Where academic tradition
meets the exciting future

You are here: TUCS > PUBLICATIONS > Publication Search > Information Extraction from Bi...

Information Extraction from Biomedical Text: The BioText Project

Filip Ginter, Tapio Pahikkala, Sampo Pyysalo, Evgeni Tsivtsivadze, Jorma Boberg, Jouni Järvinen, Aleksandr Mylläri, Tapio Salakoski, Information Extraction from Biomedical Text: The BioText Project. In: Margit Langemets, Priit Penjam (Eds.), Proceedings of the Second Baltic Conference on Human Language Technologies (HLT 2005), 131-136, Institute of Cybernetics, Tallinn University of Technology and Institute of the Estonian Language, 2005.

Abstract:

We study information extraction for identifying protein-protein
interactions stated in biomedical text. In this paper, we present an
architecture for an information extraction system and discuss our
improvements and results pertaining to several components of the
system, including information retrieval, named entity recognition,
syntactic analysis, and domain analysis. The individual results are
discussed in the context of the whole system, and domain adaptations
and differences from classical approaches are considered. We combine
structural natural language processing with machine learning methods
to address the general and domain-specific challenges of information
extraction targeting protein-protein interactions.

BibTeX entry:

@INPROCEEDINGS{inpGiPaPyTsBoJaMySa05a,
  title = {Information Extraction from Biomedical Text: The BioText Project},
  booktitle = {Proceedings of the Second Baltic Conference on Human Language Technologies (HLT 2005)},
  author = {Ginter, Filip and Pahikkala, Tapio and Pyysalo, Sampo and Tsivtsivadze, Evgeni and Boberg, Jorma and Järvinen, Jouni and Mylläri, Aleksandr and Salakoski, Tapio},
  editor = {Langemets, Margit and Penjam, Priit},
  publisher = {Institute of Cybernetics, Tallinn University of Technology and Institute of the Estonian Language},
  pages = {131-136},
  year = {2005},
  keywords = {biomedical literature mining, information retrieval, named entity recognition, word sense disambiguation, parsing, parse ranking},
}

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

Edit publication