BIOINFORMATICS Building an Abbreviation Dictionary Using a Term Recognition Approach.pdf

下载文档

2
0
约4.3万字
约 7页
2017-04-09 发布于江苏
举报
版权申诉
保障服务

BIOINFORMATICS Building an Abbreviation Dictionary Using a Term Recognition Approach.pdf

1、本文档共7页，可阅读全部内容。
2、有哪些信誉好的足球投注网站（book118）网站文档一经付费（服务费），不意味着购买了该文档的版权，仅供个人/单位学习、研究之用，不得用于商业用途，未经授权，严禁复制、发行、汇编、翻译或者网络传播等，侵权必究。
3、本站所有内容均由合作方或网友上传，本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺！文档内容仅供研究参考，付费前请自行鉴别。如您付费，意味着您自己接受本站规则且自行承担风险，本站不退款、不进行额外附加服务；查看《如何避免下载的几个坑》。如果您已付费下载过本站文档，您可以点击这里二次下载。
4、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等，请点击“版权申诉”（推荐），也可以打举报电话：400-050-0827(电话支持时间：9:00-18:30)。

BIOINFORMATICS Building an Abbreviation Dictionary Using a Term Recognition Approach

BIOINFORMATICS Building an Abbreviation Dictionary Using a Term Recognition Approach Naoaki Okazaki a,b , Sophia Ananiadou c,d a Graduate School of Information Science and Technology, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8651, Japan. b Japan Society for the Promotion of Science (JSPS). c School of Computer Science, The University of Manchester, d National Centre for Text Mining (NaCTeM), Manchester Interdisciplinary Biocentre, Oxford Road, Manchester, M13 9PL. ABSTRACT Motivation: Acronyms result from a highly productive type of term variation and trigger the need for an acronym dictionary to establish associations between acronyms and their expanded forms. Results: We propose a novel method for recognizing acronym definitions in a text collection. Assuming a word sequence co- occurring frequently with a parenthetical expression to be a potential expanded form, our method identifies acronym definitions in a similar manner to the statistical term-recognition task. Applied to the whole MEDLINE (7,811,582 abstracts), the implemented system extracted 886,755 acronym candidates and recognized 300,954 expanded forms in reasonable time. Our method outperformed base- line systems, achieving 99% precision and 82–95% recall on our evaluation corpus that roughly emulates the whole MEDLINE. Availability and Supplementary Information: The implementations and supplementary information are available at our web site: /research/acromine/ Contact: okazaki@mi.ci.i.u-tokyo.ac.jp 1 INTRODUCTION Acronyms result from a highly productive type of term variation which substitutes fully expanded terms (e.g., retinoic acid receptor alpha) with shortened term-forms (e.g., RARA). Chang et al. (2006) reported that 64,242 new acronyms were introduced in 2004 in MEDLINE abstracts. Terminological resources and scientific databases (such as UMLS 1 , Swiss-Prot 2 , SGD 3 , FlyBase 4 , and UniProt 5 ) cannot keep up-to-date with the growth of neologisms (Pustejovsky et al., 2001).