Neural fuzzy repair : integrating fuzzy matches into neural machine translation
- Author
- Bram Bulté and Arda Tezcan (UGent)
- Organization
- Abstract
- We present a simple yet powerful data augmentation method for boosting Neural Machine Translation (NMT) performance by leveraging information retrieved from a Translation Memory (TM). We propose and test two methods for augmenting NMT training data with fuzzy TM matches. Tests on the DGT-TM data set for two language pairs show consistent and substantial improvements over a range of baseline systems. The results suggest that this method is promising for any translation environment in which a sizeable TM is available and a certain amount of repetition across translations is to be expected, especially considering its ease of implementation.
- Keywords
- neural machine translation, translation memory, lt3
Downloads
-
P19-1175.pdf
- full text
- |
- open access
- |
- |
- 305.27 KB
Citation
Please use this url to cite or link to this publication: http://hdl.handle.net/1854/LU-8624135
- MLA
- Bulté, Bram, and Arda Tezcan. “Neural Fuzzy Repair : Integrating Fuzzy Matches into Neural Machine Translation.” 57TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2019), 2019, pp. 1800–09, doi:10.18653/v1/P19-1175.
- APA
- Bulté, B., & Tezcan, A. (2019). Neural fuzzy repair : integrating fuzzy matches into neural machine translation. 57TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2019), 1800–1809. https://doi.org/10.18653/v1/P19-1175
- Chicago author-date
- Bulté, Bram, and Arda Tezcan. 2019. “Neural Fuzzy Repair : Integrating Fuzzy Matches into Neural Machine Translation.” In 57TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2019), 1800–1809. https://doi.org/10.18653/v1/P19-1175.
- Chicago author-date (all authors)
- Bulté, Bram, and Arda Tezcan. 2019. “Neural Fuzzy Repair : Integrating Fuzzy Matches into Neural Machine Translation.” In 57TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2019), 1800–1809. doi:10.18653/v1/P19-1175.
- Vancouver
- 1.Bulté B, Tezcan A. Neural fuzzy repair : integrating fuzzy matches into neural machine translation. In: 57TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2019). 2019. p. 1800–9.
- IEEE
- [1]B. Bulté and A. Tezcan, “Neural fuzzy repair : integrating fuzzy matches into neural machine translation,” in 57TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2019), Florence, Italy, 2019, pp. 1800–1809.
@inproceedings{8624135,
abstract = {{We present a simple yet powerful data augmentation method for boosting Neural Machine Translation (NMT) performance by leveraging information retrieved from a Translation Memory (TM). We propose and test two methods for augmenting NMT training data with fuzzy TM matches. Tests on the DGT-TM data set for two language pairs show consistent and substantial improvements over a range of baseline systems. The results suggest that this method is promising for any translation environment in which a sizeable TM is available and a certain amount of repetition across translations is to be expected, especially considering its ease of implementation.}},
author = {{Bulté, Bram and Tezcan, Arda}},
booktitle = {{57TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2019)}},
isbn = {{9781950737482}},
keywords = {{neural machine translation,translation memory,lt3}},
language = {{eng}},
location = {{Florence, Italy}},
pages = {{1800--1809}},
title = {{Neural fuzzy repair : integrating fuzzy matches into neural machine translation}},
url = {{http://doi.org/10.18653/v1/P19-1175}},
year = {{2019}},
}
- Altmetric
- View in Altmetric
- Web of Science
- Times cited: