2004 FrameNetParsingUsingMaxEnt

From GM-RKB
Jump to navigation Jump to search

Subject Headings: Semantic Role Labeling, FrameNet

Notes

Cited By

2005

  • (Liu et al., 2005) ⇒ Ting Liu, Wanxiang Che, Sheng Li, Yuxuan Hu, Huaijun Liu. (2005). “Semantic Role Lableing System using Maximum Entropy Classifier.” In: Association for Computational Linguistics, pages 189-192, .
  • (Jiang et al., 2005) ⇒ Zheng-Yu Jiang, Jia Li, and Wee Teck Ng. (2005). “Semantic Argument Classification Exploiting Argument Interdependence.” Department of Computer Science, National University of Singapore

Quotes

Abstract

As part of its description of lexico-semantic predicate frames or conceptual structures, the FrameNet project defines a set of semantic roles specific to the core predicate of a sentence. Recently, researchers have tried to automatically produce semantic interpretations of sentences using this information. Building on prior work, we describe a new method to perform such interpretations. We define sentence segmentation first and show how Maximum Entropy re-ranking helps achieve a level of 76.2% F-score (answer among topfive candidates) or 61.5% (correct answer).


References


 AuthorvolumeDate ValuetitletypejournaltitleUrldoinoteyear
2004 FrameNetParsingUsingMaxEntEduard Hovy
Namhee Kwon
Michael Fleischmann
FrameNet-based Semantic Parsing using Maximum Entropy ModelsProceedings of COLING Conferencehttp://acl.ldc.upenn.edu/coling2004/MAIN/pdf/179-745.pdf2004