Paper: A High-Precision Approach to Detecting Hedges and their Scopes

ACL ID W10-3010
Title A High-Precision Approach to Detecting Hedges and their Scopes
Venue International Conference on Computational Natural Language Learning
Session Main Conference
Year 2010
Authors

We extend our prior work on specula- tive sentence recognition and speculation scope detection in biomedical text to the CoNLL-2010 Shared Task on Hedge De- tection. In our participation, we sought to assess the extensibility and portability of our prior work, which relies on linguis- tic categorization and weighting of hedg- ing cues and on syntactic patterns in which these cues play a role. For Task 1B, we tuned our categorization and weight- ing scheme to recognize hedging in bio- logical text. By accommodating a small number of vagueness quantifiers, we were able to extend our methodology to de- tecting vague sentences in Wikipedia arti- cles. We exploited constituent parse trees in addition to syntactic dependency rela- tions in resolving hedging scope. Our re- sults are competitive w...