Paper: Adapting An NER-System For German To The Biomedical Domain

ACL ID W04-1218
Title Adapting An NER-System For German To The Biomedical Domain
Venue International Joint Workshop On Natural Language Processing In Biomedicine And Its Applications NLPBA BioNLP
Session
Year 2004
Authors
  • Marc Rossler (University of Duisburg-Essen, Duisburg and Essen Germany)

In this paper, we report the adaptation of a named entity recognition (NER) system to the biomedical domain in order to participate in the ”Shared Task Bio-Entity Recognition”. The system is originally developed for Ger- man NER that shares characteristics with the biomedical task. To facilitate adaptability, the system is knowledge-poor and utilizes unla- beled data. Investigating the adaptability of the single components and the enhancements nec- essary, we get insights into the task of bio- entity recognition.