Distant BI-Gram model, collocation, and their applications in post-processing for Chinese character recognition

Rui Feng Xu; Qin Lu; Daniel S. Yeung; Xi Zhao Wang

doi:10.1109/icmlc.2002.1175440

Distant BI-Gram model, collocation, and their applications in post-processing for Chinese character recognition

Rui Feng Xu
, Qin Lu
, Daniel S. Yeung^*
, Xi Zhao Wang

^*Corresponding author for this work

Hong Kong Polytechnic University
Hebei University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

In this paper, we present a Distant BI-Gram model, which extended the regular BI-Gram model by considering the distance information and weight parameters, in order to describe the long-distance restrictions among the Chinese sentence. The extraction of the statistical information and weight parameters of this language model is discussed. Based on this work, the word combination strength and spread are employed to extract the recurrent word combinations, i.e. collocations. The Distant BI-Gram Model and collocation are applied to a statistic-based post-processing system for improving the recognition performance of Chinese character. The experimental results show that by employ these two language models, the post-processing system achieves a higher improvement performance.

Original language	English
Title of host publication	2002 International Conference on Machine Learning and Cybernetics, ICMLC 2002
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	2251-2255
Number of pages	5
ISBN (Print)	0780375084, 9780780375086
DOIs	https://doi.org/10.1109/icmlc.2002.1175440
State	Published - 2002
Externally published	Yes
Event	2002 International Conference on Machine Learning and Cybernetics, ICMLC 2002 - Beijing, China Duration: 4 Nov 2002 → 5 Nov 2002

Publication series

Name	Proceedings of 2002 International Conference on Machine Learning and Cybernetics
Volume	4

Conference

Conference	2002 International Conference on Machine Learning and Cybernetics, ICMLC 2002
Country/Territory	China
City	Beijing
Period	4/11/02 → 5/11/02

Keywords

Character recognition
Collocation
Distant BI-Gram
Post-processing

Access to Document

10.1109/icmlc.2002.1175440

Cite this

Xu, R. F., Lu, Q., Yeung, D. S., & Wang, X. Z. (2002). Distant BI-Gram model, collocation, and their applications in post-processing for Chinese character recognition. In 2002 International Conference on Machine Learning and Cybernetics, ICMLC 2002 (pp. 2251-2255). (Proceedings of 2002 International Conference on Machine Learning and Cybernetics; Vol. 4). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/icmlc.2002.1175440

Xu, Rui Feng ; Lu, Qin ; Yeung, Daniel S. et al. / Distant BI-Gram model, collocation, and their applications in post-processing for Chinese character recognition. 2002 International Conference on Machine Learning and Cybernetics, ICMLC 2002. Institute of Electrical and Electronics Engineers Inc., 2002. pp. 2251-2255 (Proceedings of 2002 International Conference on Machine Learning and Cybernetics).

@inproceedings{4df25dfe9f5c46c9b49467060e9936ac,

title = "Distant BI-Gram model, collocation, and their applications in post-processing for Chinese character recognition",

abstract = "In this paper, we present a Distant BI-Gram model, which extended the regular BI-Gram model by considering the distance information and weight parameters, in order to describe the long-distance restrictions among the Chinese sentence. The extraction of the statistical information and weight parameters of this language model is discussed. Based on this work, the word combination strength and spread are employed to extract the recurrent word combinations, i.e. collocations. The Distant BI-Gram Model and collocation are applied to a statistic-based post-processing system for improving the recognition performance of Chinese character. The experimental results show that by employ these two language models, the post-processing system achieves a higher improvement performance.",

keywords = "Character recognition, Collocation, Distant BI-Gram, Post-processing",

author = "Xu, \{Rui Feng\} and Qin Lu and Yeung, \{Daniel S.\} and Wang, \{Xi Zhao\}",

year = "2002",

doi = "10.1109/icmlc.2002.1175440",

language = "英语",

isbn = "0780375084",

series = "Proceedings of 2002 International Conference on Machine Learning and Cybernetics",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "2251--2255",

booktitle = "2002 International Conference on Machine Learning and Cybernetics, ICMLC 2002",

address = "美国",

note = "2002 International Conference on Machine Learning and Cybernetics, ICMLC 2002 ; Conference date: 04-11-2002 Through 05-11-2002",

}

Xu, RF, Lu, Q, Yeung, DS & Wang, XZ 2002, Distant BI-Gram model, collocation, and their applications in post-processing for Chinese character recognition. in 2002 International Conference on Machine Learning and Cybernetics, ICMLC 2002. Proceedings of 2002 International Conference on Machine Learning and Cybernetics, vol. 4, Institute of Electrical and Electronics Engineers Inc., pp. 2251-2255, 2002 International Conference on Machine Learning and Cybernetics, ICMLC 2002, Beijing, China, 4/11/02. https://doi.org/10.1109/icmlc.2002.1175440

Distant BI-Gram model, collocation, and their applications in post-processing for Chinese character recognition. / Xu, Rui Feng; Lu, Qin; Yeung, Daniel S. et al.
2002 International Conference on Machine Learning and Cybernetics, ICMLC 2002. Institute of Electrical and Electronics Engineers Inc., 2002. p. 2251-2255 (Proceedings of 2002 International Conference on Machine Learning and Cybernetics; Vol. 4).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Distant BI-Gram model, collocation, and their applications in post-processing for Chinese character recognition

AU - Xu, Rui Feng

AU - Lu, Qin

AU - Yeung, Daniel S.

AU - Wang, Xi Zhao

PY - 2002

Y1 - 2002

N2 - In this paper, we present a Distant BI-Gram model, which extended the regular BI-Gram model by considering the distance information and weight parameters, in order to describe the long-distance restrictions among the Chinese sentence. The extraction of the statistical information and weight parameters of this language model is discussed. Based on this work, the word combination strength and spread are employed to extract the recurrent word combinations, i.e. collocations. The Distant BI-Gram Model and collocation are applied to a statistic-based post-processing system for improving the recognition performance of Chinese character. The experimental results show that by employ these two language models, the post-processing system achieves a higher improvement performance.

AB - In this paper, we present a Distant BI-Gram model, which extended the regular BI-Gram model by considering the distance information and weight parameters, in order to describe the long-distance restrictions among the Chinese sentence. The extraction of the statistical information and weight parameters of this language model is discussed. Based on this work, the word combination strength and spread are employed to extract the recurrent word combinations, i.e. collocations. The Distant BI-Gram Model and collocation are applied to a statistic-based post-processing system for improving the recognition performance of Chinese character. The experimental results show that by employ these two language models, the post-processing system achieves a higher improvement performance.

KW - Character recognition

KW - Collocation

KW - Distant BI-Gram

KW - Post-processing

UR - https://www.scopus.com/pages/publications/0036925882

U2 - 10.1109/icmlc.2002.1175440

DO - 10.1109/icmlc.2002.1175440

M3 - 会议稿件

AN - SCOPUS:0036925882

SN - 0780375084

SN - 9780780375086

T3 - Proceedings of 2002 International Conference on Machine Learning and Cybernetics

SP - 2251

EP - 2255

BT - 2002 International Conference on Machine Learning and Cybernetics, ICMLC 2002

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2002 International Conference on Machine Learning and Cybernetics, ICMLC 2002

Y2 - 4 November 2002 through 5 November 2002

ER -

Xu RF, Lu Q, Yeung DS, Wang XZ. Distant BI-Gram model, collocation, and their applications in post-processing for Chinese character recognition. In 2002 International Conference on Machine Learning and Cybernetics, ICMLC 2002. Institute of Electrical and Electronics Engineers Inc. 2002. p. 2251-2255. (Proceedings of 2002 International Conference on Machine Learning and Cybernetics). doi: 10.1109/icmlc.2002.1175440

Distant BI-Gram model, collocation, and their applications in post-processing for Chinese character recognition

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this