Two-Phased Event Relation Acquisition: Coupling the Relation-Oriented and Argument-Oriented Approaches

Addressing the task of acquiring semantic relations between events from a large corpus, we first argue the complementarity between the pattern-based relation-oriented approach and the anchor-based argument-oriented approach. We then propose a two-phased approach, which first uses lexico-syntactic patterns to acquire predicate pairs and then uses two types of anchors to identify shared arguments. The present results of our empirical evaluation on a large-scale Japanese Web corpus have shown that (a) the anchor-based filtering extensively improves the accuracy of predicate pair acquisition, (b) the two types of anchors are almost equally contributive and combining them improves recall without losing accuracy, and (c) the anchor-based method also achieves high accuracy in shared argument identification.

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

[2]  Yuji Matsumoto,et al.  Exploiting Syntactic Patterns as Clues in Zero-Anaphora Resolution , 2006, ACL.

[3]  Viktor Pekar.  Acquisition of Verb Entailment from Text , 2006, HLT-NAACL.

[4]  Patrick Pantel,et al.  Global Path-Based Refinement of Noisy Graphs Applied to Verb Semantics , 2005, IJCNLP.

[5]  Yuji Matsumoto,et al.  What Kinds and Amounts of Causal Knowledge Can Be Acquired from Text by Using Connective Markers as Clues? , 2003, Discovery Science.

[6]  Fabio Massimo Zanzotto,et al.  Discovering Asymmetric Entailment Relations between Verbs Using Selectional Preferences , 2006, ACL.

[7]  Ido Dagan,et al.  Scaling Web-based Acquisition of Entailment Relations , 2004, EMNLP.

[8]  Patrick Pantel,et al.  Espresso: Leveraging Generic Patterns for Automatically Harvesting Semantic Relations , 2006, ACL.

[9]  Dekang Lin,et al.  DIRT – Discovery of Inference Rules from Text , 2001 .

[10]  R. Iida,et al.  Learning-Based Argument Structure Analysis of Event-Nouns in Japanese , 2007 .

[11]  Patrick Pantel,et al.  DIRT @SBT@discovery of inference rules from text , 2001, KDD '01.

[12]  Zellig S. Harris,et al.  Mathematical structures of language , 1968, Interscience tracts in pure and applied mathematics.

[13]  Yuji Matsumoto,et al.  Acquiring Event Relation Knowledge by Learning Cooccurrence Patterns and Fertilizing Cooccurrence Samples with Verbal Nouns , 2008, IJCNLP.

[14]  Kentaro Torisawa.  Acquiring Inference Rules with Temporal Constraints by Using Japanese Coordinated Sentences and Noun-Verb Co-occurrences , 2006, HLT-NAACL.

[15]  Daisuke Kawahara,et al.  A Fully-Lexicalized Probabilistic Model for Japanese Syntactic and Case Structure Analysis , 2006, HLT-NAACL.