Welcome to the InfoSci Platform
Reference Hub1
A Lexical Knowledge Representation Model for Natural Language Understanding

A Lexical Knowledge Representation Model for Natural Language Understanding

Ping Chen, Wei Ding, Chengmin Ding
Copyright: © 2009 |Volume: 1 |Issue: 4 |Pages: 19
ISSN: 1942-9045|EISSN: 1942-9037|ISSN: 1942-9045|EISBN13: 9781616921170|EISSN: 1942-9037|DOI: 10.4018/jssci.2009062502
Cite Article Cite Article

MLA

Chen, Ping, et al. "A Lexical Knowledge Representation Model for Natural Language Understanding." IJSSCI vol.1, no.4 2009: pp.17-35. http://doi.org/10.4018/jssci.2009062502

APA

Chen, P., Ding, W., & Ding, C. (2009). A Lexical Knowledge Representation Model for Natural Language Understanding. International Journal of Software Science and Computational Intelligence (IJSSCI), 1(4), 17-35. http://doi.org/10.4018/jssci.2009062502

Chicago

Chen, Ping, Wei Ding, and Chengmin Ding. "A Lexical Knowledge Representation Model for Natural Language Understanding," International Journal of Software Science and Computational Intelligence (IJSSCI) 1, no.4: 17-35. http://doi.org/10.4018/jssci.2009062502

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

Knowledge representation is essential for semantics modeling and intelligent information processing. For decades researchers have proposed many knowledge representation techniques. However, it is a daunting problem how to capture deep semantic information effectively and support the construction of a large-scale knowledge base efficiently. This article describes a new knowledge representation model, SenseNet, which provides semantic support for commonsense reasoning and natural language processing. SenseNet is formalized with a Hidden Markov Model. An inference algorithm is proposed to simulate human-like natural language understanding procedure. A new measurement, confidence, is introduced to facilitate the natural language understanding. The authors present a detailed case study of applying SenseNet to retrieving compensation information from company proxy filings.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.