NDLI: Integrating Generative and Discriminative Character-Based Models for Chinese Word Segmentation

Please wait, while we are loading the content...

Integrating Generative and Discriminative Character-Based Models for Chinese Word Segmentation

Content Provider	ACM Digital Library
Author	Zong, Chengqing Su, Keh-Yih Wang, Kun
Copyright Year	2012
Abstract	Among statistical approaches to Chinese word segmentation, the word-based n-gram $(\textit{generative})$ model and the character-based tagging $(\textit{discriminative})$ model are two dominant approaches in the literature. The former gives excellent performance for the $\textit{in-vocabulary}$ (IV) words; however, it handles $\textit{out-of-vocabulary}$ (OOV) words poorly. On the other hand, though the latter is more robust for OOV words, it fails to deliver satisfactory performance for IV words. These two approaches behave differently due to the unit they use (word vs. character) and the model form they adopt (generative vs. discriminative). In general, character-based approaches are more robust than word-based ones, as the vocabulary of characters is a closed set; and discriminative models are more robust than generative ones, since they can flexibly include all kinds of available information, such as future context. This article first proposes a character-based $\textit{n}-gram$ model to enhance the robustness of the generative approach. Then the proposed generative model is further integrated with the character-based discriminative model to take advantage of both approaches. Our experiments show that this integrated approach outperforms all the existing approaches reported in the literature. Afterwards, a complete and detailed error analysis is conducted. Since a significant portion of the critical errors is related to numerical/foreign strings, character-type information is then incorporated into the model to further improve its performance. Last, the proposed integrated approach is tested on cross-domain corpora, and a semi-supervised domain adaptation algorithm is proposed and shown to be effective in our experiments.
Starting Page	1
Ending Page	41
Page Count	41
File Format	PDF
ISSN	15300226
e-ISSN	15583430
DOI	10.1145/2184436.2184440
Volume Number	11
Issue Number	2
Journal	ACM Transactions on Asian Language Information Processing (TALIP)
Language	English
Publisher	Association for Computing Machinery (ACM)
Publisher Date	2012-06-01
Publisher Place	New York
Access Restriction	One Nation One Subscription (ONOS)
Subject Keyword	Chinese word segmentation Character-based approach Discriminative model Domain adaptation Generative model Model integration
Content Type	Text
Resource Type	Article
Subject	Computer Science

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in

A character-based joint model for chinese word segmentation.

7Integrating Generative and Discriminative Character-Based Models for Chinese Word Segmentation

Which is More Suitable for Chinese Word Segmentation, the Generative Model or the Discriminative One? F∗

Which is more suitable for chinese word segmentation, the generative model or the discriminative one? f∗.

Integrating Surface and Abstract Features for Robust Cross-Domain Chinese Word Segmentation

A Unified Model for Solving the OOV Problem of Chinese Word Segmentation

Toward a unified approach to statistical language modeling for Chinese

A CharacterBased Joint Model for CIPSSIGHAN Word Segmentation Bakeoff 2010 (2013)

Word Segmenter for Chinese Micro-blogging Text Segmentation Report for CIPS-SIGHAN’2014 Bakeoff

Integrating Generative and Discriminative Character-Based Models for Chinese Word Segmentation

Similar Documents

A character-based joint model for chinese word segmentation.

7Integrating Generative and Discriminative Character-Based Models for Chinese Word Segmentation

Which is More Suitable for Chinese Word Segmentation, the Generative Model or the Discriminative One? F∗

Which is more suitable for chinese word segmentation, the generative model or the discriminative one? f∗.

Integrating Surface and Abstract Features for Robust Cross-Domain Chinese Word Segmentation

A Unified Model for Solving the OOV Problem of Chinese Word Segmentation

Toward a unified approach to statistical language modeling for Chinese

A CharacterBased Joint Model for CIPSSIGHAN Word Segmentation Bakeoff 2010 (2013)

Word Segmenter for Chinese Micro-blogging Text Segmentation Report for CIPS-SIGHAN’2014 Bakeoff

Integrating Generative and Discriminative Character-Based Models for Chinese Word Segmentation