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, VerbNet for verbs and CoreLex for nouns. We discuss how we built our lexicon and ontology, and the parsing results we obtained.

• Type: Conference
• Year: 2003
• Where: NAACL
• Authors: Elena Terenzi, Barbara Di Eugenio
• Keywords: Instructional Text, Lexical Resources, Lexical Semantics Information, NAACL 2003, NAACL 2007