TY - GEN
T1 - A comparison of chinese parsers for stanford dependencies
AU - Che, Wanxiang
AU - Spitkovsky, Valentin I.
AU - Liu, Ting
PY - 2012
Y1 - 2012
N2 - Stanford dependencies are widely used in natural language processing as a semanticallyoriented representation, commonly generated either by (i) converting the output of a constituent parser, or (ii) predicting dependencies directly. Previous comparisons of the two approaches for English suggest that starting from constituents yields higher accuracies. In this paper, we re-evaluate both methods for Chinese, using more accurate dependency parsers than in previous work. Our comparison of performance and efficiency across seven popular open source parsers (four constituent and three dependency) shows, by contrast, that recent higher-order graph-based techniques can be more accurate, though somewhat slower, than constituent parsers. We demonstrate also that n-way jackknifing is a useful technique for producing automatic (rather than gold) partof- speech tags to train Chinese dependency parsers. Finally, we analyze the relations produced by both kinds of parsing and suggest which specific parsers to use in practice.
AB - Stanford dependencies are widely used in natural language processing as a semanticallyoriented representation, commonly generated either by (i) converting the output of a constituent parser, or (ii) predicting dependencies directly. Previous comparisons of the two approaches for English suggest that starting from constituents yields higher accuracies. In this paper, we re-evaluate both methods for Chinese, using more accurate dependency parsers than in previous work. Our comparison of performance and efficiency across seven popular open source parsers (four constituent and three dependency) shows, by contrast, that recent higher-order graph-based techniques can be more accurate, though somewhat slower, than constituent parsers. We demonstrate also that n-way jackknifing is a useful technique for producing automatic (rather than gold) partof- speech tags to train Chinese dependency parsers. Finally, we analyze the relations produced by both kinds of parsing and suggest which specific parsers to use in practice.
UR - https://www.scopus.com/pages/publications/84876813610
M3 - 会议稿件
AN - SCOPUS:84876813610
SN - 9781937284251
T3 - 50th Annual Meeting of the Association for Computational Linguistics, ACL 2012 - Proceedings of the Conference
SP - 11
EP - 16
BT - 50th Annual Meeting of the Association for Computational Linguistics, ACL 2012 - Proceedings of the Conference
T2 - 50th Annual Meeting of the Association for Computational Linguistics, ACL 2012
Y2 - 8 July 2012 through 14 July 2012
ER -