Generative Modeling of Coordination by Factoring Parallelism and Selectional Preferences

We present a unified generative model of coordination that considers parallelism of conjuncts and selectional preferences. Parallelism of conjuncts, which frequently characterizes coordinate structures, is modeled as a synchronized generation process in the generative parser. Selectional preferences learned from a large web corpus provide an important clue for resolving the ambiguities of coordinate structures. Our experiments of Japanese dependency parsing indicate the effectiveness of our approach, particularly in the domains of newspapers and patents.

[1]  Daisuke Kawahara,et al.  Case Frame Compilation from the Web using High-Performance Computing , 2006, LREC.

[2]  Preslav Nakov,et al.  Using the Web as an Implicit Training Set: Application to Structural Ambiguity Resolution , 2005, HLT.

[3]  Jason Eisner,et al.  Three New Probabilistic Models for Dependency Parsing: An Exploration , 1996, COLING.

[4]  Daisuke Kawahara,et al.  Coordination Disambiguation without Any Similarities , 2008, COLING.

[5]  Deirdre Hogan,et al.  Coordinate Noun Phrase Disambiguation in a Generative Parsing Model , 2007, ACL.

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

[7]  Manabu Sassano,et al.  Linear-Time Dependency Analysis for Japanese , 2004, COLING.

[8]  Frank Keller,et al.  Integrating Syntactic Priming into an Incremental Probabilistic Parser, with an Application to Psycholinguistic Modeling , 2006, ACL.

[9]  Frank Keller,et al.  Parallelism in Coordination as an Instance of Syntactic Priming: Evidence from Corpus-based Modeling , 2005, HLT.

[10]  Philip Resnik,et al.  Semantic Similarity in a Taxonomy: An Information-Based Measure and its Application to Problems of Ambiguity in Natural Language , 1999, J. Artif. Intell. Res..

[11]  Dekang Lin,et al.  Automatic Retrieval and Clustering of Similar Words , 1998, ACL.

[12]  Makoto Nagao,et al.  Building a Japanese parsed corpus while improving the parsing system , 1997 .

[13]  Makoto Nagao,et al.  A Syntactic Analysis Method of Long Japanese Sentences Based on the Detection of Conjunctive Structures , 1994, CL.

[14]  Rajeev Agarwal,et al.  A Simple but Useful Approach to Conjunct Identification , 1992, ACL.

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

[16]  Masashi Shimbo,et al.  A Discriminative Learning Model for Coordinate Conjunctions , 2007, EMNLP.

[17]  A. Kilgarriff,et al.  Disambiguating coordinations using word distribution information , 2005 .

[18]  Erhard W. Hinrichs,et al.  Parsing Coordinations , 2009, EACL.

[19]  Yuji Matsumoto,et al.  Coordinate Structure Analysis with Global Structural Constraints and Alignment-Based Local Features , 2009, ACL/IJCNLP.

[20]  Yuji Matsumoto,et al.  Japanese Dependency Analysis using Cascaded Chunking , 2002, CoNLL.