Sciweavers

Share
CICLING
2005
Springer

Putting Pieces Together: Combining FrameNet, VerbNet and WordNet for Robust Semantic Parsing

9 years 7 months ago
Putting Pieces Together: Combining FrameNet, VerbNet and WordNet for Robust Semantic Parsing
Abstract. This paper describes our work in integrating three different lexical resources: FrameNet, VerbNet, and WordNet, into a unified, richer knowledge-base, to the end of enabling more robust semantic parsing. The construction of each of these lexical resources has required many years of laborious human effort, and they all have their strengths and shortcomings. By linking them together, we build an improved resource in which (1) the coverage of FrameNet is extended, (2) the VerbNet lexicon is augmented with frame semantics, and (3) selectional restrictions are implemented using WordNet semantic classes. The synergistic exploitation of various lexical resources is crucial for many complex language processing applications, and we prove it once again effective in building a robust semantic parser.
Lei Shi, Rada Mihalcea
Added 26 Jun 2010
Updated 26 Jun 2010
Type Conference
Year 2005
Where CICLING
Authors Lei Shi, Rada Mihalcea
Comments (0)
books