| EPSRC Reference: |
GR/K97400/01 |
| Title: |
ANALYSIS OF NATURALLY-OCCURING ENGLISH TEXT WITH STOCHASTIC LEXICALIZED GRAMMARS |
| Principal Investigator: |
Weir, Professor D |
| Other Investigators: |
|
| Researcher Co-Investigators: |
|
| Project Partners: |
|
| Department: |
Sch of Engineering and Informatics |
| Organisation: |
University of Sussex |
| Scheme: |
Standard Research (Pre-FEC) |
| Starts: |
01 October 1996 |
Ends: |
31 December 1999 |
Value (£): |
242,836
|
| EPSRC Research Topic Classifications: |
| Human Communication in ICT |
|
|
| EPSRC Industrial Sector Classifications: |
|
| Related Grants: |
|
| Panel History: |
|
|
Summary on Grant Application Form |
|
We propose to develop a robust wide-coverage parsing system capable of accurate analysis of naturally-occurring English text to the logical form level. Our approach will involve exploiting a combination of three recent developments in natural language processing (NLP) research: statistical techniques involving online corpora; inheritance hierarchies for imposing structure on NLP data; and lexicalized grammars. While a few of the existing systems make use of one or two of these technologies, all three together form an especially powerful combination. This constitutes the underlying motivation for the proposed project. We hope to demonstrate that (1) lexicalized grammars can make particularly effective use of the kind of frequency information that can be (automatically) extracted from corpora, and (2) inheritance allows the necessarily large amounts of detailed grammatical information to be abstracted into a much smaller set of general principles and exceptions, thus facilitating system development and maintenance. We will produce a modular system that is freely available, with components that could be used in the development of various NLP-based applications.
|
|
Key Findings |
|
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
|
|
Potential use in non-academic contexts |
|
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
|
|
Impacts |
|
| Description |
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk |
| Summary |
|
| Date Materialised |
|
|
|
|
Sectors submitted by the Researcher |
|
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
|
| Project URL: |
|
| Further Information: |
|
| Organisation Website: |
http://www.sussex.ac.uk |