@inproceedings{nishikawa-etal-2022-multilingual,
    title = "A Multilingual Bag-of-Entities Model for Zero-Shot Cross-Lingual Text Classification",
    author = "Nishikawa, Sosuke  and
      Yamada, Ikuya  and
      Tsuruoka, Yoshimasa  and
      Echizen, Isao",
    editor = "Fokkens, Antske  and
      Srikumar, Vivek",
    booktitle = "Proceedings of the 26th Conference on Computational Natural Language Learning (CoNLL)",
    month = dec,
    year = "2022",
    address = "Abu Dhabi, United Arab Emirates (Hybrid)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/icon-24-ingestion/2022.conll-1.1/",
    doi = "10.18653/v1/2022.conll-1.1",
    pages = "1--12",
    abstract = "We present a multilingual bag-of-entities model that effectively boosts the performance of zero-shot cross-lingual text classification by extending a multilingual pre-trained language model (e.g., M-BERT). It leverages the multilingual nature of Wikidata: entities in multiple languages representing the same concept are defined with a unique identifier. This enables entities described in multiple languages to be represented using shared embeddings. A model trained on entity features in a resource-rich language can thus be directly applied to other languages. Our experimental results on cross-lingual topic classification (using the MLDoc and TED-CLDC datasets) and entity typing (using the SHINRA2020-ML dataset) show that the proposed model consistently outperforms state-of-the-art models."
}