No means 'No': a non-improper modeling approach, with embedded speculative context.

Journal: Bioinformatics (Oxford, England)
Published Date:

Abstract

MOTIVATION: The medical data are complex in nature as terms that appear in records usually appear in different contexts. Through this article, we investigate various bio model's embeddings (BioBERT, BioELECTRA and PubMedBERT) on their understanding of 'negation and speculation context' wherein we found that these models were unable to differentiate 'negated context' versus 'non-negated context'. To measure the understanding of models, we used cosine similarity scores of negated sentence embeddings versus non-negated sentence embeddings pairs. For improving these models, we introduce a generic super tuning approach to enhance the embeddings on 'negation and speculation context' by utilizing a synthesized dataset.

Authors

  • Priya Tiwary
    Saama AI Research Lab, Pune 411057, India.
  • Akshayraj Madhubalan
    Saama AI Research Lab, Pune 411057, India.
  • Amit Gautam
    Saama AI Research Lab, Pune 411057, India.