Multi-paraphrase Augmentation to Leverage Neural Caption Translation
Johanes Effendi, Sakriani Sakti, Katsuhito Sudoh, Satoshi Nakamura
Abstract
Paraphrasing has been proven to improve translation quality in machine translation (MT) and has been widely studied alongside with the development of statistical MT (SMT). In this paper, we investigate and utilize neural paraphrasing to improve translation quality in neural MT (NMT), which has not yet been much explored. Our first contribution is to propose a new way of creating a multi-paraphrase corpus through visual description. After that, we also proposed to construct neural paraphrase models which initiate expert models and utilize them to leverage NMT. Here, we diffuse the image information by using image-based paraphrasing without using the image itself. Our proposed image-based multi-paraphrase augmentation strategies showed improvement against a vanilla NMT baseline.- Anthology ID:
- 2018.iwslt-1.27
- Volume:
- Proceedings of the 15th International Conference on Spoken Language Translation
- Month:
- October 29-30
- Year:
- 2018
- Address:
- Brussels
- Editors:
- Marco Turchi, Jan Niehues, Marcello Frederico
- Venue:
- IWSLT
- SIG:
- SIGSLT
- Publisher:
- International Conference on Spoken Language Translation
- Note:
- Pages:
- 181–188
- Language:
- URL:
- https://aclanthology.org/2018.iwslt-1.27
- DOI:
- Cite (ACL):
- Johanes Effendi, Sakriani Sakti, Katsuhito Sudoh, and Satoshi Nakamura. 2018. Multi-paraphrase Augmentation to Leverage Neural Caption Translation. In Proceedings of the 15th International Conference on Spoken Language Translation, pages 181–188, Brussels. International Conference on Spoken Language Translation.
- Cite (Informal):
- Multi-paraphrase Augmentation to Leverage Neural Caption Translation (Effendi et al., IWSLT 2018)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/2018.iwslt-1.27.pdf
- Data
- MS COCO