UCM at TREC-2012: Does Negation Influence the Retrieval of Medical Reports?

Abstract

This paper details the UCM participation in the TREC 2012 Medical Records Track. We present several experiments directed to evaluate the effect of detecting negation in the task of retrieving medical reports. In particular two different algorithms based on syntactic analysis have been applied to detect negations and to infer their scope. These algorithms are then combined with a simple term-frequency approach using Lucene to retrieve the reports that are relevant to a given query. We evaluate whether ignoring the information that is within the scope of negation may result in a higher retrieving performance. However, our experiments reveal that the effect of negation in this task is not significant.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Nov 01, 2012
Accession Number
ADA581297

Entities

People

  • Alberto Diaz
  • Jorge Carrillo-de-albornoz
  • Laura Plaza
  • Miguel Ballesteros

Organizations

  • Complutense University of Madrid

Tags

DTIC Thesaurus Topics

  • Algorithms
  • Computational Linguistics
  • Education
  • European Union
  • Frequency
  • Information Operations
  • Language
  • Linguistics
  • Machine Learning
  • Natural Language Processing
  • Natural Languages
  • Pain
  • Rule Based Systems
  • Semantics
  • Standards
  • Test And Evaluation

Fields of Study

  • Computer science

Readers

  • Information Retrieval
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML
  • AI & ML - Information Retrieval
  • AI & ML - Neural Networks