Login (DCU Staff Only)
Login (DCU Staff Only)

DORAS | DCU Research Repository

Explore open access research and scholarly works from DCU

Advanced Search

Adapting WSJ-trained parsers to the British national corpus using in-domain self-training

Foster, Jennifer orcid logoORCID: 0000-0002-7789-4853, Wagner, Joachim orcid logoORCID: 0000-0002-8290-3849, Seddah, Djamé and van Genabith, Josef (2007) Adapting WSJ-trained parsers to the British national corpus using in-domain self-training. In: IWPT 2007 - 10th International Conference of Parsing Technology, 23-24 June 2007, Prague, Czech Republic.

Abstract
We introduce a set of 1,000 gold standard parse trees for the British National Corpus (BNC) and perform a series of self-training experiments with Charniak and Johnson’s reranking parser and BNC sentences. We show that retraining this parser with a combination of one million BNC parse trees (produced by the same parser) and the original WSJ training data yields improvements of 0.4% on WSJ Section 23 and 1.7% on the new BNC gold standard set.
Metadata
Item Type:Conference or Workshop Item (Paper)
Event Type:Conference
Refereed:Yes
Uncontrolled Keywords:parsers;
Subjects:Computer Science > Machine translating
DCU Faculties and Centres:Research Initiatives and Centres > National Centre for Language Technology (NCLT)
DCU Faculties and Schools > Faculty of Engineering and Computing > School of Computing
Publisher:Association for Computational Linguistics
Official URL:http://aclweb.org/anthology/W/W07/
Copyright Information:© 2007 Association for Computational Linguistics
Use License:This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License
Funders:Irish Research Council for Science Engineering and Technology, IRCSET SC/02/298, IRCSET P/04/232, Science Foundation Ireland, SFI 04/IN.3/I527
ID Code:15209
Deposited On:17 Feb 2010 16:06 by DORAS Administrator . Last Modified 10 Oct 2018 15:17
Documents

Full text available as:

[thumbnail of jfoster_et_al_07.pdf]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
29kB
Downloads

Downloads

Downloads per month over past year

Archive Staff Only: edit this record