Mention Detection: Heuristics for the OntoNotes Annotations

Abstract

Our submission was a reduced version of the system described in Haghighi and Klein (2010), with extensions to improve mention detection to suit the OntoNotes annotation scheme. Including exact matching mention detection in this shared task added a new and challenging dimension to the problem, particularly for our system, which previously used a very permissive detection method. We improved this aspect of the system by adding filters based on the annotation scheme for OntoNotes and analysis of system behavior on the development set. These changes led to improvements in coreference F-score of 10.06, 5.71, 6.78, 6.63 and 3.09 on the MUC, B3, Ceaf-e, Ceaf-m and Blanc, metrics, respectively and a final task score of 47.10.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 2011
Accession Number
ADA543887

Entities

People

  • Dan Klein
  • David Burkett
  • Jonathan K. Kummerfeld
  • Mohit Bansal

Organizations

  • University of California, Berkeley

Tags

DTIC Thesaurus Topics

  • Computational Linguistics
  • Computer Science
  • Data Sets
  • Detection
  • Filters
  • Generative Models
  • Information Operations
  • Language
  • Linguistics
  • Military Operations
  • Models
  • Natural Languages
  • Operations Research
  • Precision
  • Standards
  • Test Sets
  • Word Lists

Readers

  • Computational Linguistics
  • Sensor Fusion and Tracking Systems.