TitleFast online training with frequency-adaptive learning rates for chinese word segmentation and new word detection
AuthorsSun, Xu
Wang, Houfeng
Li, Wenjie
AffiliationDepartment of Computing, Hong Kong Polytechnic University, Hong Kong
Key Laboratory of Computational Linguistics, Ministry of Education, Peking University, China
Issue Date2012
Citation50th Annual Meeting of the Association for Computational Linguistics, ACL 2012.Jeju Island, Korea, Republic of,1(253-262).
AbstractWe present a joint model for Chinese word segmentation and new word detection. We present high dimensional new features, including word-based features and enriched edge (label-transition) features, for the joint modeling. As we know, training a word segmentation system on large-scale datasets is already costly. In our case, adding high dimensional new features will further slow down the training speed. To solve this problem, we propose a new training method, adaptive online gradient descent based on feature frequency information, for very fast online training of the parameters, even given large-scale datasets with high dimensional features. Compared with existing training methods, our training method is an order magnitude faster in terms of training time, and can achieve equal or even higher accuracies. The proposed fast training method is a general purpose optimization method, and it is not limited in the specific task discussed in this paper. ? 2012 Association for computational Linguistics.
Appears in Collections:计算语言学教育部重点实验室

Files in This Work
There are no files associated with this item.

Web of Science®

Checked on Last Week


Checked on Current Time

License: See PKU IR operational policies.