Dissertation/Thesis Abstract

Relationship Extraction and Link Discovery from Biomedical Literature
by Katukuri, Jayasimha, Ph.D., University of Louisiana at Lafayette, 2012, 133; 3548402
Abstract (Summary)

The number of published literature documents is growing enormously. While growth in the biosciences field is encouraging for researchers, it also brings the problems of information overload, making it difficult to keep abreast of all of the developments in the field. Information retrieval systems (search engines) alone would not be sufficient to address the needs of researchers. Information extraction (IE) tools, which extract specific pieces of information from text documents for the user queries, are extremely valuable.

In this dissertation, we propose a structure called bio-semantic token subsequence to capture semantic features from natural language sentences for biomedical relationship extraction. We developed two supervised learning algorithms for extracting semantic relationships between entities. The first approach "bio-semantic token subsequence kernel" implicitly utilizes features captured by the bio-semantic token subsequences. The second learning approach is called "discriminative bio-semantic token subsequence classifier", which explicitly generates a discriminative subset of bio-semantic token subsequences. In our experimental evaluations, both of these proposed methods outperformed the state-of-the-art methods reported in the literature.

A key issue in text mining is the linking together of the extracted information to form new facts or hypotheses, which can subsequently be explored further by conventional means of experimentation. In this dissertation, we modeled biomedical literature repository as a comprehensive network of biomedical concepts and proposed and evaluated a supervised link discovery method for performing large-scale cross-silo biomedical hypothesis discovery.

Indexing (document details)
Advisor: Raghavan, Vijay V.
Commitee: Chu, Chee-Hung Henry, Efe, Kemal
School: University of Louisiana at Lafayette
Department: Computer Science
School Location: United States -- Louisiana
Source: DAI-B 74/05(E), Dissertation Abstracts International
Source Type: DISSERTATION
Subjects: Computer science
Keywords: Bioinformatics, Data mining, Information extraction, Link discovery, Machine learning, Nlp, Text mining
Publication Number: 3548402
ISBN: 9781267838124
Copyright © 2019 ProQuest LLC. All rights reserved. Terms and Conditions Privacy Policy Cookie Policy
ProQuest