Adversarial Training on Disentangling Meaning and Language Representations for Unsupervised Quality Estimation

Yuto Kuroda; Tomoyuki Kajiwara; Yuki Arase; Takashi Ninomiya

COLING 2022main2 citations

Adversarial Training on Disentangling Meaning and Language Representations for Unsupervised Quality Estimation

Yuto Kuroda, Tomoyuki Kajiwara, Yuki Arase, Takashi Ninomiya

Abstract

We propose a method to distill language-agnostic meaning embeddings from multilingual sentence encoders for unsupervised quality estimation of machine translation. Our method facilitates that the meaning embeddings focus on semantics by adversarial training that attempts to eliminate language-specific information. Experimental results on unsupervised quality estimation reveal that our method achieved higher correlations with human evaluations.

BibTeX

@inproceedings{kuroda-etal-2022-adversarial,
    title = "Adversarial Training on Disentangling Meaning and Language Representations for Unsupervised Quality Estimation",
    author = "Kuroda, Yuto  and
      Kajiwara, Tomoyuki  and
      Arase, Yuki  and
      Ninomiya, Takashi",
    editor = "Calzolari, Nicoletta  and
      Huang, Chu-Ren  and
      Kim, Hansaem  and
      Pustejovsky, James  and
      Wanner, Leo  and
      Choi, Key-Sun  and
      Ryu, Pum-Mo  and
      Chen, Hsin-Hsi  and
      Donatelli, Lucia  and
      Ji, Heng  and
      Kurohashi, Sadao  and
      Paggio, Patrizia  and
      Xue, Nianwen  and
      Kim, Seokhwan  and
      Hahm, Younggyun  and
      He, Zhong  and
      Lee, Tony Kyungil  and
      Santus, Enrico  and
      Bond, Francis  and
      Na, Seung-Hoon",
    booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
    month = oct,
    year = "2022",
    address = "Gyeongju, Republic of Korea",
    publisher = "International Committee on Computational Linguistics",
    url = "https://aclanthology.org/2022.coling-1.465/",
    pages = "5240--5245"
}