| EPSRC Reference: |
GR/K14223/01 |
| Title: |
BRITISH NATIONAL CORPUS: TAGGING ENHANCEMENT |
| Principal Investigator: |
Garside, Mr R |
| Other Investigators: |
|
| Researcher Co-Investigators: |
|
| Project Partners: |
|
| Department: |
Computing & Communications |
| Organisation: |
Lancaster University |
| Scheme: |
Standard Research (Pre-FEC) |
| Starts: |
01 January 1995 |
Ends: |
02 January 1995 |
Value (£): |
132,664
|
| EPSRC Research Topic Classifications: |
| Human Communication in ICT |
|
|
| EPSRC Industrial Sector Classifications: |
|
| Related Grants: |
|
| Panel History: |
|
|
Summary on Grant Application Form |
|
1. Error analysis of the current version of the tagged British National Corpus (BNC).2. Enhancement of the grammatical tagging of the BNC to achieve close to 100% accuracy and consistency in tagging.3. Development of the tagging enhancement tool for distribution to users of the corpus.Progress:Several developments are taking place concurrently, to tackle error identification and correction phases of tagging enhancement.1.A differential comparison of automatically tagged and fully hand-corrected versions of the 2 million word Core Corpus , to identify, within each text type, the major sources of error. Software is being developed to highlight collocational patterns of words and tags for each error category, and to induce potential template rules to remedy them. 2. As a first step in error correction, we intend to re-run the latest version of CLAWS over the 100M word corpus. This will enable us to take advantage of improvements made to the tagger and its resources during the course of the original BNC project, and ensure a more consistent input for the patching software. 3. Work is in progress on the program which will implement the error correction rules, and in addition to part-of-speech tags, to apply further levels of grammatical enrichment.
|
|
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.lancs.ac.uk |