Learning Relations from Biomedical Corpora Using Dependency Trees Export

@incollection{citeulike:3020599, abstract = {In this paper we address the relation learning problem in the biomedical domain. We propose a representation which takes into account the syntactic information and allows for using different machine learning methods. To carry out the syntactic analysis, three parsers, LinkParser, Minipar and Charniak parser were used. The results we have obtained are comparable to the performance of relation learning systems in the biomedical domain and in some cases out-perform them. In addition, we have studied the impact of ensemble methods on learning relations using the representation we proposed. Given that recall is very important for the relation learning, we explored the ways of improving it. It has been shown that ensemble methods provide higher recall and precision than individual classifiers alone.}, author = {Katrenko, Sophia and Adriaans, Pieter}, booktitle = {Knowledge Discovery and Emergent Complexity in Bioinformatics }, citeulike-article-id = {3020599}, citeulike-linkout-0 = {http://dx.doi.org/10.1007/978-3-540-71037-0_5}, citeulike-linkout-1 = {http://www.springerlink.com/content/n145566q7t1u4365}, doi = {10.1007/978-3-540-71037-0_5}, journal = {Knowledge Discovery and Emergent Complexity in Bioinformatics}, pages = {61--80}, posted-at = {2008-10-15 12:43:54}, priority = {2}, title = {Learning Relations from Biomedical Corpora Using Dependency Trees}, url = {http://dx.doi.org/10.1007/978-3-540-71037-0_5}, year = {2007} }

TY - CHAP ID - citeulike:3020599 L3 - citeulike-article-id:3020599 N2 - In this paper we address the relation learning problem in the biomedical domain. We propose a representation which takes into account the syntactic information and allows for using different machine learning methods. To carry out the syntactic analysis, three parsers, LinkParser, Minipar and Charniak parser were used. The results we have obtained are comparable to the performance of relation learning systems in the biomedical domain and in some cases out-perform them. In addition, we have studied the impact of ensemble methods on learning relations using the representation we proposed. Given that recall is very important for the relation learning, we explored the ways of improving it. It has been shown that ensemble methods provide higher recall and precision than individual classifiers alone. JF - Knowledge Discovery and Emergent Complexity in Bioinformatics EP - 80 TI - Learning Relations from Biomedical Corpora Using Dependency Trees T2 - Knowledge Discovery and Emergent Complexity in Bioinformatics SP - 61 AU - Katrenko, Sophia AU - Adriaans, Pieter PY - 2007/// UR - http://dx.doi.org/10.1007/978-3-540-71037-0_5 ER -