论文信息 - Building lexical semantic representations for Natural Language instructions

Building lexical semantic representations for Natural Language instructions

We report on our work to automatically build a corpus of instructional text annotated with lexical semantics information. We have coupled the parser LCFLEX with a lexicon and ontology derived from two lexical resources, Verb-Net for verbs and CoreLex for nouns. We discuss how we built our lexicon and ontology, and the parsing results we obtained.

Barbara Di Eugenio | Elena Terenzi

[1] James Pustejovsky,et al. The Generative Lexicon , 1995, CL.

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

[3] Malka Rappaport Hovav,et al. Wiping the slate clean: A lexical semantic exploration , 1991, Cognition.

[4] Carolyn Penstein Rosé,et al. BALANCING ROBUSTNESS AND EFFICIENCY IN UNIFICATION-AUGMENTED CONTEXT-FREE PARSERS FOR LARGE PRACTICAL APPLICATIONS , 2001 .

[5] Martha Palmer,et al. Building a class-based verb lexicon using TAGs , 2000, TAG+.

[6] Christiane Fellbaum,et al. Book Reviews: WordNet: An Electronic Lexical Database , 1999, CL.

[7] James Pustejovsky,et al. Corelex: systematic polysemy and underspecification , 1998 .