Word order correction for language transfer using relative position language modeling

Chao Hong Liu, Chung-Hsien Wu, Matthew Harris

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

Sentence correction has been an important and emerging issue in computer-assisted language learning. However, existing techniques based on grammar rules or statistical machine translation are still not robust enough to tackle the common incorrect word order errors in sentences produced by second language learners of Chinese. In this paper, a novel relative position language model is proposed to address this problem, for which a corpus of erroneous English-Chinese language transfer sentences along with their corrected counterparts is created and manually judged by human annotators. Experimental results show that compared to a scoring approach based on an n-gram language model and a phrase-based machine translation system, the performance in terms of BLEU scores of the proposed approach achieved improvements of 20.3% and 26.5% for the correction of word order errors resulting from language transfer, respectively.

Original languageEnglish
Title of host publicationProceedings - 2008 6th International Symposium on Chinese Spoken Language Processing, ISCSLP 2008
Pages33-36
Number of pages4
DOIs
Publication statusPublished - 2008 Dec 1
Event2008 6th International Symposium on Chinese Spoken Language Processing, ISCSLP 2008 - Kunming, China
Duration: 2008 Dec 162008 Dec 19

Publication series

NameProceedings - 2008 6th International Symposium on Chinese Spoken Language Processing, ISCSLP 2008

Other

Other2008 6th International Symposium on Chinese Spoken Language Processing, ISCSLP 2008
CountryChina
CityKunming
Period08-12-1608-12-19

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Information Systems
  • Software

Cite this

Liu, C. H., Wu, C-H., & Harris, M. (2008). Word order correction for language transfer using relative position language modeling. In Proceedings - 2008 6th International Symposium on Chinese Spoken Language Processing, ISCSLP 2008 (pp. 33-36). [4730274] (Proceedings - 2008 6th International Symposium on Chinese Spoken Language Processing, ISCSLP 2008). https://doi.org/10.1109/CHINSL.2008.ECP.20
Liu, Chao Hong ; Wu, Chung-Hsien ; Harris, Matthew. / Word order correction for language transfer using relative position language modeling. Proceedings - 2008 6th International Symposium on Chinese Spoken Language Processing, ISCSLP 2008. 2008. pp. 33-36 (Proceedings - 2008 6th International Symposium on Chinese Spoken Language Processing, ISCSLP 2008).
@inproceedings{e7fea8ec3e5142d98fd913df38fb2bb1,
title = "Word order correction for language transfer using relative position language modeling",
abstract = "Sentence correction has been an important and emerging issue in computer-assisted language learning. However, existing techniques based on grammar rules or statistical machine translation are still not robust enough to tackle the common incorrect word order errors in sentences produced by second language learners of Chinese. In this paper, a novel relative position language model is proposed to address this problem, for which a corpus of erroneous English-Chinese language transfer sentences along with their corrected counterparts is created and manually judged by human annotators. Experimental results show that compared to a scoring approach based on an n-gram language model and a phrase-based machine translation system, the performance in terms of BLEU scores of the proposed approach achieved improvements of 20.3{\%} and 26.5{\%} for the correction of word order errors resulting from language transfer, respectively.",
author = "Liu, {Chao Hong} and Chung-Hsien Wu and Matthew Harris",
year = "2008",
month = "12",
day = "1",
doi = "10.1109/CHINSL.2008.ECP.20",
language = "English",
isbn = "9781424429431",
series = "Proceedings - 2008 6th International Symposium on Chinese Spoken Language Processing, ISCSLP 2008",
pages = "33--36",
booktitle = "Proceedings - 2008 6th International Symposium on Chinese Spoken Language Processing, ISCSLP 2008",

}

Liu, CH, Wu, C-H & Harris, M 2008, Word order correction for language transfer using relative position language modeling. in Proceedings - 2008 6th International Symposium on Chinese Spoken Language Processing, ISCSLP 2008., 4730274, Proceedings - 2008 6th International Symposium on Chinese Spoken Language Processing, ISCSLP 2008, pp. 33-36, 2008 6th International Symposium on Chinese Spoken Language Processing, ISCSLP 2008, Kunming, China, 08-12-16. https://doi.org/10.1109/CHINSL.2008.ECP.20

Word order correction for language transfer using relative position language modeling. / Liu, Chao Hong; Wu, Chung-Hsien; Harris, Matthew.

Proceedings - 2008 6th International Symposium on Chinese Spoken Language Processing, ISCSLP 2008. 2008. p. 33-36 4730274 (Proceedings - 2008 6th International Symposium on Chinese Spoken Language Processing, ISCSLP 2008).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Word order correction for language transfer using relative position language modeling

AU - Liu, Chao Hong

AU - Wu, Chung-Hsien

AU - Harris, Matthew

PY - 2008/12/1

Y1 - 2008/12/1

N2 - Sentence correction has been an important and emerging issue in computer-assisted language learning. However, existing techniques based on grammar rules or statistical machine translation are still not robust enough to tackle the common incorrect word order errors in sentences produced by second language learners of Chinese. In this paper, a novel relative position language model is proposed to address this problem, for which a corpus of erroneous English-Chinese language transfer sentences along with their corrected counterparts is created and manually judged by human annotators. Experimental results show that compared to a scoring approach based on an n-gram language model and a phrase-based machine translation system, the performance in terms of BLEU scores of the proposed approach achieved improvements of 20.3% and 26.5% for the correction of word order errors resulting from language transfer, respectively.

AB - Sentence correction has been an important and emerging issue in computer-assisted language learning. However, existing techniques based on grammar rules or statistical machine translation are still not robust enough to tackle the common incorrect word order errors in sentences produced by second language learners of Chinese. In this paper, a novel relative position language model is proposed to address this problem, for which a corpus of erroneous English-Chinese language transfer sentences along with their corrected counterparts is created and manually judged by human annotators. Experimental results show that compared to a scoring approach based on an n-gram language model and a phrase-based machine translation system, the performance in terms of BLEU scores of the proposed approach achieved improvements of 20.3% and 26.5% for the correction of word order errors resulting from language transfer, respectively.

UR - http://www.scopus.com/inward/record.url?scp=60849095799&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=60849095799&partnerID=8YFLogxK

U2 - 10.1109/CHINSL.2008.ECP.20

DO - 10.1109/CHINSL.2008.ECP.20

M3 - Conference contribution

AN - SCOPUS:60849095799

SN - 9781424429431

T3 - Proceedings - 2008 6th International Symposium on Chinese Spoken Language Processing, ISCSLP 2008

SP - 33

EP - 36

BT - Proceedings - 2008 6th International Symposium on Chinese Spoken Language Processing, ISCSLP 2008

ER -

Liu CH, Wu C-H, Harris M. Word order correction for language transfer using relative position language modeling. In Proceedings - 2008 6th International Symposium on Chinese Spoken Language Processing, ISCSLP 2008. 2008. p. 33-36. 4730274. (Proceedings - 2008 6th International Symposium on Chinese Spoken Language Processing, ISCSLP 2008). https://doi.org/10.1109/CHINSL.2008.ECP.20