Expanding a radiology lexicon using contextual patterns in radiology reports


Creative Commons License

Percha B., Zhang Y., Bozkurt S., Rubin D., Altman R. B., Langlotz C. P.

JOURNAL OF THE AMERICAN MEDICAL INFORMATICS ASSOCIATION, vol.25, no.6, pp.679-685, 2018 (SCI-Expanded) identifier identifier identifier

  • Publication Type: Article / Article
  • Volume: 25 Issue: 6
  • Publication Date: 2018
  • Doi Number: 10.1093/jamia/ocx152
  • Journal Name: JOURNAL OF THE AMERICAN MEDICAL INFORMATICS ASSOCIATION
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Social Sciences Citation Index (SSCI), Scopus
  • Page Numbers: pp.679-685
  • Keywords: text mining, radiology, lexicons, ontologies, natural language processing, EXTRACTION, KNOWLEDGE, SYSTEM, NAMES
  • Akdeniz University Affiliated: No

Abstract

Objective: Distributional semantics algorithms, which learn vector space representations of words and phrases from large corpora, identify related terms based on contextual usage patterns. We hypothesize that distributional semantics can speed up lexicon expansion in a clinical domain, radiology, by unearthing synonyms from the corpus.