Towards answering biological questions with experimental evidence: automatically identifying text that summarize image content in full-text articles

AMIA Annu Symp Proc. 2006;2006:834-8.


Images (i.e., figures) are important experimental evidence that are typically reported in bioscience full-text articles. Biologists need to access images to validate research facts and to formulate or to test novel research hypotheses. We propose to build a biological question answering system that provides experimental evidences as answers in response to biological questions. As a first step, we develop natural language processing techniques to identify sentences that summarize image content.

MeSH terms

  • Algorithms
  • Biological Science Disciplines*
  • Information Storage and Retrieval / methods*
  • Medical Illustration
  • Natural Language Processing*