Expired Project

Parsing the British National Corpus (100M Words) with Automatically Acquired Deep probabilistic LFG Resources

Project details

Project title: Parsing the British National Corpus (100M Words) with Automatically Acquired Deep probabilistic LFG Resources
Project code: dccom003c
Project class: C

Start date: Friday 28 April 2006
End date: Monday 28 August 2006

Full National Service

National Capability Service

People

Project PI: Dr. Djame Seddah
Number of users: 2-5
Registered users: 3

Resulting publications

• A Comparative Evaluation of Deep and Shallow Approaches to the Automatic Detection of Common Grammatical ErrorsEMNLP-CoNLL
• Adapting WSJ-Trained Parsers to the British National Corpus using In-Domain Self-Training
• C-Structures and F-Structures for the British National Corpus (In Proceedings of the Twelfth International Lexical Functional Grammar Conference LFG07)

Allocated resources