Word Segmentation by Separation Inference for East Asian Languages

UM > Faculty of Science and Technology > DEPARTMENT OF COMPUTER AND INFORMATION SCIENCE

Status	已發表Published
	Word Segmentation by Separation Inference for East Asian Languages
	Tong, Y. ; Guo, J. Z.; Zhou, J. Z.; Chen, G.; Zheng, G. K.
	2022-05-01
Source Publication	Findings of the Association for Computational Linguistics: ACL 2022
Pages	3924-3932
Abstract	Chinese Word Segmentation (CWS) intends to divide a raw sentence into words through sequence labeling. Thinking in reverse, CWS can also be viewed as a process of grouping a sequence of characters into a sequence of words. In such a way, CWS is reformed as a separation inference task in every adjacent character pair. Since every character is either connected or not connected to the others, the tagging schema is simplified as two tags “Connection” (C) or “NoConnection” (NC). Therefore, bigram is specially tailored for “C-NC” to model the separation state of every two consecutive characters. Our Separation Inference (SpIn) framework is evaluated on five public datasets, is demonstrated to work for machine learning and deep learning models, and outperforms state-of-the-art performance for CWS in all experiments. Performance boosts on Japanese Word Segmentation (JWS) and Korean Word Segmentation (KWS) further prove the framework is universal and effective for East Asian Languages.
Keyword	east Asian languages separation inference word segmentation
URL	View the original
Language	英語English
The Source to Article	PB_Publication
PUB ID	63310
Document Type	Conference paper
Collection	DEPARTMENT OF COMPUTER AND INFORMATION SCIENCE
Corresponding Author	Guo, J. Z.
Recommended Citation GB/T 7714	Tong, Y. ,Guo, J. Z.,Zhou, J. Z.,et al. Word Segmentation by Separation Inference for East Asian Languages[C], 2022, 3924-3932.
APA	Tong, Y. ., Guo, J. Z.., Zhou, J. Z.., Chen, G.., & Zheng, G. K. (2022). Word Segmentation by Separation Inference for East Asian Languages. Findings of the Association for Computational Linguistics: ACL 2022, 3924-3932.

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

If you have any objections to this item, please fill out the form below and the administrator will contact you as soon as possible.
Content:
Email：	*
Affiliation No.
Verification Code:	Refresh

Any comments and suggestions are welcomed.
Title:	*
Content:
Email：	*
Verification Code:	Refresh