Unsupervised Discovery of Compound Entities for Relationship Extraction Export

@incollection{citeulike:4446452, abstract = {In this paper we investigate unsupervised population of a biomedical ontology via information extraction from biomedical literature. Relationships in text seldom connect simple entities. We therefore focus on identifying compound entities rather than mentions of simple entities. We present a method based on rules over grammatical dependency structures for unsupervised segmentation of sentences into compound entities and relationships. We complement the rule-based approach with a statistical component that prunes structures with low information content, thereby reducing false positives in the prediction of compound entities, their constituents and relationships. The extraction is manually evaluated with respect to the UMLS Semantic Network by analyzing the conformance of the extracted triples with the corresponding UMLS relationship type definitions.}, author = {Ramakrishnan, Cartic and Mendes, Pablo and Wang, Shaojun and Sheth, Amit}, citeulike-article-id = {4446452}, citeulike-linkout-0 = {http://dx.doi.org/10.1007/978-3-540-87696-0_15}, citeulike-linkout-1 = {http://www.springerlink.com/content/q627837504173220}, doi = {10.1007/978-3-540-87696-0_15}, journal = {Knowledge Engineering: Practice and Patterns}, keywords = {biology, needpdf, nested\_ner}, pages = {146--155}, posted-at = {2009-08-04 00:08:36}, priority = {2}, title = {Unsupervised Discovery of Compound Entities for Relationship Extraction}, url = {http://dx.doi.org/10.1007/978-3-540-87696-0_15}, year = {2008} }

TY - CHAP ID - citeulike:4446452 L3 - citeulike-article-id:4446452 N2 - In this paper we investigate unsupervised population of a biomedical ontology via information extraction from biomedical literature. Relationships in text seldom connect simple entities. We therefore focus on identifying compound entities rather than mentions of simple entities. We present a method based on rules over grammatical dependency structures for unsupervised segmentation of sentences into compound entities and relationships. We complement the rule-based approach with a statistical component that prunes structures with low information content, thereby reducing false positives in the prediction of compound entities, their constituents and relationships. The extraction is manually evaluated with respect to the UMLS Semantic Network by analyzing the conformance of the extracted triples with the corresponding UMLS relationship type definitions. JF - Knowledge Engineering: Practice and Patterns EP - 155 TI - Unsupervised Discovery of Compound Entities for Relationship Extraction SP - 146 KW - biology KW - needpdf KW - nested_ner AU - Ramakrishnan, Cartic AU - Mendes, Pablo AU - Wang, Shaojun AU - Sheth, Amit PY - 2008/// UR - http://dx.doi.org/10.1007/978-3-540-87696-0_15 ER -