TY - GEN
T1 - Generating diverse translations with sentence codes
AU - Shu, Raphael
AU - Nakayama, Hideki
AU - Cho, Kyunghyun
N1 - Funding Information:
The research results have been achieved by ”Research and Development of Deep Learning Technology for Advanced Multilingual Speech Translation”, the Commissioned Research of National Institute of Information and Communications Technology (NICT), JAPAN. This work was partially supported by JSPS KAKENHI Grant Number JP16H05872, Samsung Advanced Institute of Technology (Next Generation Deep Learning: from pattern recognition to AI) and Samsung Electronics (Improving Deep Learning using Latent Structure).
Funding Information:
The research results have been achieved by”Research and Development of Deep Learning Technology for Advanced Multilingual Speech Translation”, the Commissioned Research of National Institute of Information and Communications Technology (NICT), JAPAN. This work was partially supported by JSPS KAKENHI Grant Number JP16H05872, Samsung Advanced Institute of Technology (Next Generation Deep Learning: from pattern recognition to AI) and Samsung Electronics (Improving Deep Learning using Latent Structure).
Publisher Copyright:
© 2019 Association for Computational Linguistics
PY - 2020
Y1 - 2020
N2 - Users of machine translation systems may desire to obtain multiple candidates translated in different ways. In this work, we attempt to obtain diverse translations by using sentence codes to condition the sentence generation. We describe two methods to extract the codes, either with or without the help of syntax information. For diverse generation, we sample multiple candidates, each of which conditioned on a unique code. Experiments show that the sampled translations have much higher diversity scores when using reasonable sentence codes, where the translation quality is still on par with the baselines even under strong constraint imposed by the codes. In qualitative analysis, we show that our method is able to generate paraphrase translations with drastically different structures. The proposed approach can be easily adopted to existing translation systems as no modification to the model is required.
AB - Users of machine translation systems may desire to obtain multiple candidates translated in different ways. In this work, we attempt to obtain diverse translations by using sentence codes to condition the sentence generation. We describe two methods to extract the codes, either with or without the help of syntax information. For diverse generation, we sample multiple candidates, each of which conditioned on a unique code. Experiments show that the sampled translations have much higher diversity scores when using reasonable sentence codes, where the translation quality is still on par with the baselines even under strong constraint imposed by the codes. In qualitative analysis, we show that our method is able to generate paraphrase translations with drastically different structures. The proposed approach can be easily adopted to existing translation systems as no modification to the model is required.
UR - http://www.scopus.com/inward/record.url?scp=85084081516&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85084081516&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85084081516
T3 - ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference
SP - 1823
EP - 1827
BT - ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference
PB - Association for Computational Linguistics (ACL)
T2 - 57th Annual Meeting of the Association for Computational Linguistics, ACL 2019
Y2 - 28 July 2019 through 2 August 2019
ER -