Sciweavers

Share
ICASSP
2009
IEEE

Combining discriminative re-ranking and co-training for parsing Mandarin speech transcripts

10 years 4 months ago
Combining discriminative re-ranking and co-training for parsing Mandarin speech transcripts
Discriminative reranking has been able to significantly improve parsing performance, and co-training has proven to be an effective weakly supervised learning algorithm to bootstrap parsers from a small in-domain seed labeled corpus using a large amount of unlabeled in-domain data. In this paper, we present systematic investigations on combining discriminative reranking and co-training, including co-training reranked parsers and co-training rerankers. We show that combining discriminative reranking and co-training could im
Wen Wang
Added 21 May 2010
Updated 21 May 2010
Type Conference
Year 2009
Where ICASSP
Authors Wen Wang
Comments (0)
books