Word sense disambiguation (WSD) is critical in the biomedical domain for improving the precision of natural language processing (NLP), text mining, and information retrieval systems because ambiguous words negatively impact accurate access to literature containing biomolecular entities, such as genes, proteins, cells, diseases, and other important entities. Automated techniques have been developed that address the WSD problem for a number of text processing situations, but the problem is still a challenging one. Supervised WSD machine learning (ML) methods have been applied in the biomedical domain and have shown promising results, but the results typically incorporate a number of confounding factors, and it is problematic to truly understand the effectiveness and generalizability of the methods because these factors interact with each other and affect the final results. Thus, there is a need to explicitly address the factors and to systematically quantify their effects on performance.
:D\:\\ASUS-FINO\\Inkhognito_M\\David\\PhD\\Web Semântica\\Biomedicine Ontology\\Automated Acquisition\\WSD\\2006-BMC-Machine learning and word sense disambiguation in the biomedical domain - design and evaluation issues.pdf:PDF
%0 Journal Article
%1 Xu2006
%A Xu, Hua
%A Markatou, Marianthi
%A Dimova, Rositsa
%A Liu, Hongfang
%A Friedman, Carol
%D 2006
%J BMC bioinformatics
%K Algorithms,Animals,Artificial Analysis, Automated,Terminology Biology,Computational Biology: Computer-Assisted,Pattern Controlled, Intelligence,Computational Interpretation, Language Medical NLP Processing,Numerical Recognition, Statistical,Humans,Models, Statistical,Natural System,Vocabulary, Topic,Unified as methods,Data
%P 334
%R 10.1186/1471-2105-7-334
%T Machine learning and word sense disambiguation in the biomedical domain: design and evaluation issues.
%U http://www.pubmedcentral.nih.gov/
%V 7
%X Word sense disambiguation (WSD) is critical in the biomedical domain for improving the precision of natural language processing (NLP), text mining, and information retrieval systems because ambiguous words negatively impact accurate access to literature containing biomolecular entities, such as genes, proteins, cells, diseases, and other important entities. Automated techniques have been developed that address the WSD problem for a number of text processing situations, but the problem is still a challenging one. Supervised WSD machine learning (ML) methods have been applied in the biomedical domain and have shown promising results, but the results typically incorporate a number of confounding factors, and it is problematic to truly understand the effectiveness and generalizability of the methods because these factors interact with each other and affect the final results. Thus, there is a need to explicitly address the factors and to systematically quantify their effects on performance.
@article{Xu2006,
abstract = {Word sense disambiguation (WSD) is critical in the biomedical domain for improving the precision of natural language processing (NLP), text mining, and information retrieval systems because ambiguous words negatively impact accurate access to literature containing biomolecular entities, such as genes, proteins, cells, diseases, and other important entities. Automated techniques have been developed that address the WSD problem for a number of text processing situations, but the problem is still a challenging one. Supervised WSD machine learning (ML) methods have been applied in the biomedical domain and have shown promising results, but the results typically incorporate a number of confounding factors, and it is problematic to truly understand the effectiveness and generalizability of the methods because these factors interact with each other and affect the final results. Thus, there is a need to explicitly address the factors and to systematically quantify their effects on performance.},
added-at = {2015-01-14T21:25:14.000+0100},
author = {Xu, Hua and Markatou, Marianthi and Dimova, Rositsa and Liu, Hongfang and Friedman, Carol},
biburl = {https://www.bibsonomy.org/bibtex/2f6c07b7be88cfb3f977e4d7763bf57db/diverzulu},
doi = {10.1186/1471-2105-7-334},
file = {:D\:\\ASUS-FINO\\Inkhognito_M\\David\\PhD\\Web Semântica\\Biomedicine Ontology\\Automated Acquisition\\WSD\\2006-BMC-Machine learning and word sense disambiguation in the biomedical domain - design and evaluation issues.pdf:PDF},
interhash = {3409e26a5a68822737d633c0a0b9013d},
intrahash = {f6c07b7be88cfb3f977e4d7763bf57db},
issn = {1471-2105},
journal = {BMC bioinformatics},
keywords = {Algorithms,Animals,Artificial Analysis, Automated,Terminology Biology,Computational Biology: Computer-Assisted,Pattern Controlled, Intelligence,Computational Interpretation, Language Medical NLP Processing,Numerical Recognition, Statistical,Humans,Models, Statistical,Natural System,Vocabulary, Topic,Unified as methods,Data},
month = jan,
pages = 334,
pmid = {16822321},
timestamp = {2015-01-14T21:25:14.000+0100},
title = {Machine learning and word sense disambiguation in the biomedical domain: design and evaluation issues.},
url = {http://www.pubmedcentral.nih.gov/},
volume = 7,
year = 2006
}