@inproceedings{wu-etal-2025-int,
    title = "{INT}: Establishing Information Transfer for Multilingual Intent Detection and Slot Filling",
    author = "Wu, Di  and
      Jiang, Liting  and
      Mao, Bohui  and
      Xie, Hongyan  and
      Su, Haoxiang  and
      He, Zhongjiang  and
      Fang, Ruiyu  and
      Song, Shuangyong  and
      Huang, Hao  and
      Li, Xuelong",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/mtsummit-25-ingestion/2025.findings-acl.783/",
    doi = "10.18653/v1/2025.findings-acl.783",
    pages = "15120--15142",
    ISBN = "979-8-89176-256-5",
    abstract = "Multilingual spoken language understanding (SLU) involves intent detection (ID) and slot filling (SF) across multiple languages. The inherent linguistic diversity presents significant challenges in achieving performance comparable to traditional SLU. Recent studies have attempted to improve multilingual SLU performance by sharing multilingual encoders. However, these approaches have not directly established information flow between languages. To address this, we first demonstrate the feasibility of such information transfer and pinpoint the key challenges: prediction error mitigation and multilingual slot alignment. We then propose the INformation Transfer network (INT) to tackle these challenges. The gate unit in INT controls the information flow between languages, reducing the adverse impact of prediction errors on both ID and SF. Additionally, we reformulate SF as a span prediction problem and introduce a slot-matching attention mechanism to achieve slot alignment across languages. Experimental results on the MASSIVE and MASSIVE-UG datasets show that our model outperforms all baselines in overall accuracy across all languages, and demonstrates robust performance when different languages are used as the source."
}