mirage

Using generation for grammar analysis and error detection

DSpace/Manakin Repository

 

Search DR-NTU


Advanced Search Subject Search

Browse

My Account

Using generation for grammar analysis and error detection

Show full item record

Title: Using generation for grammar analysis and error detection
Author: Goodman, Michael Wayne; Bond, Francis
Copyright year: 2009
Abstract: We demonstrate that the bidirectionality of deep grammars, allowing them to generate as well as parse sentences, can be used to automatically and effectively identify errors in the grammars. The system is tested on two implemented HPSG grammars: Jacy for Japanese, and the ERG for English. Using this system, we were able to increase generation coverage in Jacy by 18% (45% to 63%) with only four weeks of grammar development.
Subject: DRNTU::Humanities::Linguistics
Type: Conference Paper
Conference name: Annual Meeting of the Association for Computational Linguistics (47th : 2009 : Singapore)
School: School of Humanities and Social Sciences
Rights: Proceedings of the ACL-IJCNLP 2009 Conference Short Papers (2009:Singapore) © copyright 2009 ACL and AFNLP. The conference paper is available at www.acl-ijcnlp-2009.org/
Version: Accepted version

Files in this item

Files Size Format View Description
148255_1.pdf 82.39Kb PDF View/Open Accepted version
   

SFX Query

- Get published version (via NTU subscribed resources)
   

This item appears in the following Collection(s)

Show full item record

Statistics

Total views

All Items Views
Using generation for grammar analysis and error detection 391

Total downloads

All Bitstreams Views
148255_1.pdf 278

Top country downloads

Country Code Views
United States of America 84
China 58
Thailand 21
Singapore 18
France 9

Top city downloads

city Views
Beijing 51
Mountain View 49
Singapore 18
Bangkok 16
Chicago 5

Downloads / month

  2014-07 2014-08 2014-09 total
148255_1.pdf 0 0 3 3