GENETAG: a tagged corpus for gene/protein named entity recognition. Export

@article{tanabe2005, abstract = {BACKGROUND: Named entity recognition (NER) is an important first step for text mining the biomedical literature. Evaluating the performance of biomedical NER systems is impossible without a standardized test corpus. The annotation of such a corpus for gene/protein name NER is a difficult process due to the complexity of gene/protein names. We describe the construction and annotation of GENETAG, a corpus of 20K MEDLINE sentences for gene/protein NER. 15K GENETAG sentences were used for the BioCreAtIvE Task 1A Competition. RESULTS: To ensure heterogeneity of the corpus, MEDLINE sentences were first scored for term similarity to documents with known gene names, and 10K high- and 10K low-scoring sentences were chosen at random. The original 20K sentences were run through a gene/protein name tagger, and the results were modified manually to reflect a wide definition of gene/protein names subject to a specificity constraint, a rule that required the tagged entities to refer to specific entities. Each sentence in GENETAG was annotated with acceptable alternatives to the gene/protein names it contained, allowing for partial matching with semantic constraints. Semantic constraints are rules requiring the tagged entity to contain its true meaning in the sentence context. Application of these constraints results in a more meaningful measure of the performance of an NER system than unrestricted partial matching. CONCLUSION: The annotation of GENETAG required intricate manual judgments by annotators which hindered tagging consistency. The data were pre-segmented into words, to provide indices supporting comparison of system responses to the "gold standard". However, character-based indices would have been more robust than word-based indices. GENETAG Train, Test and Round1 data and ancillary programs are freely available at ftp://ftp.ncbi.nlm.nih.gov/pub/tanabe/GENETAG.tar.gz. A newer version of GENETAG-05, will be released later this year.}, address = {National Center for Biotechnology Information, National Library of Medicine, NIH, 8600 Rockville Pike, Bethesda, MD 20894, USA. tanabe@ncbi.nlm.nih.gov}, author = {Tanabe, Lorraine and Xie, Natalie and Thom, Lynne H. and Matten, Wayne and Wilbur, W. John}, citeulike-article-id = {556830}, citeulike-linkout-0 = {http://dx.doi.org/10.1186/1471-2105-6-S1-S3}, citeulike-linkout-1 = {http://view.ncbi.nlm.nih.gov/pubmed/15960837}, citeulike-linkout-2 = {http://www.hubmed.org/display.cgi?uids=15960837}, doi = {10.1186/1471-2105-6-S1-S3}, issn = {1471-2105}, journal = {BMC bioinformatics}, keywords = {corpus, gene, karla, parser, protein, text-mining}, posted-at = {2009-08-25 11:51:54}, priority = {2}, title = {GENETAG: a tagged corpus for gene/protein named entity recognition.}, url = {http://dx.doi.org/10.1186/1471-2105-6-S1-S3}, volume = {6 Suppl 1}, year = {2005} }

TY - JOUR ID - tanabe2005 L3 - citeulike-article-id:556830 N2 - BACKGROUND: Named entity recognition (NER) is an important first step for text mining the biomedical literature. Evaluating the performance of biomedical NER systems is impossible without a standardized test corpus. The annotation of such a corpus for gene/protein name NER is a difficult process due to the complexity of gene/protein names. We describe the construction and annotation of GENETAG, a corpus of 20K MEDLINE sentences for gene/protein NER. 15K GENETAG sentences were used for the BioCreAtIvE Task 1A Competition. RESULTS: To ensure heterogeneity of the corpus, MEDLINE sentences were first scored for term similarity to documents with known gene names, and 10K high- and 10K low-scoring sentences were chosen at random. The original 20K sentences were run through a gene/protein name tagger, and the results were modified manually to reflect a wide definition of gene/protein names subject to a specificity constraint, a rule that required the tagged entities to refer to specific entities. Each sentence in GENETAG was annotated with acceptable alternatives to the gene/protein names it contained, allowing for partial matching with semantic constraints. Semantic constraints are rules requiring the tagged entity to contain its true meaning in the sentence context. Application of these constraints results in a more meaningful measure of the performance of an NER system than unrestricted partial matching. CONCLUSION: The annotation of GENETAG required intricate manual judgments by annotators which hindered tagging consistency. The data were pre-segmented into words, to provide indices supporting comparison of system responses to the "gold standard". However, character-based indices would have been more robust than word-based indices. GENETAG Train, Test and Round1 data and ancillary programs are freely available at ftp://ftp.ncbi.nlm.nih.gov/pub/tanabe/GENETAG.tar.gz. A newer version of GENETAG-05, will be released later this year. JF - BMC bioinformatics SN - 1471-2105 AD - National Center for Biotechnology Information, National Library of Medicine, NIH, 8600 Rockville Pike, Bethesda, MD 20894, USA. tanabe@ncbi.nlm.nih.gov TI - GENETAG: a tagged corpus for gene/protein named entity recognition. VL - 6 Suppl 1 KW - corpus KW - gene KW - karla KW - parser KW - protein KW - text-mining AU - Tanabe, Lorraine AU - Xie, Natalie AU - Thom, Lynne AU - Matten, Wayne AU - Wilbur, John PY - 2005/// UR - http://dx.doi.org/10.1186/1471-2105-6-S1-S3 ER -