Self-Training for Biomedical Parsing

Parser self-training is the technique of taking an existing parser, parsing extra data and then creating a second parser by treating the extra data as further training data. Here we apply this technique to parser adaptation. In particular, we self-train the standard Charniak/Johnson Penn-Treebank parser usbeled biomedical abstracts. This achieves an f-score of 84.3% on a stant set of biomedical abstracts from the Genia corpus. This is a 20% error reduction over the best previous result on biomedical data (80.2% on the same test set).

• Type: Conference
• Year: 2008
• Where: ACL
• Authors: David McClosky, Eugene Charniak
• Keywords: ACL 2008, Biomedical Abstracts, Computational Linguistics, Extra Data, Parser