Paper: Fast and simple semantic class assignment for biomedical text

ACL ID W11-0205
Title Fast and simple semantic class assignment for biomedical text
Venue Workshop on Biomedical Natural Language Processing
Session
Year 2011
Authors

A simple and accurate method for assigning broad semantic classes to text strings is pre- sented. The method is to map text strings to terms in ontologies based on a pipeline of exact matches, normalized strings, headword matching, and stemming headwords. The results of three experiments evaluating the technique are given. Five semantic classes are evaluated against the CRAFT corpus of full-text journal articles. Twenty semantic classes are evaluated against the correspond- ing full ontologies, i.e. by reflexive match- ing. One semantic class is evaluated against a structured test suite. Precision, recall, and F-measure on the corpus when evaluat- ing against only the ontologies in the cor- pus is micro-averaged 67.06/78.49/72.32 and macro-averaged 69.84/83.12/75.31. Accuracy on the corpus...