Browse DORAS
Browse Theses
Latest Additions
Creative Commons License
Except where otherwise noted, content on this site is licensed for use under a:

Exploiting multi-word units in history-based probabilistic generation

Hogan, Deirdre and Cafferkey, Conor and Cahill, Aoife and van Genabith, Josef (2007) Exploiting multi-word units in history-based probabilistic generation. In: EMNLP-CoNLL 2007 - Joint Meeting of the Conference on Empirical Methods in Natural Language Processing and the Conference on Computational Natural Language Learning, 28-30 June 2007, Prague, Czech Republic.

Full text available as:

PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader


We present a simple history-based model for sentence generation from LFG f-structures, which improves on the accuracy of previous models by breaking down PCFG independence assumptions so that more f-structure conditioning context is used in the prediction of grammar rule expansions. In addition, we present work on experiments with named entities and other multi-word units, showing a statistically significant improvement of generation accuracy. Tested on section 23 of the PennWall Street Journal Treebank, the techniques described in this paper improve BLEU scores from 66.52 to 68.82, and coverage from 98.18% to 99.96%.

Item Type:Conference or Workshop Item (Paper)
Event Type:Conference
Uncontrolled Keywords:lexical functional grammar;
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:
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
ID Code:15212
Deposited On:17 Feb 2010 16:40 by DORAS Administrator. Last Modified 17 Feb 2010 16:40

Download statistics

Archive Staff Only: edit this record