Open-domain Anatomical Entity Mention Detection

Tomoko Ohta, Sampo Pyysalo, Jun’ichi Tsujii, Sophia AnaniadouResearch 2012

Abstract

Anatomical entities such as kidney, muscle and blood are central to much of biomedical scientific discourse, and the detection of men-tions of anatomical entities is thus necessary for the automatic analysis of the structure of domain texts. Although a number of resources and methods addressing aspects of the task have been introduced, there have so far been no annotated corpora for training and evaluat-ing systems for broad-coverage, open-domain anatomical entity mention detection. We in-troduce the AnEM corpus, a domain- and species-independent resource manually anno-tated for anatomical entity mentions using a fine-grained classification system. The cor-pus texts are selected randomly from citation abstracts and full-text papers with the aim of making the corpus representative of the en-tire available biomedical scientific literature. We demonstrate the use of the corpus through an evaluation of the broad-coverage MetaMap tagger and a CRF-based system trained on the corpus data, considering also a combination of these two methods. The combined sys-tem demonstrates a promising level of per-formance, approaching 80 % F-score for men-tion detection for a relaxed matching criterion. The corpus and other introduced resources are available under open licences from
BibTeX
@inproceedings{ohta2012open,
  author = {Tomoko Ohta and Sampo Pyysalo and Jun’ichi Tsujii and Sophia Ananiadou},
  title = {{Open-domain Anatomical Entity Mention Detection}},
  booktitle = {Research},
  year = {2012},
}

Loading related content...

Figure