CoNLL 2014 shared task: Grammatical error correction with a syntactic N-gram language model from a big corpora

S. David Hernandez; Hiram Calvo

CoNLL 2014 shared task: Grammatical error correction with a syntactic N-gram language model from a big corpora

S. David Hernandez, Hiram Calvo

Centro de Investigación en Computación (CIC)

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

10 Scopus citations

Abstract

We describe our approach to grammatical error correction presented in the CoNLL Shared Task 2014. Our work is focused on error detection in sentences with a language model based on syntactic tri-grams and bi-grams extracted from dependency trees generated from 90% of the English Wikipedia. Also, we add a naïve module to error correction that outputs a set of possible answers, those sentences are scored using a syntactic n-gram language model. The sentence with the best score is the final suggestion of the system. The system was ranked 11th, evidently this is a very simple approach, but since the beginning our main goal was to test the syntactic n-gram language model with a big corpus to future comparison.

Original language	English
Title of host publication	CoNLL 2014 - 18th Conference on Computational Natural Language Learning, Proceedings of the Shared Task
Publisher	Association for Computational Linguistics (ACL)
Pages	53-59
Number of pages	7
ISBN (Electronic)	9781941643198
State	Published - 2014
Event	18th Conference on Computational Natural Language Learning: Shared Task, CoNLL 2014 - Baltimore, United States Duration: 26 Jun 2014 → 27 Jun 2014

Publication series

Name	CoNLL 2014 - 18th Conference on Computational Natural Language Learning, Proceedings of the Shared Task

Conference

Conference	18th Conference on Computational Natural Language Learning: Shared Task, CoNLL 2014
Country/Territory	United States
City	Baltimore
Period	26/06/14 → 27/06/14

Cite this

David Hernandez, S., & Calvo, H. (2014). CoNLL 2014 shared task: Grammatical error correction with a syntactic N-gram language model from a big corpora. In CoNLL 2014 - 18th Conference on Computational Natural Language Learning, Proceedings of the Shared Task (pp. 53-59). (CoNLL 2014 - 18th Conference on Computational Natural Language Learning, Proceedings of the Shared Task). Association for Computational Linguistics (ACL).

David Hernandez, S. ; Calvo, Hiram. / CoNLL 2014 shared task : Grammatical error correction with a syntactic N-gram language model from a big corpora. CoNLL 2014 - 18th Conference on Computational Natural Language Learning, Proceedings of the Shared Task. Association for Computational Linguistics (ACL), 2014. pp. 53-59 (CoNLL 2014 - 18th Conference on Computational Natural Language Learning, Proceedings of the Shared Task).

@inproceedings{97cbc611d72d4ef6964e63a7e1657b9d,

title = "CoNLL 2014 shared task: Grammatical error correction with a syntactic N-gram language model from a big corpora",

abstract = "We describe our approach to grammatical error correction presented in the CoNLL Shared Task 2014. Our work is focused on error detection in sentences with a language model based on syntactic tri-grams and bi-grams extracted from dependency trees generated from 90% of the English Wikipedia. Also, we add a na{\"i}ve module to error correction that outputs a set of possible answers, those sentences are scored using a syntactic n-gram language model. The sentence with the best score is the final suggestion of the system. The system was ranked 11th, evidently this is a very simple approach, but since the beginning our main goal was to test the syntactic n-gram language model with a big corpus to future comparison.",

author = "{David Hernandez}, S. and Hiram Calvo",

note = "Publisher Copyright: {\textcopyright} 2014 Association for Computational Linguistics.; 18th Conference on Computational Natural Language Learning: Shared Task, CoNLL 2014 ; Conference date: 26-06-2014 Through 27-06-2014",

year = "2014",

language = "Ingl{\'e}s",

series = "CoNLL 2014 - 18th Conference on Computational Natural Language Learning, Proceedings of the Shared Task",

publisher = "Association for Computational Linguistics (ACL)",

pages = "53--59",

booktitle = "CoNLL 2014 - 18th Conference on Computational Natural Language Learning, Proceedings of the Shared Task",

}

David Hernandez, S & Calvo, H 2014, CoNLL 2014 shared task: Grammatical error correction with a syntactic N-gram language model from a big corpora. in CoNLL 2014 - 18th Conference on Computational Natural Language Learning, Proceedings of the Shared Task. CoNLL 2014 - 18th Conference on Computational Natural Language Learning, Proceedings of the Shared Task, Association for Computational Linguistics (ACL), pp. 53-59, 18th Conference on Computational Natural Language Learning: Shared Task, CoNLL 2014, Baltimore, United States, 26/06/14.

CoNLL 2014 shared task: Grammatical error correction with a syntactic N-gram language model from a big corpora. / David Hernandez, S.; Calvo, Hiram.
CoNLL 2014 - 18th Conference on Computational Natural Language Learning, Proceedings of the Shared Task. Association for Computational Linguistics (ACL), 2014. p. 53-59 (CoNLL 2014 - 18th Conference on Computational Natural Language Learning, Proceedings of the Shared Task).

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

TY - GEN

T1 - CoNLL 2014 shared task

T2 - 18th Conference on Computational Natural Language Learning: Shared Task, CoNLL 2014

AU - David Hernandez, S.

AU - Calvo, Hiram

PY - 2014

Y1 - 2014

N2 - We describe our approach to grammatical error correction presented in the CoNLL Shared Task 2014. Our work is focused on error detection in sentences with a language model based on syntactic tri-grams and bi-grams extracted from dependency trees generated from 90% of the English Wikipedia. Also, we add a naïve module to error correction that outputs a set of possible answers, those sentences are scored using a syntactic n-gram language model. The sentence with the best score is the final suggestion of the system. The system was ranked 11th, evidently this is a very simple approach, but since the beginning our main goal was to test the syntactic n-gram language model with a big corpus to future comparison.

AB - We describe our approach to grammatical error correction presented in the CoNLL Shared Task 2014. Our work is focused on error detection in sentences with a language model based on syntactic tri-grams and bi-grams extracted from dependency trees generated from 90% of the English Wikipedia. Also, we add a naïve module to error correction that outputs a set of possible answers, those sentences are scored using a syntactic n-gram language model. The sentence with the best score is the final suggestion of the system. The system was ranked 11th, evidently this is a very simple approach, but since the beginning our main goal was to test the syntactic n-gram language model with a big corpus to future comparison.

UR - http://www.scopus.com/inward/record.url?scp=84976434238&partnerID=8YFLogxK

M3 - Contribución a la conferencia

AN - SCOPUS:84976434238

T3 - CoNLL 2014 - 18th Conference on Computational Natural Language Learning, Proceedings of the Shared Task

SP - 53

EP - 59

BT - CoNLL 2014 - 18th Conference on Computational Natural Language Learning, Proceedings of the Shared Task

PB - Association for Computational Linguistics (ACL)

Y2 - 26 June 2014 through 27 June 2014

ER -

David Hernandez S, Calvo H. CoNLL 2014 shared task: Grammatical error correction with a syntactic N-gram language model from a big corpora. In CoNLL 2014 - 18th Conference on Computational Natural Language Learning, Proceedings of the Shared Task. Association for Computational Linguistics (ACL). 2014. p. 53-59. (CoNLL 2014 - 18th Conference on Computational Natural Language Learning, Proceedings of the Shared Task).

CoNLL 2014 shared task: Grammatical error correction with a syntactic N-gram language model from a big corpora

Abstract

Publication series

Conference

Other files and links

Fingerprint

Cite this