A high-precision approach to detecting hedges and their scopes

Halil Kilicoglu, Sabine Bergler

Research output: Contribution to conferencePaper

Abstract

We extend our prior work on speculative sentence recognition and speculation scope detection in biomedical text to the CoNLL-2010 Shared Task on Hedge Detection. In our participation, we sought to assess the extensibility and portability of our prior work, which relies on linguistic categorization and weighting of hedging cues and on syntactic patterns in which these cues play a role. For Task 1B, we tuned our categorization and weighting scheme to recognize hedging in biological text. By accommodating a small number of vagueness quantifiers, we were able to extend our methodology to detecting vague sentences in Wikipedia articles. We exploited constituent parse trees in addition to syntactic dependency relations in resolving hedging scope. Our results are competitive with those of closeddomain trained systems and demonstrate that our high-precision oriented methodology is extensible and portable.

Original languageEnglish (US)
Pages70-77
Number of pages8
StatePublished - Dec 1 2010
Externally publishedYes
Event14th Conference on Computational Natural Language Learning, CoNLL 2010: Shared Task - Uppsala, Sweden
Duration: Jul 15 2010Jul 16 2010

Conference

Conference14th Conference on Computational Natural Language Learning, CoNLL 2010: Shared Task
CountrySweden
CityUppsala
Period7/15/107/16/10

ASJC Scopus subject areas

  • Artificial Intelligence
  • Human-Computer Interaction
  • Linguistics and Language

Fingerprint Dive into the research topics of 'A high-precision approach to detecting hedges and their scopes'. Together they form a unique fingerprint.

  • Cite this

    Kilicoglu, H., & Bergler, S. (2010). A high-precision approach to detecting hedges and their scopes. 70-77. Paper presented at 14th Conference on Computational Natural Language Learning, CoNLL 2010: Shared Task, Uppsala, Sweden.