Sciweavers

29 search results - page 1 / 6
» When is Self-Training Effective for Parsing
Sort
View
COLING
2008
13 years 9 months ago
When is Self-Training Effective for Parsing?
Self-training has been shown capable of improving on state-of-the-art parser performance (McClosky et al., 2006) despite the conventional wisdom on the matter and several studies ...
David McClosky, Eugene Charniak, Mark Johnson
EMNLP
2009
13 years 5 months ago
Self-Training PCFG Grammars with Latent Annotations Across Languages
We investigate the effectiveness of selftraining PCFG grammars with latent annotations (PCFG-LA) for parsing languages with different amounts of labeled training data. Compared to...
Zhongqiang Huang, Mary P. Harper
ACL
2011
12 years 11 months ago
Effective Measures of Domain Similarity for Parsing
It is well known that parsing accuracy suffers when a model is applied to out-of-domain data. It is also known that the most beneficial data to parse a given domain is data that ...
Barbara Plank, Gertjan van Noord
COLING
2010
13 years 2 months ago
Effective Constituent Projection across Languages
We describe an effective constituent projection strategy, where constituent projection is performed on the basis of dependency projection. Especially, a novel measurement is propo...
Wenbin Jiang, Yajuan Lv, Yang Liu, Qun Liu
ACL
2010
13 years 5 months ago
Transition-Based Parsing with Confidence-Weighted Classification
We show that using confidence-weighted classification in transition-based parsing gives results comparable to using SVMs with faster training and parsing time. We also compare wit...
Martin Haulrich