2009 · 10 citations · 10 references
This paper discusses the benefits and limitations of drawing conceptual inferences based on entries in a rich verb lexicon, VerbNet. Automatic sense tagging and semantic role labeling can be used to match predicate arguments structures in a sentence with specific syntactic and semantic frames from the lexicon, allowing conceptual inferences to be drawn. However, as with any hand-crafted resource, the entries do not always contain the desired inferences. Links to an ontology are suggested as a means of broadening the range of possible inferences. 1.
10
WordNet: An Electronic Lexical Database
Adam Kilgarriff, Christiane Fellbaum · Language · 2000 · 11.7K citations
Natural Language Processing, Semantic Similarity, Wordnet Lexical Database +15
Collin F. Baker, Charles J. Fillmore, John B. Lowe · 1998 · 2.6K citations · Full text
Berkeley Framenet Project, Semantic Role Labeling, Engineering +18
English Verb Classes and Alternations: A Preliminary Investigation
Carol L. Tenny, Beth Levin · Language · 1995 · 2.3K citations
An Electronic Lexical Database
Christiane Fellbaum · 1998 · 715 citations
Natural Language Processing, Applied Linguistics, Engineering +11