Fast online training with frequency-adaptive learning rates for chinese word segmentation and new word detection

Xu Sun, Houfeng Wang, Wenjie Li

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

56 Citations (Scopus)

Abstract

We 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.
Original languageEnglish
Title of host publication50th Annual Meeting of the Association for Computational Linguistics, ACL 2012 - Proceedings of the Conference
Pages253-262
Number of pages10
Volume1
Publication statusPublished - 1 Dec 2012
Event50th Annual Meeting of the Association for Computational Linguistics, ACL 2012 - Jeju Island, Korea, Republic of
Duration: 8 Jul 201214 Jul 2012

Conference

Conference50th Annual Meeting of the Association for Computational Linguistics, ACL 2012
Country/TerritoryKorea, Republic of
CityJeju Island
Period8/07/1214/07/12

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Software

Cite this