Language Embeddings for Typology and Cross-lingual Transfer Learning

Dian Yu; Taiqi He; Kenji Sagae

ACL 2021long13 citations

Language Embeddings for Typology and Cross-lingual Transfer Learning

Abstract

Cross-lingual language tasks typically require a substantial amount of annotated data or parallel translation data. We explore whether language representations that capture relationships among languages can be learned and subsequently leveraged in cross-lingual tasks without the use of parallel data. We generate dense embeddings for 29 languages using a denoising autoencoder, and evaluate the embeddings using the World Atlas of Language Structures (WALS) and two extrinsic tasks in a zero-shot setting: cross-lingual dependency parsing and cross-lingual natural language inference.

BibTeX

@inproceedings{yu-etal-2021-language,
    title = "Language Embeddings for Typology and Cross-lingual Transfer Learning",
    author = "Yu, Dian  and
      He, Taiqi  and
      Sagae, Kenji",
    editor = "Zong, Chengqing  and
      Xia, Fei  and
      Li, Wenjie  and
      Navigli, Roberto",
    booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
    month = aug,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2021.acl-long.560/",
    doi = "10.18653/v1/2021.acl-long.560",
    pages = "7210--7225"
}