Paper: Unsupervised Parsing for Generating Surface-Based Relation Extraction Patterns

ACL ID E14-4020
Title Unsupervised Parsing for Generating Surface-Based Relation Extraction Patterns
Venue Annual Meeting of The European Chapter of The Association of Computational Linguistics
Session Main Conference
Year 2014
Authors

Finding the right features and patterns for identifying relations in natural language is one of the most pressing research ques- tions for relation extraction. In this pa- per, we compare patterns based on super- vised and unsupervised syntactic parsing and present a simple method for extract- ing surface patterns from a parsed training set. Results show that the use of surface- based patterns not only increases extrac- tion speed, but also improves the quality of the extracted relations. We find that, in this setting, unsupervised parsing, besides requiring less resources, compares favor- ably in terms of extraction quality.