Comparison and combination of several MeSH indexing approaches.
作者： Dina Demner-Fushman , James G Mork , Alan R Aronson , Antonio Jose Jimeno Yepes
DOI:
关键词:
摘要: MeSH indexing of MEDLINE is becoming a more difficult task for the group highly qualified staff at US National Library Medicine, due to large yearly growth and increasing size MeSH. Since 2002, this has been assisted by Medical Text Indexer or MTI program. We extend previous machine learning analysis adding diverse set headings targeting examples where shown perform poorly. Machine algorithms exceed MTI's performance on that are used very frequently which frequency low. find when we combine suggestions prediction algorithms, improves compared any single method most evaluated headings.
参考文章(33)
Lu X, Chen L, Jin B, Chen, Mapping annotations with textual evidence using an scLDA model. american medical informatics association annual symposium. ,vol. 2011, pp. 834- 842 ,(2011)
Donald C. Comeau, Lana Yeganova, Won Kim, W. John Wilbur, Text Mining Techniques for Leveraging Positively Labeled Data meeting of the association for computational linguistics. pp. 155- 163 ,(2011)
Thomas G. Dietterich, Ensemble Methods in Machine Learning Multiple Classifier Systems. pp. 1- 15 ,(2000) , 10.1007/3-540-45014-9_1
W. Bruce Croft, Combining Approaches to Information Retrieval The Information Retrieval Series. pp. 1- 36 ,(2002) , 10.1007/0-306-47019-5_1
M E Funk, C A Reid, Indexing consistency in MEDLINE. Bulletin of The Medical Library Association. ,vol. 71, pp. 176- 183 ,(1983)
Meliha Yetisgen-Yildiz, Wanda Pratt, The effect of feature representation on MEDLINE document classification. american medical informatics association annual symposium. ,vol. 2005, pp. 849- 853 ,(2005)
Gabriel Dulac-Arnold, Ludovic Denoyer, Patrick Gallinari, Text Classification: A Sequential Reading Approach Lecture Notes in Computer Science. ,vol. 6611, pp. 411- 423 ,(2011) , 10.1007/978-3-642-20161-5_41
Marianne Lykke, Birger Larsen, Haakon Lund, Peter Ingwersen, Developing a Test Collection for the Evaluation of Integrated Search Lecture Notes in Computer Science. pp. 627- 630 ,(2010) , 10.1007/978-3-642-12275-0_63
Daniel Ramage, David Hall, Ramesh Nallapati, Christopher D. Manning, Labeled LDA: A supervised topic model for credit attribution in multi-labeled corpora empirical methods in natural language processing. pp. 248- 256 ,(2009) , 10.3115/1699510.1699543
Graham L Poulter, Daniel L Rubin, Russ B Altman, Cathal Seoighe, MScanner: a classifier for retrieving Medline citations BMC Bioinformatics. ,vol. 9, pp. 108- 108 ,(2008) , 10.1186/1471-2105-9-108