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

Discriminative re-ranking 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 re-ranking and co-training, including co-training re-ranked parsers and co-training re-rankers. We show that combining discriminative re-ranking and co-training could improve the F-measure by 1.8%-2% absolute compared to co-training two state-of-the-art Chinese parsers without re-ranking, for parsing Mandarin broadcast news and conversation transcripts.