Two-Phase Biomedical Named Entity Recognition Using A Hybrid Method

Two-Phase Biomedical Named Entity Recognition Using A Hybrid Method Seonho Kim1, Juntae Yoon2, Kyung-Mi Park1, and Hae-Chang Rim1 1 Dept. of Computer Science and Engineering, Korea University, Seoul, Korea 2 NLP Lab. Daumsoft Inc. Seoul, Korea Abstract. Biomedical named entity recognition (NER) is a difficult problem in biomedical information processing due to the widespread am- biguity of terms out of context and extensive lexical variations. This pa- per presents a two-phase biomedical NER consisting of term boundary detection and semantic labeling. By dividing the problem, we can adopt an effective model for each process. In our study, we use two exponential models, conditional random fields and maximum entropy, at each phase. Moreover, results by this machine learning based model are refined by rule-based postprocessing implemented using a finite state method. Ex- periments show it achieves the performance of F-score 71.19% on the JNLPBA 2004 shared task of identifying 5 classes of biomedical NEs. 1 Introduction Due to dynamic progress in biomedical literature, a vast amount of new infor- mation and research results have been published and many of them are available in the electronic form - for example, like the PubMed MedLine database. Thus, automatic knowledge discovery and efficient information access are strongly de- manded to curate domain databases, to find out relevant information, and to integrate/update new information across an increasingly large body of scien- tific articles. In particular, since most biomedical texts introduce specific no- tations, acronyms, and innovative names to represent new concepts, relations, processes, functions, locations, and events, automatic extraction of biomedical terminologies and mining of their diverse usage are major challenges in biomed- ical information processing system. In these processes, biomedical named entity recognition (NER) is the core step to access the higher level of information. In fact, there has been a wide range of research on NER like the NER task on the standard newswire domain in the Message Understanding Conference (MUC- 6). In this task, the best system reported 95% accuracy in identifying seven types of named entities (person, organization, location, time, date, money, and per- cent). While the performance in the standard domain turned out to be quite good as shown in the papers, that in the biomedical domain is not still satisfactory, which is mainly due to the following characteristics of biomedical terminologies: First, NEs have various naming conventions. For instance, some entities have descriptive and expanded forms such as “activated B cell lines, 47 kDa sterol R. Dale et al. (Eds.): IJCNLP 2005, LNAI 3651, pp. 646–657, 2005. c ⃝ Springer-Verlag Berlin Heidelberg 2005 Two-Phase Biomedical Named Entity Recognition 647 regulatory element binding factor”, whereas some entities appear in shortened or abbreviated forms like “EGFR” and “EGF receptor” representing epidermal growth factor receptor. Second, biomedical NEs have the widespread ambiguity out of context. For instance, “IL-2” can be doubly classified as “protein” and “DNA” according to its context. Third, biomedical NEs often comprise a nested structure, for example “⟨DNA⟩⟨protein⟩TNF alpha⟨/protein⟩gene⟨/DNA⟩”. Ac- cording to [13], 16.57% of biomedical terms in GENIA …

Content truncated to 500 words