Brought to you by EarthWeb
IT Library Logo

Click Here!
Click Here!

Search the site:
 
EXPERT SEARCH -----
Programming Languages
Databases
Security
Web Services
Network Services
Middleware
Components
Operating Systems
User Interfaces
Groupware & Collaboration
Content Management
Productivity Applications
Hardware
Fun & Games

EarthWeb Direct EarthWeb Direct Fatbrain Auctions Support Source Answers

EarthWeb sites
Crossnodes
Datamation
Developer.com
DICE
EarthWeb.com
EarthWeb Direct
ERP Hub
Gamelan
GoCertify.com
HTMLGoodies
Intranet Journal
IT Knowledge
IT Library
JavaGoodies
JARS
JavaScripts.com
open source IT
RoadCoders
Y2K Info

Previous Table of Contents Next


6. SUMMARY AND CONCLUSION

In this chapter, we have examined the Natural Language Processing (NLP) techniques that can be of some utility in an expert system (and, more generally, knowledge-based system) context. After a short historical introduction, we recalled the traditional differentiation of the NLP domain into morphological analysis, syntactic analysis, semantic analysis, discourse, and pragmatic analysis -- even if this sort of distinction becomes sometimes blurred in modern systems (see, e.g., the dialog, and the Spoken Language Understanding systems), it is still particularly effective from a didactic point of view. For each of these subfields, we have analyzed quickly the most important techniques used, devoting some additional space to particularly "hot" topics like unification grammars in syntax and conceptual representation in semantics. A section mentioning some of the most promising trends in the NLP domain concludes the chapter.

The NLP domain has changed dramatically over recent years. Some, not necessarily trivial, commercial NLP products are now on the market, and it is easy to anticipate the fact that future ESs and KBSs will increasingly integrate components produced by the NLP technology. The success of pragmatically based applications such as extraction of information from texts or speech recognition systems has moved the focus from pure theoretical research, oriented toward the production of toy systems in very limited domains, to applied research largely motivated by industrial considerations, and oriented toward the construction of larger-scale NLP systems. Even if NLP still constitutes one of the more complex and difficult endeavors in computer science, the domain seems now sufficiently ripe to contribute to the establishment and to the consolidation of a concrete, sound, and human-friendly computer technology for the next millennium.

REFERENCES

Allen, J. (1987) Natural Language Understanding. Menlo Park (CA): Benjamin/Cummings.
Androutsopoulos, I., Ritchie, G.D., and Thanisch, P. (1995) "Natural Language Interfaces to
Databases -- An Introduction," Natural Language Engineering, 1, 29-81.
Carter, D. (1987) Interpreting Anaphors in Natural Language Texts. Chichester: Ellis
Horwood.
Cowie, J., and Lehnert, W. (1996) "Information Extraction," Communications of the ACM,
39(1), 80-91.
Knight, K. (1989) "Unification: A Multidisciplinary Survey," ACM Computing Surveys, 21,
93-124.
Pereira, F.C.N., and Grosz, B.J., Eds. (1994) Natural Language Processing. Cambridge (MA):
The MIT Press.
Shieber, S.M. (1992) Constraint-Based Grammar Formalisms. Cambridge (MA): The MIT
Press.
Sowa, J.F. (1991) "Toward the Expressive Power of Natural Language," in Principles of
Semantic Networks, Sowa, J.F., Ed. San Mateo (CA): Morgan Kaufmann.
Special Section on Interactive Natural Language Processing, 1996, Manaris, B.Z., and Slator,
B.M., Eds., IEEE Computer, 29(7), 28-86.
Zarri, G.P. (1995) "Knowledge Acquisition from Complex Narrative Texts Using the NKRL
Technology," in Proceedings of the 9th Banff Knowledge Acquisition for Knowledge-Based Systems Workshop, Vol. 1. Calgary: Department of Computer Science of the University.


Previous Table of Contents Next

footer nav
Use of this site is subject certain Terms & Conditions.
Copyright (c) 1996-1999 EarthWeb, Inc.. All rights reserved. Reproduction in whole or in part in any form or medium without express written permission of EarthWeb is prohibited. Please read our privacy policy for details.