An environment for relation mining over richly annotated corpora: the case of GENIA. Export

@article{citeulike:2363352, abstract = {BACKGROUND: The biomedical domain is witnessing a rapid growth of the amount of published scientific results, which makes it increasingly difficult to filter the core information. There is a real need for support tools that 'digest' the published results and extract the most important information. RESULTS: We describe and evaluate an environment supporting the extraction of domain-specific relations, such as protein-protein interactions, from a richly-annotated corpus. We use full, deep-linguistic parsing and manually created, versatile patterns, expressing a large set of syntactic alternations, plus semantic ontology information. CONCLUSION: The experiments show that our approach described is capable of delivering high-precision results, while maintaining sufficient levels of recall. The high level of abstraction of the rules used by the system, which are considerably more powerful and versatile than finite-state approaches, allows speedy interactive development and validation.}, author = {Rinaldi, F. and Schneider, G. and Kaljurand, K. and Hess, M. and Romacker, M.}, citeulike-article-id = {2363352}, citeulike-linkout-0 = {http://dx.doi.org/10.1186/1471-2105-7-S3-S3}, citeulike-linkout-1 = {http://view.ncbi.nlm.nih.gov/pubmed/17134476}, citeulike-linkout-2 = {http://www.hubmed.org/display.cgi?uids=17134476}, doi = {10.1186/1471-2105-7-S3-S3}, issn = {1471-2105}, journal = {BMC bioinformatics}, keywords = {fabio-rinaldi, genia, text-mining}, number = {Suppl 3}, posted-at = {2009-07-06 14:38:39}, priority = {2}, title = {An environment for relation mining over richly annotated corpora: the case of GENIA.}, url = {http://dx.doi.org/10.1186/1471-2105-7-S3-S3}, volume = {7 Suppl 3}, year = {2006} }

TY - JOUR ID - citeulike:2363352 L3 - citeulike-article-id:2363352 N2 - BACKGROUND: The biomedical domain is witnessing a rapid growth of the amount of published scientific results, which makes it increasingly difficult to filter the core information. There is a real need for support tools that 'digest' the published results and extract the most important information. RESULTS: We describe and evaluate an environment supporting the extraction of domain-specific relations, such as protein-protein interactions, from a richly-annotated corpus. We use full, deep-linguistic parsing and manually created, versatile patterns, expressing a large set of syntactic alternations, plus semantic ontology information. CONCLUSION: The experiments show that our approach described is capable of delivering high-precision results, while maintaining sufficient levels of recall. The high level of abstraction of the rules used by the system, which are considerably more powerful and versatile than finite-state approaches, allows speedy interactive development and validation. IS - Suppl 3 JF - BMC bioinformatics SN - 1471-2105 TI - An environment for relation mining over richly annotated corpora: the case of GENIA. VL - 7 Suppl 3 KW - fabio-rinaldi KW - genia KW - text-mining AU - Rinaldi, F AU - Schneider, G AU - Kaljurand, K AU - Hess, M AU - Romacker, M PY - 2006/// UR - http://dx.doi.org/10.1186/1471-2105-7-S3-S3 ER -