Improved Lexical Acquisition through DPP-based Verb Clustering

Subcategorization frames (SCFs), selectional preferences (SPs) and verb classes capture related aspects of the predicateargument structure. We present the first unified framework for unsupervised learning of these three types of information. We show how to utilize Determinantal Point Processes (DPPs), elegant probabilistic models that are defined over the possible subsets of a given dataset and give higher probability mass to high quality and diverse subsets, for clustering. Our novel clustering algorithm constructs a joint SCF-DPP DPP kernel matrix and utilizes the efficient sampling algorithms of DPPs to cluster together verbs with similar SCFs and SPs. We evaluate the induced clusters in the context of the three tasks and show results that are superior to strong baselines for each 1 .

[1]  Paula Chesley,et al.  Automatic extraction of subcategorization frames for French , 2006, LREC.

[2]  Anna Korhonen,et al.  Probabilistic models of similarity in syntactic context , 2011, EMNLP.

[3]  M. Pennacchiotti,et al.  Learning Selectional Preferences for Entailment or Paraphrasing Rules , 2007 .

[4]  George A. Miller,et al.  WordNet: A Lexical Database for English , 1995, HLT.

[5]  Anna Korhonen,et al.  Semantically Motivated Subcategorization Acquisition , 2002, ACL 2002.

[6]  Roberto Basili,et al.  Verb Subcategorization Kernels for Automatic Semantic Labeling , 2005, ACL 2005.

[7]  Beth Levin,et al.  English Verb Classes and Alternations: A Preliminary Investigation , 1993 .

[8]  Suzanne Stevenson,et al.  A General Feature Space for Automatic Verb Classification , 2003, EACL.

[9]  Ted Briscoe,et al.  Automatic Extraction of Subcategorization from Corpora , 1997, ANLP.

[10]  Anna Korhonen,et al.  Improving Verb Clustering with Automatically Acquired Selectional Preferences , 2009, EMNLP.

[11]  Yuval Krymolowski,et al.  Verb Class Discovery from Rich Syntactic Data , 2008, CICLing.

[12]  Ben Taskar,et al.  Structured Determinantal Point Processes , 2010, NIPS.

[13]  Ralph Grishman,et al.  Comlex Syntax: Building a Computational Lexicon , 1994, COLING.

[14]  Serena Villata,et al.  Automatic extraction of subcategorization frames for Italian , 2008, LREC.

[15]  Oren Etzioni,et al.  A Latent Dirichlet Allocation Method for Selectional Preferences , 2010, ACL.

[16]  Ben Taskar,et al.  Determinantal Point Processes for Machine Learning , 2012, Found. Trends Mach. Learn..

[17]  Ben Taskar,et al.  k-DPPs: Fixed-Size Determinantal Point Processes , 2011, ICML.

[18]  Diarmuid Ó Séaghdha.  Latent Variable Models of Selectional Preference , 2010, ACL.

[19]  Gertjan van Noord,et al.  Using Unknown Word Techniques to Learn Known Words , 2010, EMNLP.

[20]  Mats Rooth,et al.  Inducing a Semantically Annotated Lexicon via EM-Based Clustering , 1999, ACL.

[21]  Ben Taskar,et al.  Discovering Diverse and Salient Threads in Document Collections , 2012, EMNLP.

[22]  Daisuke Kawahara,et al.  Acquiring Reliable Predicate-argument Structures from Raw Corpora for Case Frame Compilation , 2010, LREC.

[23]  Anna Korhonen,et al.  Learning Syntactic Verb Frames using Graphical Models , 2012, ACL.

[24]  Tim Van de Cruys,et al.  A Non-negative Tensor Factorization Model for Selectional Preference Induction , 2009, Natural Language Engineering.

[25]  Nigel Collier,et al.  The Choice of Features for Classification of Verbs in Biomedical Texts , 2008, COLING.

[26]  Zoubin Ghahramani,et al.  Unsupervised and Constrained Dirichlet Process Mixture Models for Verb Clustering , 2009 .

[27]  Joseph Reisinger,et al.  Cross-Cutting Models of Lexical Semantics , 2011, EMNLP 2011.

[28]  Stefan Thater,et al.  Contextualizing Semantic Representations Using Syntactically Enriched Vector Models , 2010, ACL.

[29]  Ben Taskar,et al.  Learning Determinantal Point Processes , 2011, UAI.

[30]  Andy Way,et al.  Large-Scale Induction and Evaluation of Lexical Resources from the Penn-II and Penn-III Treebanks , 2005, Computational Linguistics.

[31]  Sabine Schulte im Walde.  Experiments on the Automatic Induction of German Semantic Verb Classes , 2006, CL.

[32]  Ted Briscoe,et al.  A System for Large-Scale Acquisition of Verbal, Nominal and Adjectival Subcategorization Frames from Corpora , 2007, ACL.

[33]  Vito Pirrelli,et al.  Unsupervised Acquisition of Verb Subcategorization Frames from Shallow-Parsed Corpora , 2008, LREC.

[34]  Thierry Poibeau,et al.  LexSchem: a Large Subcategorization Lexicon for French Verbs , 2008, LREC.

[35]  Martha Palmer,et al.  Investigations into the role of lexical semantics in word sense disambiguation , 2004 .

[36]  Patrick Pantel,et al.  LEDIR: An Unsupervised Algorithm for Learning Directionality of Inference Rules , 2007, EMNLP.

[37]  Thierry Poibeau,et al.  Multi-way Tensor Factorization for Unsupervised Lexical Acquisition , 2012, COLING.

[38]  Sabine Schulte im Walde,et al.  Combining EM Training and the MDL Principle for an Automatic Verb Classification Incorporating Selectional Preferences , 2008, ACL.

[39]  John B. Lowe,et al.  The Berkeley FrameNet Project , 1998, ACL.

[40]  Katrin Erk,et al.  A Simple, Similarity-based Model for Selectional Preferences , 2007, ACL.

[41]  Anna Korhonen,et al.  Hierarchical Verb Clustering Using Graph Factorization , 2011, EMNLP.

[42]  Mitchell P. Marcus,et al.  OntoNotes: The 90% Solution , 2006, NAACL.

[43]  Li Cai,et al.  Exploiting Web-Derived Selectional Preference to Improve Statistical Dependency Parsing , 2011, ACL.

[44]  Daniel Gildea,et al.  The Proposition Bank: An Annotated Corpus of Semantic Roles , 2005, CL.

[45]  Martha Palmer,et al.  Verbnet: a broad-coverage, comprehensive verb lexicon , 2005 .

[46]  Lei Shi,et al.  Putting Pieces Together: Combining FrameNet, VerbNet and WordNet for Robust Semantic Parsing , 2005, CICLing.

[47]  Laura Alonso Alemany,et al.  IRASubcat, a highly parametrizable, language independent tool for the acquisition of verbal subcategorization information from corpus , 2010, NAACL.

[48]  Eneko Agirre,et al.  Generalizing over Lexical Features: Selectional Preferences for Semantic Role Classification , 2009, ACL/IJCNLP.

[49]  Geoffrey E. Hinton.  Training Products of Experts by Minimizing Contrastive Divergence , 2002, Neural Computation.

[50]  Chris Brew,et al.  Which Are the Best Features for Automatic Verb Classification , 2008, ACL.

[51]  Mats Rooth,et al.  Valence Induction with a Head-Lexicalized PCFG , 1998, EMNLP.

[52]  Akshar Bharati,et al.  Inferring Semantic Roles Using Sub-Categorization Frames and Maximum Entropy Model , 2005, CoNLL.

[53]  Lukasz Debowski,et al.  Valence extraction using EM selection and co-occurrence matrices , 2009, Lang. Resour. Evaluation.

[54]  Eneko Agirre,et al.  Robustness and Generalization of Role Sets: PropBank vs. VerbNet , 2008, ACL.