51ÖØ¿ÚÁÔÆæ

The browser you are using is not supported by this website. All versions of Internet Explorer are no longer supported, either by us or Microsoft (read more here: ).

Please use a modern browser to fully experience our website, such as the newest versions of Edge, Chrome, Firefox or Safari etc.

Expanding a dictionary of marker words for uncertainty and negation using distributional semantics

Author

  • Alyaa Alfalahi
  • Maira Skeppstedt
  • Rickard Ahlblom
  • Roza Baskalayci
  • Aron Henriksson
  • Lars Asker
  • Carita Paradis
  • Andreas Kerren

Editor

  • Cyril Grouin
  • Thierry Hamon
  • Aurélie Névéol
  • Pierre Zweigenbaum

Summary, in English

Approaches to determining the factuality of diagnoses and findings in clinical text tend to rely on dictionaries of marker words for uncertainty and negation. Here, a method for semi-automatically expanding a dictionary of marker words using distributional semantics is presented and evaluated. It is shown that ranking candidates for inclusion according to their proximity to cluster centroids of semantically similar seed words is more successful than ranking them according to proximity to each individual seed word.

Department/s

Publishing year

2015

Language

English

Pages

90-96

Publication/Series

EMNLP 2015 - 6th International Workshop on Health Text Mining and Information Analysis, LOUHI 2015 : Proceedings of the Workshop

Full text

  • - 527 kB

Links

Document type

Conference paper

Publisher

The Association for Computational Linguistics

Topic

  • Computer and Information Sciences

Keywords

  • clinical text
  • negation
  • uncertainty
  • marker words
  • distributional semantics

Conference name

6th International Workshop on Health Text Mining and Information Analysis, LOUHI 2015, co-located with EMNLP 2015

Conference date

2015-09-17

Conference place

Lisbon, Portugal

Status

Published

Project

  • StaViCTA - Advances in the description and explanation of stance in discourse using visual and computational text analytics

ISBN/ISSN/Other

  • ISBN: 9781941643327
  • urn:nbn:se:lnu:diva-45648
  • oai:DiVA.org:lnu-45648