Negation-based transfer learning for improving biomedical Named Entity Recognition and Relation Extraction.

Journal: Journal of biomedical informatics
Published Date:

Abstract

BACKGROUND AND OBJECTIVES: Named Entity Recognition (NER) and Relation Extraction (RE) are two of the most studied tasks in biomedical Natural Language Processing (NLP). The detection of specific terms and entities and the relationships between them are key aspects for the development of more complex automatic systems in the biomedical field. In this work, we explore transfer learning techniques for incorporating information about negation into systems performing NER and RE. The main purpose of this research is to analyse to what extent the successful detection of negated entities in separate tasks helps in the detection of biomedical entities and their relationships.

Authors

  • Hermenegildo Fabregat
    Department of Computer Science, Universidad Nacional de Educación a Distancia (UNED), Juan del Rosal 16, Madrid 28040, Spain. Electronic address: gildo.fabregat@lsi.uned.es.
  • Andres Duque
    Departamento de Lenguajes y Sistemas Informáticos, Universidad Nacional de Educación a Distancia, Madrid, Spain.
  • Juan Martinez-Romo
    NLP & IR Group, Dpto. Lenguajes y Sistemas Informáticos, Universidad Nacional de Educación a Distancia (UNED), Madrid 28040, Spain. Electronic address: juaner@lsi.uned.es.
  • Lourdes Araujo
    NLP & IR Group, Dpto. Lenguajes y Sistemas Informáticos, Universidad Nacional de Educación a Distancia (UNED), Madrid 28040, Spain. Electronic address: lurdes@lsi.uned.es.