@inproceedings{fukushima-etal-2025-reversible,
    title = "Reversible Disentanglement of Meaning and Language Representations from Multilingual Sentence Encoders",
    author = "Fukushima, Keita  and
      Kajiwara, Tomoyuki  and
      Ninomiya, Takashi",
    editor = "Adelani, David Ifeoluwa  and
      Arnett, Catherine  and
      Ataman, Duygu  and
      Chang, Tyler A.  and
      Gonen, Hila  and
      Raja, Rahul  and
      Schmidt, Fabian  and
      Stap, David  and
      Wang, Jiayi",
    booktitle = "Proceedings of the 5th Workshop on Multilingual Representation Learning (MRL 2025)",
    month = nov,
    year = "2025",
    address = "Suzhuo, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.mrl-main.18/",
    doi = "10.18653/v1/2025.mrl-main.18",
    pages = "265--270",
    ISBN = "979-8-89176-345-6",
    abstract = "We propose an unsupervised method to disentangle sentence embeddings from multilingual sentence encoders into language-specific and language-agnostic representations. Such language-agnostic representations distilled by our method can estimate cross-lingual semantic sentence similarity by cosine similarity. Previous studies have trained individual extractors to distill each language-specific and -agnostic representation. This approach suffers from missing information resulting in the original sentence embedding not being fully reconstructed from both language-specific and -agnostic representations; this leads to performance degradation in estimating cross-lingual sentence similarity. We only train the extractor for language-agnostic representations and treat language-specific representations as differences from the original sentence embedding; in this way, there is no missing information. Experimental results for both tasks, quality estimation of machine translation and cross-lingual sentence similarity estimation, show that our proposed method outperforms existing unsupervised methods."
}