The Importance of Lexicalized Syntax Models for Natural Language Generation Tasks
Abstract
The parsing community has long recognized the importance of lexicalized models of syntax. By contrast, these models do not appear to have had an impact on the statistical NLG community. To prove their importance in NLG, we show that a lexicalized model of syntax improves the performance of a statistical text compression system, and show results that suggest it would also improve the performances of an MT application and a pure natural language generation system.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jan 01, 2002
- Accession Number
- ADA459361
Entities
People
- Daniel Marcu
- Hal Daynem Iii
- Irene Langkilde-geary
- Kenji Yamada
- Kevin Knight
Organizations
- University of Southern California