Shuo Xu1, Xin An2, Lijun Zhu1, Yunliang Zhang1, Haodong Zhang3. 1. Information Technology Supporting Center, Institute of Scientific and Technical Information of China, No. 15 Fuxing Rd., Haidian District, 100038 Beijing, PR China. 2. School of Economics and Management, Beijing Forestry University, No. 35 Qinghua East Rd., Haidian District, 100083 Beijing, PR China. 3. Network Center, Science and Technology Daily, No. 15 Fuxing Rd., Haidian District, 100038 Beijing, PR China.
Abstract
BACKGROUND: In order to improve information access on chemical compounds and drugs (chemical entities) described in text repositories, it is very crucial to be able to identify chemical entity mentions (CEMs) automatically within text. The CHEMDNER challenge in BioCreative IV was specially designed to promote the implementation of corresponding systems that are able to detect mentions of chemical compounds and drugs, which has two subtasks: CDI (Chemical Document Indexing) and CEM. RESULTS: Our system processing pipeline consists of three major components: pre-processing (sentence detection, tokenization), recognition (CRF-based approach), and post-processing (rule-based approach and format conversion). In our post-challenge system, the cost parameter in CRF model was optimized by 10-fold cross validation with grid search, and word representations feature induced by Brown clustering method was introduced. For the CEM subtask, our official runs were ranked in top position by obtaining maximum 88.79% precision, 69.08% recall and 77.70% balanced F-measure, which were improved further to 88.43% precision, 76.48% recall and 82.02% balanced F-measure in our post-challenge system. CONCLUSIONS: In our system, instead of extracting a CEM as a whole, we regarded it as a sequence labeling problem. Though our current system has much room for improvement, our system is valuable in showing that the performance in term of balanced F-measure can be improved largely by utilizing large amounts of relatively inexpensive un-annotated PubMed abstracts and optimizing the cost parameter in CRF model. From our practice and lessons, if one directly utilizes some open-source natural language processing (NLP) toolkits, such as OpenNLP, Standford CoreNLP, false positive (FP) rate may be very high. It is better to develop some additional rules to minimize the FP rate if one does not want to re-train the related models. Our CEM recognition system is available at: http://www.SciTeMiner.org/XuShuo/Demo/CEM.
BACKGROUND: In order to improve information access on chemical compounds and drugs (chemical entities) described in text repositories, it is very crucial to be able to identify chemical entity mentions (CEMs) automatically within text. The CHEMDNER challenge in BioCreative IV was specially designed to promote the implementation of corresponding systems that are able to detect mentions of chemical compounds and drugs, which has two subtasks: CDI (Chemical Document Indexing) and CEM. RESULTS: Our system processing pipeline consists of three major components: pre-processing (sentence detection, tokenization), recognition (CRF-based approach), and post-processing (rule-based approach and format conversion). In our post-challenge system, the cost parameter in CRF model was optimized by 10-fold cross validation with grid search, and word representations feature induced by Brown clustering method was introduced. For the CEM subtask, our official runs were ranked in top position by obtaining maximum 88.79% precision, 69.08% recall and 77.70% balanced F-measure, which were improved further to 88.43% precision, 76.48% recall and 82.02% balanced F-measure in our post-challenge system. CONCLUSIONS: In our system, instead of extracting a CEM as a whole, we regarded it as a sequence labeling problem. Though our current system has much room for improvement, our system is valuable in showing that the performance in term of balanced F-measure can be improved largely by utilizing large amounts of relatively inexpensive un-annotated PubMed abstracts and optimizing the cost parameter in CRF model. From our practice and lessons, if one directly utilizes some open-source natural language processing (NLP) toolkits, such as OpenNLP, Standford CoreNLP, false positive (FP) rate may be very high. It is better to develop some additional rules to minimize the FP rate if one does not want to re-train the related models. Our CEM recognition system is available at: http://www.SciTeMiner.org/XuShuo/Demo/CEM.
Entities:
Keywords:
Brown Clustering; Chemical Compound and Drug Name Recognition; Conditional Random Fields; Natural Language Processing; Word Representations
Authors: Martin Krallinger; Obdulia Rabal; Florian Leitner; Miguel Vazquez; David Salgado; Zhiyong Lu; Robert Leaman; Yanan Lu; Donghong Ji; Daniel M Lowe; Roger A Sayle; Riza Theresa Batista-Navarro; Rafal Rak; Torsten Huber; Tim Rocktäschel; Sérgio Matos; David Campos; Buzhou Tang; Hua Xu; Tsendsuren Munkhdalai; Keun Ho Ryu; S V Ramanan; Senthil Nathan; Slavko Žitnik; Marko Bajec; Lutz Weber; Matthias Irmer; Saber A Akhondi; Jan A Kors; Shuo Xu; Xin An; Utpal Kumar Sikdar; Asif Ekbal; Masaharu Yoshioka; Thaer M Dieb; Miji Choi; Karin Verspoor; Madian Khabsa; C Lee Giles; Hongfang Liu; Komandur Elayavilli Ravikumar; Andre Lamurias; Francisco M Couto; Hong-Jie Dai; Richard Tzong-Han Tsai; Caglar Ata; Tolga Can; Anabel Usié; Rui Alves; Isabel Segura-Bedmar; Paloma Martínez; Julen Oyarzabal; Alfonso Valencia Journal: J Cheminform Date: 2015-01-19 Impact factor: 5.514
Authors: Martin Krallinger; Alexander Morgan; Larry Smith; Florian Leitner; Lorraine Tanabe; John Wilbur; Lynette Hirschman; Alfonso Valencia Journal: Genome Biol Date: 2008-09-01 Impact factor: 13.583