A Compositional Approach toward Dynamic Phrasal Thesaurus

To enhance the technology for computing semantic equivalence, we introduce the notion of phrasal thesaurus which is a natural extension of conventional word-based the saurus. Among a variety of phrases that conveys the same meaning, i.e., paraphrases, we focus on syntactic variants that are compositionally explainable using a small number of atomic knowledge, and develop a system which dynamically generates such variants. This paper describes the proposed system and three sorts of knowledge developed for dynamic phrasal thesaurus in Japanese: (i) transformation pattern, (ii) generation function, and (iii) lexical function.

[1]  Kentaro Inui,et al.  A Class-oriented Approach to Building a Paraphrase Corpus , 2005, IWP@IJCNLP.

[2]  Kyo Kageura,et al.  Detecting Japanese term variation in textual corpus , 2002 .

[3]  Regina Barzilay,et al.  Learning to Paraphrase: An Unsupervised Approach Using Multiple-Sequence Alignment , 2003, NAACL.

[4]  Mark Dras,et al.  Tree adjoining grammar and the reluctant paraphrasing of text , 1999 .

[5]  Satoshi Sato,et al.  Verb Paraphrase based on Case Frame Alignment , 2002, ACL.

[6]  Manabu Okumura,et al.  Paraphrasing by Case Alternation , 2000 .

[7]  Patrick Pantel,et al.  ISP: Learning Inferential Selectional Preferences , 2007, NAACL.

[8]  Patrick Pantel,et al.  VerbOcean: Mining the Web for Fine-Grained Semantic Verb Relations , 2004, EMNLP.

[9]  Yuji Matsumoto,et al.  Exploiting Lexical Conceptual Structure for Paraphrase Generation , 2005, IJCNLP.

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

[11]  Patrick Pantel,et al.  Discovery of inference rules for question-answering , 2001, Natural Language Engineering.

[12]  Igor Mel’čuk,et al.  Lexical functions: a tool for the description of lexical relations in a lexicon , 1996 .

[13]  Michael Collins,et al.  Convolution Kernels for Natural Language , 2001, NIPS.

[14]  高橋 哲朗.  Computation of semantic equivalence for question answering , 2005 .

[15]  Chris Brockett,et al.  Support Vector Machines for Paraphrase Identification and Corpus Construction , 2005, IJCNLP.

[16]  David J. Weir,et al.  The Distributional Similarity of Sub-Parses , 2005, EMSEE@ACL.

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

[18]  Kevin Knight,et al.  Generation that Exploits Corpus-Based Statistical Knowledge , 1998, ACL.