Parser-based retraining for domain adaptation of probabilistic generators
Hogan, Deirdre, Foster, JenniferORCID: 0000-0002-7789-4853, Wagner, JoachimORCID: 0000-0002-8290-3849 and van Genabith, Josef
(2008)
Parser-based retraining for domain adaptation of probabilistic generators.
In: INLG 08 - 5th International Natural Language Generation Conference, 12-14 June 2008, Salt Fork, Ohio, USA.
While the effect of domain variation on Penn-treebank-
trained probabilistic parsers has been investigated in previous work, we study its effect on a Penn-Treebank-trained probabilistic generator. We show that applying the generator to data from the British National Corpus
results in a performance drop (from a BLEU score of 0.66 on the standard WSJ test set to a BLEU score of 0.54 on our BNC test set). We develop a generator retraining method where the domain-specific training data is automatically
produced using state-of-the-art parser output. The retraining method recovers a substantial portion of the performance drop, resulting in a generator which achieves a BLEU score of 0.61 on our BNC test data.
This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License
Funders:
Enterprise Ireland, EI CFTD/2007/229, Science Foundation Ireland, SFI 04/IN/I527, Irish Research Council for Science Engineering and Technology, IRCSET P/04/232
ID Code:
15194
Deposited On:
16 Feb 2010 14:59 by
DORAS Administrator
. Last Modified 10 Oct 2018 15:16