A Supervised Algorithm for Verb Disambiguation into VerbNet Classes

VerbNet (VN) is a major large-scale English verb lexicon. Mapping verb instances to their VN classes has been proven useful for several NLP tasks. However, verbs are polysemous with respect to their VN classes. We introduce a novel supervised learning model for mapping verb instances to VN classes, using rich syntactic features and class membership constraints. We evaluate the algorithm in both in-domain and corpus adaptation scenarios. In both cases, we use the manually tagged Semlink WSJ corpus as training data. For indomain (testing on Semlink WSJ data), we achieve 95.9% accuracy, 35.1% error reduction (ER) over a strong baseline. For adaptation, we test on the GENIA corpus and achieve 72.4% accuracy with 10.7% ER. This is the first large-scale experimentation with automatic algorithms for this task.

[1]  Neville Ryant,et al.  Extending VerbNet with Novel Verb Classes , 2006, LREC.

[2]  Suzanne Stevenson,et al.  Automatic Verb Classification Based on Statistical Distributions of Argument Structure , 2001, CL.

[3]  Martha Palmer,et al.  Combining Lexical Resources: Mapping Between PropBank and VerbNet , 2006 .

[4]  Bernard E. M. Jones Towards a Syntactic Account of Punctuation , 1996, COLING.

[5]  Sabine Schulte im Walde Clustering Verbs Semantically According to their Alternation Behaviour , 2000, COLING.

[6]  Bonnie J. Dorr,et al.  Role of Word Sense Disalnbiguation in Lexical Acquisition: Predicting Semantics from Syntactic Cues , 1996, COLING.

[7]  MerloPaola,et al.  Automatic verb classification based on statistical distributions of argument structure , 2001 .

[8]  Karin Kipper Schuler,et al.  Argument Realization , 2006, Comput. Linguistics.

[9]  John Dunnion,et al.  Automatically building conceptual graphs using VerbNet and WordNet , 2004, ISICT.

[10]  D. Roth,et al.  Token-level Disambiguation of VerbNet classes , 2005 .

[11]  Min-Yen Kan,et al.  Role of Verbs in Document Analysis , 1998, ACL.

[12]  Jianguo Li Disambiguating Levin Verbs Using Untagged Data , 2007 .

[13]  Martha Palmer,et al.  Class-Based Construction of a Verb Lexicon , 2000, AAAI/IAAI.

[14]  Martha Palmer,et al.  Investigating Regular Sense Extensions Based on Intersective Levin Classes , 1998, COLING-ACL.

[15]  Bonnie J. Dorr,et al.  Large-Scale Dictionary Construction for Foreign Language Tutoring and Interlingual Machine Translation , 1998, Machine Translation.

[16]  Eugene Charniak,et al.  Coarse-to-Fine n-Best Parsing and MaxEnt Discriminative Reranking , 2005, ACL.

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

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

[19]  Dan Roth,et al.  A Sequential Model for Multi-Class Classification , 2001, EMNLP.

[20]  Ted Briscoe,et al.  Extended Lexical-Semantic Classification of English Verbs , 2004, HLT-NAACL 2004.

[21]  Rada Mihalcea,et al.  SenseLearner: Word Sense Disambiguation for All Words in Unrestricted Text , 2005, ACL.

[22]  Dan Roth,et al.  Learning to Resolve Natural Language Ambiguities: A Unified Approach , 1998, AAAI/IAAI.

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

[24]  Michael Collins,et al.  Head-Driven Statistical Models for Natural Language Parsing , 2003, CL.

[25]  Suzanne Stevenson,et al.  Exploiting a Verb Lexicon in Automatic Semantic Role Labelling , 2005, HLT.

[26]  Mirella Lapata,et al.  Verb Class Disambiguation Using Informative Priors , 2004, CL.

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

[28]  Jun'ichi Tsujii,et al.  GENIA corpus - a semantically annotated corpus for bio-textmining , 2003, ISMB.

[29]  Martha Palmer,et al.  Can Semantic Roles Generalize Across Genres? , 2007, NAACL.

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