Related Entity Finding Based on Co-Occurrence

Abstract

We report on experiments for the Related Entity Finding task in which we focus on only using Wikipedia as a target corpus in which to identify (related) entitities. Our approach is based on co-occurrences between the source entity and potential target entities. We observe improvements in performance when a context-independent co-occurrence model is combined with context-dependent co-occurrence models in which we stress the importance of the expected relation between source and target entity. Applying type filtering yields further improvements results.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Nov 01, 2009
Accession Number
ADA517706

Entities

People

  • Krisztian Balog
  • Maarten De Rijke
  • Marc Bron

Organizations

  • University of Amsterdam

Tags

DTIC Thesaurus Topics

  • Abstracts
  • Computational Linguistics
  • Filtration
  • Information Operations
  • Intelligent Systems
  • Language
  • Linguistics
  • Monte Carlo Method
  • Named Entity Recognition
  • Natural Language Processing
  • Natural Languages
  • Pipelines
  • Probability
  • Recognition
  • Scientific Research
  • Standards

Fields of Study

  • Computer science

Readers

  • Computational Linguistics
  • Information Retrieval
  • Systems Analysis and Design