A neural network architecture for detecting grammatical errors in statistical machine translation
- Author
- Arda Tezcan (UGent) , Veronique Hoste (UGent) and Lieve Macken (UGent)
- Organization
- Abstract
- In this paper we present a Neural Network (NN) architecture for detecting grammatical er- rors in Statistical Machine Translation (SMT) using monolingual morpho-syntactic word rep- resentations in combination with surface and syntactic context windows. We test our approach on two language pairs and two tasks, namely detecting grammatical errors and predicting over- all post-editing e ort. Our results show that this approach is not only able to accurately detect grammatical errors but it also performs well as a quality estimation system for predicting over- all post-editing e ort, which is characterised by all types of MT errors. Furthermore, we show that this approach is portable to other languages.
- Keywords
- machine translation, quality estimation, grammatical errors, recurrent neural networks, LT3
Downloads
-
Tezcan Hoste Macken.pdf
- full text
- |
- open access
- |
- |
- 792.73 KB
Citation
Please use this url to cite or link to this publication: http://hdl.handle.net/1854/LU-8522713
- MLA
- Tezcan, Arda, et al. “A Neural Network Architecture for Detecting Grammatical Errors in Statistical Machine Translation.” THE PRAGUE BULLETIN OF MATHEMATICAL LINGUISTICS, no. 108, 2017, pp. 133–45, doi:10.1515/pralin-2017-0015.
- APA
- Tezcan, A., Hoste, V., & Macken, L. (2017). A neural network architecture for detecting grammatical errors in statistical machine translation. THE PRAGUE BULLETIN OF MATHEMATICAL LINGUISTICS, (108), 133–145. https://doi.org/10.1515/pralin-2017-0015
- Chicago author-date
- Tezcan, Arda, Veronique Hoste, and Lieve Macken. 2017. “A Neural Network Architecture for Detecting Grammatical Errors in Statistical Machine Translation.” THE PRAGUE BULLETIN OF MATHEMATICAL LINGUISTICS, no. 108: 133–45. https://doi.org/10.1515/pralin-2017-0015.
- Chicago author-date (all authors)
- Tezcan, Arda, Veronique Hoste, and Lieve Macken. 2017. “A Neural Network Architecture for Detecting Grammatical Errors in Statistical Machine Translation.” THE PRAGUE BULLETIN OF MATHEMATICAL LINGUISTICS (108): 133–145. doi:10.1515/pralin-2017-0015.
- Vancouver
- 1.Tezcan A, Hoste V, Macken L. A neural network architecture for detecting grammatical errors in statistical machine translation. THE PRAGUE BULLETIN OF MATHEMATICAL LINGUISTICS. 2017;(108):133–45.
- IEEE
- [1]A. Tezcan, V. Hoste, and L. Macken, “A neural network architecture for detecting grammatical errors in statistical machine translation,” THE PRAGUE BULLETIN OF MATHEMATICAL LINGUISTICS, no. 108, pp. 133–145, 2017.
@article{8522713,
abstract = {{In this paper we present a Neural Network (NN) architecture for detecting grammatical er- rors in Statistical Machine Translation (SMT) using monolingual morpho-syntactic word rep- resentations in combination with surface and syntactic context windows. We test our approach on two language pairs and two tasks, namely detecting grammatical errors and predicting over- all post-editing e ort. Our results show that this approach is not only able to accurately detect grammatical errors but it also performs well as a quality estimation system for predicting over- all post-editing e ort, which is characterised by all types of MT errors. Furthermore, we show that this approach is portable to other languages.}},
author = {{Tezcan, Arda and Hoste, Veronique and Macken, Lieve}},
issn = {{0032-6585}},
journal = {{THE PRAGUE BULLETIN OF MATHEMATICAL LINGUISTICS}},
keywords = {{machine translation,quality estimation,grammatical errors,recurrent neural networks,LT3}},
language = {{eng}},
location = {{Prague}},
number = {{108}},
pages = {{133--145}},
title = {{A neural network architecture for detecting grammatical errors in statistical machine translation}},
url = {{http://doi.org/10.1515/pralin-2017-0015}},
year = {{2017}},
}
- Altmetric
- View in Altmetric