NCTU and NTUT's Entry to CLP-2014 Chinese Spelling Check Evaluation

Yih-Ru Wang; Yuan Fu Liao

NCTU and NTUT's Entry to CLP-2014 Chinese Spelling Check Evaluation

研究成果 › 同行評審

7 引文斯高帕斯（Scopus）

摘要

This paper describes our Chinese spelling check system submitted to SIGHAN Bake-off 2014 evaluation. The system's main components are still the conditional random field (CRF)-based word segmentation/part-ofspeech (POS) tagger and tri-gram language model (LM) used last year. But we tried to refine the misspelling rules, decision-making threshold and improve LM rescoring speed to reduce false alarm rate and improve rescoring speed. Bake-off 2014 evaluation results show that one of our system (Run2) did achieve reasonable performance with about 0.485/0.468 accuracies and 0.226/0.180 F1 scores in the detection/ correction metrics.

原文	English
頁面	216-219
頁數	4
出版狀態	Published - 2014
事件	3rd CIPS-SIGHAN Joint Conference on Chinese Language Processing, CLP 2014 - Wuhan, 中國持續時間: 20 10月 2014 → 21 10月 2014

Conference

Conference	3rd CIPS-SIGHAN Joint Conference on Chinese Language Processing, CLP 2014
國家/地區	中國
城市	Wuhan
期間	20/10/14 → 21/10/14

其它文件與鏈接

Link to publication in Scopus

引用此

@conference{076eb63593ff45cb98e59b5825dc6555,

title = "NCTU and NTUT's Entry to CLP-2014 Chinese Spelling Check Evaluation",

abstract = "This paper describes our Chinese spelling check system submitted to SIGHAN Bake-off 2014 evaluation. The system's main components are still the conditional random field (CRF)-based word segmentation/part-ofspeech (POS) tagger and tri-gram language model (LM) used last year. But we tried to refine the misspelling rules, decision-making threshold and improve LM rescoring speed to reduce false alarm rate and improve rescoring speed. Bake-off 2014 evaluation results show that one of our system (Run2) did achieve reasonable performance with about 0.485/0.468 accuracies and 0.226/0.180 F1 scores in the detection/ correction metrics.",

author = "Yih-Ru Wang and Liao, {Yuan Fu}",

note = "Publisher Copyright: {\textcopyright} 2014 CLP 2014 - 3rd CIPS-SIGHAN Joint Conference on Chinese Language Processing. All rights reserved.; 3rd CIPS-SIGHAN Joint Conference on Chinese Language Processing, CLP 2014 ; Conference date: 20-10-2014 Through 21-10-2014",

year = "2014",

language = "English",

pages = "216--219",

}

TY - CONF

T1 - NCTU and NTUT's Entry to CLP-2014 Chinese Spelling Check Evaluation

AU - Wang, Yih-Ru

AU - Liao, Yuan Fu

PY - 2014

Y1 - 2014

N2 - This paper describes our Chinese spelling check system submitted to SIGHAN Bake-off 2014 evaluation. The system's main components are still the conditional random field (CRF)-based word segmentation/part-ofspeech (POS) tagger and tri-gram language model (LM) used last year. But we tried to refine the misspelling rules, decision-making threshold and improve LM rescoring speed to reduce false alarm rate and improve rescoring speed. Bake-off 2014 evaluation results show that one of our system (Run2) did achieve reasonable performance with about 0.485/0.468 accuracies and 0.226/0.180 F1 scores in the detection/ correction metrics.

AB - This paper describes our Chinese spelling check system submitted to SIGHAN Bake-off 2014 evaluation. The system's main components are still the conditional random field (CRF)-based word segmentation/part-ofspeech (POS) tagger and tri-gram language model (LM) used last year. But we tried to refine the misspelling rules, decision-making threshold and improve LM rescoring speed to reduce false alarm rate and improve rescoring speed. Bake-off 2014 evaluation results show that one of our system (Run2) did achieve reasonable performance with about 0.485/0.468 accuracies and 0.226/0.180 F1 scores in the detection/ correction metrics.

UR - http://www.scopus.com/inward/record.url?scp=85017110694&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:85017110694

SP - 216

EP - 219

T2 - 3rd CIPS-SIGHAN Joint Conference on Chinese Language Processing, CLP 2014

Y2 - 20 October 2014 through 21 October 2014

ER -

NCTU and NTUT's Entry to CLP-2014 Chinese Spelling Check Evaluation

摘要

Conference

其它文件與鏈接

指紋

引用此