@inproceedings{nonomura-etal-2026-mitigating,
    title = "Mitigating Language Bias in Multilingual Sentence Embeddings for Cross-Lingual Similarity Estimation",
    author = "Nonomura, Kanade  and
      Fukushima, Keita  and
      Kondo, Risa  and
      Kajiwara, Tomoyuki",
    editor = "Mohammad, Saif M.  and
      Ousidhoum, Nedjma",
    booktitle = "Proceedings of the 15th Joint Conference on Lexical and Computational Semantics (*{SEM} 2026)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.starsem-conference.26/",
    pages = "385--394",
    ISBN = "979-8-89176-413-2",
    abstract = "We disentangle multilingual sentence embeddings into language-dependent and language-agnostic components, leveraging the latter to improve cross-lingual similarity estimation. Previous studies on this approach have trained disentanglers by combining intra-component constraints, which either align or disalign language-dependent embeddings or language-agnostic embeddings, with inter-component constraints across both embeddings. However, when and how these constraints are effective remains unclear. Our experiments on sentence similarity estimation and machine translation quality estimation revealed that while intra-component constraints and the combination of both constraints are effective for encoder-based multilingual sentence embeddings, inter-component constraints are effective for decoder-based ones. Furthermore, our detailed analysis revealed distinct roles: intra-component constraints improve uniformity within the embedding space, while inter-component constraints enhance cross-lingual alignment between parallel sentences."
}