Two-phase biomedical named entity recognition using CRFs. Li, L., Zhou, R., & Huang, D. Computational Biology and Chemistry, 33(4):334-338, IEEE, 2009.
Two-phase biomedical named entity recognition using CRFs. [link]Website  abstract   bibtex   
As a fundamental step of biomedical text mining, Biomedical Named Entity Recognition (Bio-NER) remains a challenging task. This paper explores a so-called two-phase approach to identify biomedical entities, in which the recognition task is divided into two subtasks: Named Entity Detection (NED) and Named Entity Classification (NEC). And the two subtasks are finished in two phases. At the first phase, we try to identify each named entity with a Conditional Random Fields (CRFs) model without identifying its type; at the second phase, another CRFs model is used to determine the correct entity type for each identified entity. This treatment can reduce the training time significantly and furthermore, more relevant features can be selected for each subtask. In order to achieve a better performance, post-processing algorithms are employed before NEC subtask. Experiments conducted on JNLPBA2004 datasets show that our two-phase approach can achieve an F-score of 74.31%, which outperforms most of the state-of-the-art systems.
@article{
 title = {Two-phase biomedical named entity recognition using CRFs.},
 type = {article},
 year = {2009},
 identifiers = {[object Object]},
 keywords = {abstracting indexing topic,biomedical research,computational biology,controlled,vocabulary},
 pages = {334-338},
 volume = {33},
 websites = {http://www.ncbi.nlm.nih.gov/pubmed/19656727},
 publisher = {IEEE},
 institution = {Department of Computer Science and Engineering, Dalian University of Technology, 116023 Dalian, China.},
 id = {e12c6f72-fcde-3626-a375-7d6e5973ef04},
 created = {2011-12-28T07:04:55.000Z},
 file_attached = {false},
 profile_id = {5284e6aa-156c-3ce5-bc0e-b80cf09f3ef6},
 group_id = {066b42c8-f712-3fc3-abb2-225c158d2704},
 last_modified = {2017-03-14T14:36:19.698Z},
 tags = {named entities},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {true},
 hidden = {false},
 citation_key = {Li2009},
 private_publication = {false},
 abstract = {As a fundamental step of biomedical text mining, Biomedical Named Entity Recognition (Bio-NER) remains a challenging task. This paper explores a so-called two-phase approach to identify biomedical entities, in which the recognition task is divided into two subtasks: Named Entity Detection (NED) and Named Entity Classification (NEC). And the two subtasks are finished in two phases. At the first phase, we try to identify each named entity with a Conditional Random Fields (CRFs) model without identifying its type; at the second phase, another CRFs model is used to determine the correct entity type for each identified entity. This treatment can reduce the training time significantly and furthermore, more relevant features can be selected for each subtask. In order to achieve a better performance, post-processing algorithms are employed before NEC subtask. Experiments conducted on JNLPBA2004 datasets show that our two-phase approach can achieve an F-score of 74.31%, which outperforms most of the state-of-the-art systems.},
 bibtype = {article},
 author = {Li, Lishuang and Zhou, Rongpeng and Huang, Degen},
 journal = {Computational Biology and Chemistry},
 number = {4}
}

Downloads: 0