• TUCS Publication Series
• How to Publish in TUCS Series
• Publication Search
• Publication Graph
• Publication Input
• Publication Input Guide
• JuFo Browser

Statistical Parsing of Varieties of Clinical Finnish

Veronika Laippala, Timo Viljanen, Antti Airola, Jenna Nyblom, Sanna Salanterä, Tapio Salakoski, Filip Ginter, Statistical Parsing of Varieties of Clinical Finnish. In: Hanna Suominen (Ed.), Proceedings of the 4th International Louhi Workshop on Health Document Text Mining and Information Analysis, 1–6, National ICT Australia, 2013.

Abstract:

In this paper, we study the development and domain-adaptation of statistical syntactic parsers for three different clinical domains in Finnish: daily nursing notes written by nurses in an Intensive Care Unit, physicians' notes from heart patients' health records and daily nursing notes from heart patients' health records. We find that a parser trained only on a general language treebank performs poorly in all subdomains, whereas a treebank consisting of text from several clinical domains gives better results. The best results are achieved by using all the clinical treebanks and a general Finnish treebank as training data.

BibTeX entry:

@INPROCEEDINGS{inpLaViAiNySaSaGi13a,
  title = {Statistical Parsing of Varieties of Clinical Finnish},
  booktitle = {Proceedings of the 4th International Louhi Workshop on Health Document Text Mining and Information Analysis},
  author = {Laippala, Veronika and Viljanen, Timo and Airola, Antti and Nyblom, Jenna and Salanterä, Sanna and Salakoski, Tapio and Ginter, Filip},
  editor = {Suominen, Hanna},
  publisher = {National ICT Australia},
  pages = {1–6},
  year = {2013},
  keywords = {automatic syntactic analysis, domain-adaptation, clinical languages},
}

Belongs to TUCS Research Unit(s): Turku BioNLP Group

Edit publication