A General and Multi-lingual Phrase Chunking Model based on Masking Method

A General and Multi-lingual Phrase Chunking Model based on Masking Method (2006)

Cached

Download Links

[www.csie.ncu.edu.tw]

Other Repositories/Bibliography

DBLP

by Yu-chieh Wu , Chia-hui Chang , Yue-shi Lee

Venue:	In CICLING
Citations:	7 - 4 self

Versions

Version History

Metadata Version 3

Datum	Value	Source
TITLE	A General and Multi-lingual Phrase Chunking Model based on Masking Method	INFERENCE
AUTHOR NAME	Yu-chieh Wu	SVM HeaderParse 0.2
AUTHOR AFFIL	1 Department of Computer Science and Information Engineering, National Central University,	SVM HeaderParse 0.2
AUTHOR ADDR	No.300, Jhong-Da Rd., Jhongli City, Taoyuan County 32001, Taiwan, R.O.C.	SVM HeaderParse 0.2
AUTHOR NAME	Chia-hui Chang	SVM HeaderParse 0.2
AUTHOR AFFIL	1 Department of Computer Science and Information Engineering, National Central University,	SVM HeaderParse 0.2
AUTHOR ADDR	No.300, Jhong-Da Rd., Jhongli City, Taoyuan County 32001, Taiwan, R.O.C.	SVM HeaderParse 0.2
AUTHOR NAME	Yue-shi Lee	SVM HeaderParse 0.2
AUTHOR AFFIL	2 Department of Computer Science and Information Engineering, Ming Chuan University,	SVM HeaderParse 0.2
AUTHOR ADDR	No.5, De-Ming Rd, Gweishan District, Taoyuan 333, Taiwan, R.O.C.	SVM HeaderParse 0.2
ABSTRACT	Abstract. Several phrase chunkers have been proposed over the past few years. Some state-of-the-art chunkers achieved better performance via integrating external resources, e.g., parsers and additional training data, or combining multiple learners. However, in many languages and domains, such external materials are not easily available and the combination of multiple learners will increase the cost of training and testing. In this paper, we propose a mask method to improve the chunking accuracy. The experimental results show that our chunker achieves better performance in comparison with other deep parsers and chunkers. For CoNLL-2000 data set, our system achieves 94.12 in F rate. For the base-chunking task, our system reaches 92.95 in F rate. When porting to Chinese, the performance of the base-chunking task is 92.36 in F rate. Also, our chunker is quite efficient. The complete chunking time of a 50K words document is about 50 seconds. 1	SVM HeaderParse 0.2
YEAR	2006	INFERENCE
VENUE	In CICLING	INFERENCE
VENUE TYPE	CONFERENCE	INFERENCE
PAGES	144--155	INFERENCE
VOLUME	3878	INFERENCE
CITATIONS	20 found	ParsCit 1.0