BIOSMILE: Adapting semantic role labeling for biomedical verbs: An exponential model coupled with automatically generated template features

Richard Tzong Han Tsai, Wen Chi Chou, Yu Chun Lin, Cheng Lung Sung, Wei Ku, Ying Shan Su, Ting Yi Sung, Wen Lian Hs

Research output: Contribution to conferencePaperpeer-review

17 Scopus citations

Abstract

In this paper, we construct a biomedical semantic role labeling (SRL) system that can be used to facilitate relation extraction. First, we construct a proposition bank on top of the popular biomedical GENIA treebank following the PropBank annotation scheme. We only annotate the predicate-argument structures (PAS's) of thirty frequently used biomedical predicates and their corresponding arguments. Second, we use our proposition bank to train a biomedical SRL system, which uses a maximum entropy (ME) model. Thirdly, we automatically generate argument-type templates which can be used to improve classification of biomedical argument types. Our experimental results show that a newswire SRL system that achieves an F-score of 86.29% in the newswire domain can maintain an F-score of 64.64% when ported to the biomedical domain. By using our annotated biomedical corpus, we can increase that F-score by 22.9%. Adding automatically generated template features further increases overall F-score by 0.47% and adjunct arguments (AM) Fscore by 1.57%, respectively.

Original languageEnglish
Pages57-64
Number of pages8
StatePublished - 2006
EventHLT-NAACL 2006 Workshop on Linking Natural Language Processing and Biology: Towards Deeper Biological Literature Analysis, BioNLP 2006 - New York, United States
Duration: 8 Jun 2006 → …

Conference

ConferenceHLT-NAACL 2006 Workshop on Linking Natural Language Processing and Biology: Towards Deeper Biological Literature Analysis, BioNLP 2006
Country/TerritoryUnited States
CityNew York
Period8/06/06 → …

Fingerprint

Dive into the research topics of 'BIOSMILE: Adapting semantic role labeling for biomedical verbs: An exponential model coupled with automatically generated template features'. Together they form a unique fingerprint.

Cite this