Shallow semantic labeling using two-phase feature-enhanced string matching
Publication in refereed journal

Times Cited
Web of Science3WOS source URL (as at 09/07/2020) Click here for the latest count
Altmetrics Information

Other information
AbstractA two-phase annotation method for semantic labeling in natural language processing is proposed. The dynamic programming approach stresses on a non-exact string matching which takes full advantage of the underlying grammatical structure of the parse trees in a Treebank. The first phase of the labeling is a coarse-grained syntactic parsing which is complementary to a semantic dissimilarities analysis in its latter phase. The approach goes beyond shallow parsing to a deeper level of case role identification, while preserving robustness, without being bogged down into a complete linguistic analysis. The paper presents experimental results for recognizing more than 50 different semantic labels in 10,000 sentences. Results show that the approach improves the labeling, even though with incomplete information. Detailed evaluations are discussed in order to justify its significances. (C) 2009 Elsevier Ltd. All rights reserved.
All Author(s) ListChan SWK
Journal nameExpert Systems with Applications
Volume Number36
Issue Number6
Pages9729 - 9736
LanguagesEnglish-United Kingdom
KeywordsNatural language processing; Shallow parsing; String matching
Web of Science Subject CategoriesComputer Science; Computer Science, Artificial Intelligence; COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE; Engineering; Engineering, Electrical & Electronic; ENGINEERING, ELECTRICAL & ELECTRONIC; Operations Research & Management Science; OPERATIONS RESEARCH & MANAGEMENT SCIENCE

Last updated on 2020-10-07 at 02:08