Paper Info
Title
A Separately Passive-Aggressive Training Algorithm for Joint POS Tagging and Dependency Parsing.
Abstract
Recent study shows that parsing accuracy can be largely improved by the joint optimization of part-of-speech (POS) tagging and dependency parsing. However, the POS tagging task does not benefit much from the joint framework. We argue that the fundamental reason behind is because the POS features are overwhelmed by the syntactic features during the joint optimization, and the joint models only prefer such POS tags that are favourable solely from the parsing viewpoint. To solve this issue, we propose a separately passive-aggressive learning algorithm (SPA), which is designed to separately update the POS features weights and the syntactic feature weights under the joint optimization framework. The proposed SPA is able to take advantage of previous joint optimization strategies to significantly improve the parsing accuracy, but also overcome their shortages to significantly boost the tagging accuracy by effectively solving the syntax-insensitive POS ambiguity issues. Experiments on the Chinese Penn Treebank 5.1 (CTB5) and the English Penn Treebank (PTB) demonstrate the effectiveness of our proposed methodology and empirically verify our observations as discussed above. We achieve the best tagging and parsing accuracies on both datasets, 94.60% in tagging accuracy and 81.67% in parsing accuracy on CTB5, and 97.62% and 93.52% on PTB. © 2012 The COLING.
Year
DOI
Venue
2012
null
COLING
Keywords
Field
DocType
dependency parsing,joint models,part-of-speech tagging,separately passiveaggressive algorithm
Computer science,Algorithm,Speech recognition,Dependency grammar,Natural language processing,Artificial intelligence,Treebank,Parsing,Economic shortage,Syntax,Ambiguity
Conference
Volume
Issue
ISSN
null
null
null
Citations 
PageRank 
References 
14
0.54
30
Authors
4
Name
Order
Citations
PageRank
Zhenghua Li132528.48
Min Zhang21849157.00
Wanxiang Che371166.39
Ting Liu42735232.31