%0 Conference Paper %1 palakal.bio.rel.2002 %A Palakal, Mathew %A Stephens, Matthew %A Mukhopadhyay, Snehasis %A Raje, Rajeev %A Rhodes, Simon %B CSB '02: Proceedings of the IEEE Computer Society Conference on Bioinformatics %C Washington, DC, USA %D 2002 %I IEEE Computer Society %K CAT CAT-REL-ML-HMM-directed-rel CAT-REL-STAT-n-gram %P 97 %T A Multi-Level Text Mining Method to Extract Biological Relationships %X Accurate and computationally efficient approaches in discovering relationships between biological objects from text documents are important for biologists to develop biological models. This paper presents a novel approach to extract relationships between multiplebiological objects that are present in a text document. The approach involves object identification, reference resolution, ontology and synonym discovery, and extracting object-object relationships. Hidden Markov Models (HMMs), dictionaries, and N-Gram models are used to set the framework to tackle the complex task of extracting object-object relationships. Experiments were carried out using a corpus of one thousand Medline abstracts. Intermediate results were obtained for the object identification process, synonym discovery, and finally the relationship extraction. For a corpus of thousand abstracts, 53 relationships were extracted of which 43 were correct, giving a specificity of 81%. The approach is both adaptable and scalable to new problems as opposed to rule-based methods. %@ 0-7695-1653-X

@inproceedings{palakal.bio.rel.2002, abstract = {Accurate and computationally efficient approaches in discovering relationships between biological objects from text documents are important for biologists to develop biological models. This paper presents a novel approach to extract relationships between multiplebiological objects that are present in a text document. The approach involves object identification, reference resolution, ontology and synonym discovery, and extracting object-object relationships. Hidden Markov Models (HMMs), dictionaries, and N-Gram models are used to set the framework to tackle the complex task of extracting object-object relationships. Experiments were carried out using a corpus of one thousand Medline abstracts. Intermediate results were obtained for the object identification process, synonym discovery, and finally the relationship extraction. For a corpus of thousand abstracts, 53 relationships were extracted of which 43 were correct, giving a specificity of 81%. The approach is both adaptable and scalable to new problems as opposed to rule-based methods.}, added-at = {2010-11-07T23:41:18.000+0100}, address = {Washington, DC, USA}, author = {Palakal, Mathew and Stephens, Matthew and Mukhopadhyay, Snehasis and Raje, Rajeev and Rhodes, Simon}, biburl = {https://www.bibsonomy.org/bibtex/20c968cbd435ad9abbcae938ca4a85c3f/huiyangsfsu}, booktitle = {CSB '02: Proceedings of the IEEE Computer Society Conference on Bioinformatics}, interhash = {7ec8158642b66f1cd9daff1fc59271c3}, intrahash = {0c968cbd435ad9abbcae938ca4a85c3f}, isbn = {0-7695-1653-X}, keywords = {CAT CAT-REL-ML-HMM-directed-rel CAT-REL-STAT-n-gram}, pages = 97, publisher = {IEEE Computer Society}, timestamp = {2010-11-09T06:05:57.000+0100}, title = {A Multi-Level Text Mining Method to Extract Biological Relationships}, year = 2002 }