Controlling the Voice of a Sentence in Japanese-to-English Neural Machine Translation
Hayahide Yamagishi, Shin Kanouchi, Takayuki Sato, Mamoru Komachi
Abstract
In machine translation, we must consider the difference in expression between languages. For example, the active/passive voice may change in Japanese-English translation. The same verb in Japanese may be translated into different voices at each translation because the voice of a generated sentence cannot be determined using only the information of the Japanese sentence. Machine translation systems should consider the information structure to improve the coherence of the output by using several topicalization techniques such as passivization. Therefore, this paper reports on our attempt to control the voice of the sentence generated by an encoder-decoder model. To control the voice of the generated sentence, we added the voice information of the target sentence to the source sentence during the training. We then generated sentences with a specified voice by appending the voice information to the source sentence. We observed experimentally whether the voice could be controlled. The results showed that, we could control the voice of the generated sentence with 85.0% accuracy on average. In the evaluation of Japanese-English translation, we obtained a 0.73-point improvement in BLEU score by using gold voice labels.- Anthology ID:
- W16-4620
- Volume:
- Proceedings of the 3rd Workshop on Asian Translation (WAT2016)
- Month:
- December
- Year:
- 2016
- Address:
- Osaka, Japan
- Editors:
- Toshiaki Nakazawa, Hideya Mino, Chenchen Ding, Isao Goto, Graham Neubig, Sadao Kurohashi, Ir. Hammam Riza, Pushpak Bhattacharyya
- Venue:
- WAT
- SIG:
- Publisher:
- The COLING 2016 Organizing Committee
- Note:
- Pages:
- 203–210
- Language:
- URL:
- https://aclanthology.org/W16-4620
- DOI:
- Cite (ACL):
- Hayahide Yamagishi, Shin Kanouchi, Takayuki Sato, and Mamoru Komachi. 2016. Controlling the Voice of a Sentence in Japanese-to-English Neural Machine Translation. In Proceedings of the 3rd Workshop on Asian Translation (WAT2016), pages 203–210, Osaka, Japan. The COLING 2016 Organizing Committee.
- Cite (Informal):
- Controlling the Voice of a Sentence in Japanese-to-English Neural Machine Translation (Yamagishi et al., WAT 2016)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/W16-4620.pdf
- Data
- ASPEC