Annotating named entities in clinical text by combining pre-annotation and active learning
2013 (English)In: 51st Annual Meeting of the Association for Computational Linguistics (ACL 2013): Student Research Workshop, Association for Computational Linguistics, 2013, 74-80 p.Conference paper (Refereed)
Sentence types typical to Swedish clini- cal text were extracted by comparing sen- tence part-of-speech tag sequences in clin- ical and in standard Swedish text. Parsings by a syntactic dependency parser, trained on standard Swedish, were manually ana- lysed for the 33 sentence types most typ- ical to clinical text. This analysis re- sulted in the identification of eight error types, and for two of these error types, pre- processing rules were constructed to im- prove the performance of the parser. For all but one of the ten sentence types af- fected by these two rules, the parsing was improved by pre-processing.
Place, publisher, year, edition, pages
Association for Computational Linguistics, 2013. 74-80 p.
Research subject Computer and Systems Sciences
IdentifiersURN: urn:nbn:se:su:diva-95577ISBN: 978-1-62748-976-8OAI: oai:DiVA.org:su-95577DiVA: diva2:660885
ACL 2013: The 51st Annual Meeting of the Association for Computational Linguistics, Sofia, Bulgaria, August 4-9 2013