Collaborative text-annotation resource for disease-centered relation extraction from biomedical text. Export

@article{CanoMBWP09, abstract = {Agglomerating results from studies of individual biological components has shown the potential to produce biomedical discovery and the promise of therapeutic development. Such knowledge integration could be tremendously facilitated by automated text mining for relation extraction in the biomedical literature. Relation extraction systems cannot be developed without substantial datasets annotated with ground truth for benchmarking and training. The creation of such datasets is hampered by the absence of a resource for launching a distributed annotation effort, as well as by the lack of a standardized annotation schema. We have developed an annotation schema and an annotation tool which can be widely adopted so that the resulting annotated corpora from a multitude of disease studies could be assembled into a unified benchmark dataset. The contribution of this paper is threefold. First, we provide an overview of available benchmark corpora and derive a simple annotation schema for specific binary relation extraction problems such as protein-protein and gene-disease relation extraction. Second, we present BioNotate: an open source annotation resource for the distributed creation of a large corpus. Third, we present and make available the results of a pilot annotation effort of the autism disease network.}, author = {Cano, C and Monaghan, T and Blanco, A and Wall, D P P. and Peshkin, L}, citeulike-article-id = {4158899}, citeulike-linkout-0 = {http://dx.doi.org/10.1016/j.jbi.2009.02.001}, citeulike-linkout-1 = {http://view.ncbi.nlm.nih.gov/pubmed/19232400}, citeulike-linkout-2 = {http://www.hubmed.org/display.cgi?uids=19232400}, day = {14}, doi = {10.1016/j.jbi.2009.02.001}, issn = {1532-0480}, journal = {Journal of biomedical informatics}, keywords = {annotation, autism, benchmark, binary, bionotate, corpus, disease, extraction, network, relation}, month = {February}, posted-at = {2009-03-10 12:26:52}, priority = {2}, title = {Collaborative text-annotation resource for disease-centered relation extraction from biomedical text.}, url = {http://dx.doi.org/10.1016/j.jbi.2009.02.001}, year = {2009} }

TY - JOUR ID - CanoMBWP09 L3 - citeulike-article-id:4158899 N2 - Agglomerating results from studies of individual biological components has shown the potential to produce biomedical discovery and the promise of therapeutic development. Such knowledge integration could be tremendously facilitated by automated text mining for relation extraction in the biomedical literature. Relation extraction systems cannot be developed without substantial datasets annotated with ground truth for benchmarking and training. The creation of such datasets is hampered by the absence of a resource for launching a distributed annotation effort, as well as by the lack of a standardized annotation schema. We have developed an annotation schema and an annotation tool which can be widely adopted so that the resulting annotated corpora from a multitude of disease studies could be assembled into a unified benchmark dataset. The contribution of this paper is threefold. First, we provide an overview of available benchmark corpora and derive a simple annotation schema for specific binary relation extraction problems such as protein-protein and gene-disease relation extraction. Second, we present BioNotate: an open source annotation resource for the distributed creation of a large corpus. Third, we present and make available the results of a pilot annotation effort of the autism disease network. JF - Journal of biomedical informatics SN - 1532-0480 TI - Collaborative text-annotation resource for disease-centered relation extraction from biomedical text. KW - annotation KW - autism KW - benchmark KW - binary KW - bionotate KW - corpus KW - disease KW - extraction KW - network KW - relation AU - Cano, C AU - Monaghan, T AU - Blanco, A AU - Wall, D P AU - Peshkin, L PY - 2009/02/14/ UR - http://dx.doi.org/10.1016/j.jbi.2009.02.001 ER -