Evaluation of two dependency parsers on biomedical corpus targeted at protein-protein interactions Export

@article{citeulike:2063654, abstract = {We present an evaluation of Link Grammar and Connexor Machinese Syntax, two major broad-coverage dependency parsers, on a custom hand-annotated corpus consisting of sentences regarding protein-protein interactions. In the evaluation, we apply the notion of an interaction subgraph, which is the subgraph of a dependency graph expressing a protein-protein interaction. We measure the performance of the parsers for recovery of individual dependencies, fully correct parses, and interaction subgraphs. For Link Grammar, an open system that can be inspected in detail, we further perform a comprehensive failure analysis, report specific causes of error, and suggest potential modifications to the grammar. We find that both parsers perform worse on biomedical English than previously reported on general English. While Connexor Machinese Syntax significantly outperforms Link Grammar, the failure analysis suggests specific ways in which the latter could be modified for better performance in the domain.}, author = {Pyysalo, Sampo and Ginter, Filip and Pahikkala, Tapio and Boberg, Jorma and Jarvinen, Jouni and Salakoski, Tapio}, booktitle = {Recent Advances in Natural Language Processing for Biomedical Applications Special Issue}, citeulike-article-id = {2063654}, citeulike-linkout-0 = {http://dx.doi.org/10.1016/j.ijmedinf.2005.06.009}, citeulike-linkout-1 = {http://view.ncbi.nlm.nih.gov/pubmed/16099201}, citeulike-linkout-2 = {http://www.hubmed.org/display.cgi?uids=16099201}, citeulike-linkout-3 = {http://www.sciencedirect.com/science/article/B6T7S-4GVGV0B-1/2/5c743b64f78822f163a6634f8a51449d}, doi = {10.1016/j.ijmedinf.2005.06.009}, journal = {International Journal of Medical Informatics}, keywords = {biomedicine, evaluation, parsers}, month = {June}, number = {6}, pages = {430--442}, posted-at = {2009-05-15 05:45:34}, priority = {2}, title = {Evaluation of two dependency parsers on biomedical corpus targeted at protein-protein interactions}, url = {http://dx.doi.org/10.1016/j.ijmedinf.2005.06.009}, volume = {75}, year = {2006} }

TY - JOUR ID - citeulike:2063654 L3 - citeulike-article-id:2063654 N2 - We present an evaluation of Link Grammar and Connexor Machinese Syntax, two major broad-coverage dependency parsers, on a custom hand-annotated corpus consisting of sentences regarding protein-protein interactions. In the evaluation, we apply the notion of an interaction subgraph, which is the subgraph of a dependency graph expressing a protein-protein interaction. We measure the performance of the parsers for recovery of individual dependencies, fully correct parses, and interaction subgraphs. For Link Grammar, an open system that can be inspected in detail, we further perform a comprehensive failure analysis, report specific causes of error, and suggest potential modifications to the grammar. We find that both parsers perform worse on biomedical English than previously reported on general English. While Connexor Machinese Syntax significantly outperforms Link Grammar, the failure analysis suggests specific ways in which the latter could be modified for better performance in the domain. IS - 6 JF - International Journal of Medical Informatics EP - 442 TI - Evaluation of two dependency parsers on biomedical corpus targeted at protein-protein interactions VL - 75 T2 - Recent Advances in Natural Language Processing for Biomedical Applications Special Issue SP - 430 KW - biomedicine KW - evaluation KW - parsers AU - Pyysalo, Sampo AU - Ginter, Filip AU - Pahikkala, Tapio AU - Boberg, Jorma AU - Jarvinen, Jouni AU - Salakoski, Tapio PY - 2006/06// UR - http://dx.doi.org/10.1016/j.ijmedinf.2005.06.009 ER -