Improving English verb sense disambiguation performance with linguistically motivated features and clear sense distinction boundaries |
| |
Authors: | Jinying Chen Martha S. Palmer |
| |
Affiliation: | (1) BBN Technologies, Cambridge, MA, USA;(2) University of Colorado, Boulder, CO, USA |
| |
Abstract: | This paper presents a high-performance broad-coverage supervised word sense disambiguation (WSD) system for English verbs that uses linguistically motivated features and a smoothed maximum entropy machine learning model. We describe three specific enhancements to our system’s treatment of linguistically motivated features which resulted in the best published results on SENSEVAL-2 verbs. We then present the results of training our system on OntoNotes data, both the SemEval-2007 task and additional data. OntoNotes data is designed to provide clear sense distinctions, based on using explicit syntactic and semantic criteria to group WordNet senses, with sufficient examples to constitute high quality, broad coverage training data. Using similar syntactic and semantic features for WSD, we achieve performance comparable to that of human taggers, and competitive with the top results for the SemEval-2007 task. Empirical analysis of our results suggests that clarifying sense boundaries and/or increasing the number of training instances for certain verbs could further improve system performance. |
| |
Keywords: | Word sense disambiguation Sense granularity Maximum entropy Linguistically motivated features Linear regression |
本文献已被 SpringerLink 等数据库收录! |
|