdeanu, Mihai and Bauer, John and Finkel, Jenny and Bethard, Steven J. and McClosky, David}, +title = {The {Stanford} {CoreNLP} Natural Language Processing Toolkit}, +booktitle = {Proceedings of 52nd Annual Meeting of the Association for Computational Linguistics: System Demonstrations}, +year = {2014}, +pages = {55--60}, +url = {http://www.aclweb.org/anthology/P/P14/P14-5010} +} + +@article{pennington2014glove, +title={Glove: Global vectors for word representation}, +author={Pennington, Jeffrey and Socher, Richard and Manning, Christopher D}, +journal={Proceedings of the Empiricial Methods in Natural Language Processing (EMNLP 2014)}, +volume={12}, +year={2014} +} + + diff --git a/emnlp2015.tex b/emnlp2015.tex index 3a09fa062473943a30b858bdd324fe039b6d6c2b..23c796d1deb0087156286c29f51482da4cc823b8 100644 --- a/emnlp2015.tex +++ b/emnlp2015.tex @@ -21,8 +21,46 @@ \usepackage{times} \usepackage{url} \usepackage{latexsym} - +\usepackage{amsmath,amssymb} +\usepackage{multirow} +\usepackage{color} +\usepackage{graphicx} +\usepackage{bbm} +\usepackage{xspace} +\usepackage{wasysym} +\usepackage{latexsym} +\usepackage{graphicx} +\usepackage{algorithmic} +\usepackage{float} +\usepackage{mathtools} +\usepackage{array} +\usepackage{graphics} +\usepackage{comment} +\usepackage{caption} +\usepackage[hidelinks]{hyperref} + +\captionsetup{font=footnotesize} \newcommand{\jwcomment}[1]{\textcolor{cyan}{\bf \small [ #1 --JW]}} + +\newcommand{\dev}{\textsc{dev}\xspace} +\newcommand{\test}{\textsc{test}\xspace} +\newcommand{\avg}{\textsc{avg}\xspace} +\newcommand{\mostsim}{\textsc{MostSim}\xspace} +\newcommand{\leastup}{\textsc{LeastUpdate}\xspace} +\newcommand{\skipgram}{skip-gram\xspace} +\newcommand{\glove}{glove\xspace} +\newcommand{\annoppdb}{Annotated-PPDB\xspace} +\newcommand{\boldparagram}{\textbf{Paragram}\xspace} +\newcommand{\paragram}{\textsc{paragram}\xspace} +\newcommand{\annoppdbthreek}{Annotated-PPDB-3K\xspace} +\newcommand{\mlpara}{ML-Paraphrase\xspace} +\newcommand{\wsall}{WS353\xspace} +\newcommand{\wssim}{WS-S\xspace} +\newcommand{\wsrel}{WS-R\xspace} +\newcommand{\simlex}{SL999\xspace} +\newcommand{\latentalign}{LatentAlign\xspace} +\newcommand{\newllm}{NewLLM\xspace} +\newcommand{\lclr}{LCLR\xspace} %\setlength\titlebox{5cm} % You can expand the titlebox if you need extra space @@ -56,23 +94,36 @@ We present a straight-forward algorithm that gives state-of-the-art results on t Text similarity and textual entailment are important tasks for NLP \jwcomment{Talk about why these are important with citations. Not sure what to put here - maybe talk about the need for downstream task evaluations as well as the importance of word and phrase embeddings}. In this paper, we make the following contributions: \vspace{2pt} + \noindent\textbf{Introduce a strong baseline} for both tasks. In fact, it gives state-of-the-art performance on the entailment task. + \noindent\textbf{Provide a state-of-the-art model} blah + \section{Related Work} +There has been a lot of interest in word embeddings ... + +But recently a variety of methods have been developed to create phrase embeddings cute socher me naacl short. + +In this work we show that with a straight forward and easy to implement Model we can ibtain state of the art on an entailmemt task and also use this midel to evaluate the suitability of these word and phrase embeddings on entailment and paraphrase tasks. + +Latent alignment approaches have been used before fir paraphrase detection and textual entailment. Our work differs in twi major waysFor one, our model is not limited to binary classification. Secondly our model isvan online approach that linearly goes theough the training data. This in contrast to lclr that linearly goes through the positive examles in the dataset but goes theough the negative examples repeatedly until alignments are no longer added to a cach. Thus in practice , this creates unpredictability as the algorithm can be stuck in this loop a long time without making much progress towards the glibal solution. Lastly, our model is easy to implement and can be optimized with just sgd making it suitsble for the evaluation of word and phrase dmbeddings. + + +We evaluate on both the textual entailment snd paraphrase tasks from sem eval. We experiment with the two predominant embeddings in use today cite glive and skipgram as well as embeddings explicitely geared towards paragrasing cite me. We also experimnet with \section{Latent Alignment Model} Given two sentences, we seek to align each token to either: (1) a token in the other sentence or (2) a NULL token. In the second case. the token can be seen to be deleted. Thus given a loss function $l$, our model becomes: \begin{equation} -$x+y$ +x+y \end{equation} In the Sem-Eval task, textual entailment is a multi-class problem with three classes (Entailment, Contradiction, and Neutral), while textual similarity is a regression problem. We chose to model both problems as regression, by mapping the entailment labels to real numbers (Contradiction=0, Neural=1, Entailment=2) allowing us to be able to use the same model for both tasks. For a loss function, we chose regularized square loss: \begin{equation} -$z+t$ -end{equation} +z+t +\end{equation} Our model, \latentalign, can of course handle arbitrary features, but one of the goals of this work was to create a strong baseline model. Thus we simply just used what we call "word-word" features. These are binary features that, for a given word pair, $w_1$ and $w_2$, have a value of 1 if $w_1$ is aligned to $w_2$ and 0 otherwise. @@ -141,7 +192,7 @@ Results \section{Conclusion} -\bibliographystyle{ref.bib} +\bibliographystyle{emnlp.bib} \bibliography{acl2015} \end{document} diff --git a/make.sh b/make.sh new file mode 100755 index 0000000000000000000000000000000000000000..de8374166d5aa01c55079e81f11822964d34e62e --- /dev/null +++ b/make.sh @@ -0,0 +1,5 @@ +#!/bin/sh +pdflatex emnlp2015.tex +bibtex emnlp2015 +pdflatex emnlp2015.tex +pdflatex emnlp2015.tex \ No newline at end of file diff --git a/make_clean.sh b/make_clean.sh new file mode 100644 index 0000000000000000000000000000000000000000..1c30988d5cb02dc7df963f3d2a5525eaaa4e3be9 --- /dev/null +++ b/make_clean.sh @@ -0,0 +1,5 @@ +rm *.log +rm *.aux +rm *.bbl +rm *.blg +rm *.out \ No newline at end of file