Natural language processing for information retrieval
- 1 January 1996
- journal article
- Published by Association for Computing Machinery (ACM) in Communications of the ACM
- Vol. 39 (1) , 92-101
- https://doi.org/10.1145/234173.234210
Abstract
The paper summarizes the essential properties of document retrieval and reviews both conventionalpractice and research findings, the latter suggesting that simple statistical techniques can be effective.It then considers the new opportunities and challenges presented by the user's ability tosearch full text directly (rather than e.g. titles and abstracts), and suggests appropriate approachesto doing this, with a focus on the potential role of natural language processing. The paper also...Keywords
This publication has 18 references indexed in Scilit:
- Overview of the Second Text Retrieval Conference (TREC-2)Information Processing & Management, 1995
- The importance of proper weighting methodsPublished by Association for Computational Linguistics (ACL) ,1993
- The use of phrases and structured queries in information retrievalPublished by Association for Computing Machinery (ACM) ,1991
- Topic parsing: Accounting for text macro structures in full-text analysisInformation Processing & Management, 1990
- Natural language interfaces to databasesThe Knowledge Engineering Review, 1990
- SCISOR: extracting information from on-line newsCommunications of the ACM, 1990
- Noun classification from predicate-argument structuresPublished by Association for Computational Linguistics (ACL) ,1990
- Models for retrieval with probabilistic indexingInformation Processing & Management, 1989
- A stochastic parts program and noun phrase parser for unrestricted textPublished by Association for Computational Linguistics (ACL) ,1988
- The vocabulary problem in human-system communicationCommunications of the ACM, 1987