Comparing MT approaches for text normalization
- Author
- Claudia Matos Veliz, Orphée De Clercq (UGent) and Veronique Hoste (UGent)
- Organization
- Abstract
- One of the main characteristics of social media data is the use of non-standard language. Since NLP tools have been trained on traditional text material their performance drops when applied to social media data. One way to overcome this is to first perform text normalization. In this work, we apply text normalization to noisy English and Dutch text coming from different social media genres: text messages, message board posts and tweets. We consider the normalization task as a Machine Translation problem and test the two leading paradigms: statistical and neural machine translation. For SMT we explore the added value of varying background corpora for training the language model. For NMT we have a look at data augmentation since the parallel datasets we are working with are limited in size. Our results reveal that when relying on SMT to perform the normalization it is beneficial to use a background corpus that is close to the genre you are normalizing. Regarding NMT, we find that the translations - or normalizations - coming out of this model are far from perfect and that for a low-resource language like Dutch adding additional training data works better than artificially augmenting the data.
- Keywords
- LT3
Downloads
-
publisher version.pdf
- full text (Published version)
- |
- open access
- |
- |
- 507.57 KB
Citation
Please use this url to cite or link to this publication: http://hdl.handle.net/1854/LU-8629116
- MLA
- Matos Veliz, Claudia, et al. “Comparing MT Approaches for Text Normalization.” Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019), edited by Galia Angelova et al., INCOMA Ltd., 2019, pp. 740–49, doi:10.26615/978-954-452-056-4_086.
- APA
- Matos Veliz, C., De Clercq, O., & Hoste, V. (2019). Comparing MT approaches for text normalization. In G. Angelova, R. Mitkov, I. Nikolova, & I. Temnikova (Eds.), Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019) (pp. 740–749). https://doi.org/10.26615/978-954-452-056-4_086
- Chicago author-date
- Matos Veliz, Claudia, Orphée De Clercq, and Veronique Hoste. 2019. “Comparing MT Approaches for Text Normalization.” In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019), edited by Galia Angelova, Ruslan Mitkov, Ivelina Nikolova, and Irina Temnikova, 740–49. INCOMA Ltd. https://doi.org/10.26615/978-954-452-056-4_086.
- Chicago author-date (all authors)
- Matos Veliz, Claudia, Orphée De Clercq, and Veronique Hoste. 2019. “Comparing MT Approaches for Text Normalization.” In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019), ed by. Galia Angelova, Ruslan Mitkov, Ivelina Nikolova, and Irina Temnikova, 740–749. INCOMA Ltd. doi:10.26615/978-954-452-056-4_086.
- Vancouver
- 1.Matos Veliz C, De Clercq O, Hoste V. Comparing MT approaches for text normalization. In: Angelova G, Mitkov R, Nikolova I, Temnikova I, editors. Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019). INCOMA Ltd.; 2019. p. 740–9.
- IEEE
- [1]C. Matos Veliz, O. De Clercq, and V. Hoste, “Comparing MT approaches for text normalization,” in Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019), Varna, Bulgaria, 2019, pp. 740–749.
@inproceedings{8629116,
abstract = {{One of the main characteristics of social media data is the use of non-standard language. Since NLP tools have been trained on traditional text material their performance drops when applied to social media data. One way to overcome this is to first perform text normalization. In this work, we apply text normalization to noisy English and Dutch text coming from different social media genres: text messages, message board posts and tweets. We consider the normalization task as a Machine Translation problem and test the two leading paradigms: statistical and neural machine translation. For SMT we explore the added value of varying background corpora for training the language model. For NMT we have a look at data augmentation since the parallel datasets we are working with are limited in size. Our results reveal that when relying on SMT to perform the normalization it is beneficial to use a background corpus that is close to the genre you are normalizing. Regarding NMT, we find that the translations - or normalizations - coming out of this model are far from perfect and that for a low-resource language like Dutch adding additional training data works better than artificially augmenting the data.}},
author = {{Matos Veliz, Claudia and De Clercq, Orphée and Hoste, Veronique}},
booktitle = {{Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019)}},
editor = {{Angelova, Galia and Mitkov, Ruslan and Nikolova, Ivelina and Temnikova, Irina}},
isbn = {{9789544520557}},
issn = {{1313-8502}},
keywords = {{LT3}},
language = {{eng}},
location = {{Varna, Bulgaria}},
pages = {{740--749}},
publisher = {{INCOMA Ltd.}},
title = {{Comparing MT approaches for text normalization}},
url = {{http://doi.org/10.26615/978-954-452-056-4_086}},
year = {{2019}},
}
- Altmetric
- View in Altmetric