Paper: Combining Lexical Syntactic And Semantic Features With Maximum Entropy Models For Information Extraction

ACL ID P04-3022
Title Combining Lexical Syntactic And Semantic Features With Maximum Entropy Models For Information Extraction
Venue Annual Meeting of the Association of Computational Linguistics
Session System Demonstration
Year 2004
Authors

Extracting semantic relationships between entities is challenging because of a paucity of annotated data and the errors induced by entity detection mod- ules. We employ Maximum Entropy models to combine diverse lexical, syntactic and semantic fea- tures derived from the text. Our system obtained competitive results in the Automatic Content Ex- traction (ACE) evaluation. Here we present our gen- eral approach and describe our ACE results.