Probabilistic Chinese word segmentation with non-local information and stochastic training

Authors:
Xu Sun;Yaozhong Zhang;Takuya Matsuzaki;Yoshimasa Tsuruoka;Jun'Ichi Tsujii
Affiliations:
Key Laboratory of Computational Linguistics (Peking University), Ministry of Education, Beijing, China and School of EECS, Peking University, Beijing, China;Dept of Computer Science, The University of Tokyo, Tokyo, Japan;National Institute of Informatics, Tokyo, Japan;Dept of EEIS, The University of Tokyo, Tokyo, Japan;Microsoft Research Asia, Haidian District, Beijing, China
Venue:
Information Processing and Management: an International Journal
Year:
2013

Citing 15
Cited 0

Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data

ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
Chinese segmentation and new word detection using conditional random fields

COLING '04 Proceedings of the 20th international conference on Computational Linguistics
Pegasos: Primal Estimated sub-GrAdient SOlver for SVM

Proceedings of the 24th international conference on Machine learning
Hidden Conditional Random Fields

IEEE Transactions on Pattern Analysis and Machine Intelligence
Exponentiated Gradient Algorithms for Conditional Random Fields and Max-Margin Markov Networks

The Journal of Machine Learning Research
Modeling latent-dynamic in shallow parsing: a latent conditional model with improved inference

COLING '08 Proceedings of the 22nd International Conference on Computational Linguistics - Volume 1
Sequential labeling with latent variables: an exact inference algorithm and its efficient approximation

EACL '09 Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics
A hybrid Markov/semi-Markov conditional random field for sequence segmentation

EMNLP '06 Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing
A discriminative latent variable chinese segmenter with hybrid word/character information

NAACL '09 Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics
Latent variable perceptron algorithm for structured classification

IJCAI'09 Proceedings of the 21st international jont conference on Artifical intelligence
Stochastic gradient descent training for L1-regularized log-linear models with cumulative penalty

ACL '09 Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP: Volume 1 - Volume 1
Robust approach to abbreviating terms: a discriminative latent variable model with global information

ACL '09 Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP: Volume 2 - Volume 2
A Unified Character-Based Tagging Framework for Chinese Word Segmentation

ACM Transactions on Asian Language Information Processing (TALIP)
Integrating unsupervised and supervised word segmentation: The role of goodness measures

Information Sciences: an International Journal
Fast online training with frequency-adaptive learning rates for Chinese word segmentation and new word detection

ACL '12 Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Long Papers - Volume 1

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this article, we focus on Chinese word segmentation by systematically incorporating non-local information based on latent variables and word-level features. Differing from previous work which captures non-local information by using semi-Markov models, we propose an alternative method for modeling non-local information: a latent variable word segmenter employing word-level features. In order to reduce computational complexity of learning non-local information, we further present an improved online training method, which can arrive the same objective optimum with a significantly accelerated training speed. We find that the proposed method can help the learning of long range dependencies and improve the segmentation quality of long words (for example, complicated named entities). Experimental results demonstrate that the proposed method is effective. With this improvement, evaluations on the data of the second SIGHAN CWS bakeoff show that our system is competitive with the state-of-the-art systems.