Paper: Event Role Extraction using Domain-Relevant Word Representations

ACL ID D14-1199
Title Event Role Extraction using Domain-Relevant Word Representations
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2014
Authors

The efficiency of Information Extraction systems is known to be heavily influenced by domain-specific knowledge but the cost of developing such systems is consider- ably high. In this article, we consider the problem of event extraction and show that learning word representations from unla- beled domain-specific data and using them for representing event roles enable to out- perform previous state-of-the-art event ex- traction models on the MUC-4 data set.