Gene Mention Tagging with CRFs and Parsing 1 Tackling the BioCreative 2 Gene Mention task with Conditional Random Fields and Syntactic Parsing
暂无分享,去创建一个
This paper presents an approach to Gene Mention tagging using Conditional Random Fields (CRFs) and syntactic parsing, by taking advantage of the flexibility of the former in order to add features from the output of the latter. We did not use any material or information other than the training data provided in order to maintain the domain independence of the system. Nevertheless, the resulting system achieved 82.84% F-score, which places it in the second performance quartile of the competition.
[1] Andrew McCallum,et al. Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data , 2001, ICML.
[2] Burr Settles,et al. Biomedical Named Entity Recognition using Conditional Random Fields and Rich Feature Sets , 2004, NLPBA/BioNLP.
[3] Ted Briscoe,et al. The Second Release of the RASP System , 2006, ACL.