Joint training and decoding using virtual nodes for cascaded segmentation and tagging tasks

Authors:
Xian Qian;Qi Zhang;Yaqian Zhou;Xuanjing Huang;Lide Wu
Affiliations:
Fudan University, Shanghai, P.R. China;Fudan University, Shanghai, P.R. China;Fudan University, Shanghai, P.R. China;Fudan University, Shanghai, P.R. China;Fudan University, Shanghai, P.R. China
Venue:
EMNLP '10 Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing
Year:
2010

Citing 8
Cited 1

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

ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
Text chunking based on a generalization of winnow

The Journal of Machine Learning Research
Dynamic conditional random fields: factorized probabilistic models for labeling and segmenting sequence data

ICML '04 Proceedings of the twenty-first international conference on Machine learning
Chunking with support vector machines

NAACL '01 Proceedings of the second meeting of the North American Chapter of the Association for Computational Linguistics on Language technologies
A high-performance semi-supervised learning method for text chunking

ACL '05 Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics
Learning with probabilistic features for improved pipeline models

EMNLP '08 Proceedings of the Conference on Empirical Methods in Natural Language Processing
A dual-layer CRFs based joint decoding method for cascaded segmentation and labeling tasks

IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
A general and multi-lingual phrase chunking model based on masking method

CICLing'06 Proceedings of the 7th international conference on Computational Linguistics and Intelligent Text Processing

Joint Chinese word segmentation, POS tagging and parsing

EMNLP-CoNLL '12 Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning

Quantified Score

Hi-index	0.01

Visualization

Abstract

Many sequence labeling tasks in NLP require solving a cascade of segmentation and tagging subtasks, such as Chinese POS tagging, named entity recognition, and so on. Traditional pipeline approaches usually suffer from error propagation. Joint training/decoding in the cross-product state space could cause too many parameters and high inference complexity. In this paper, we present a novel method which integrates graph structures of two sub-tasks into one using virtual nodes, and performs joint training and decoding in the factorized state space. Experimental evaluations on CoNLL 2000 shallow parsing data set and Fourth SIGHAN Bakeoff CTB POS tagging data set demonstrate the superiority of our method over cross-product, pipeline and candidate reranking approaches.