@inproceedings{yerukola-etal-2021-data,
    title = "Data Augmentation for Voice-Assistant {NLU} using {BERT}-based Interchangeable Rephrase",
    author = "Yerukola, Akhila  and
      Bretan, Mason  and
      Jin, Hongxia",
    editor = "Merlo, Paola  and
      Tiedemann, Jorg  and
      Tsarfaty, Reut",
    booktitle = "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume",
    month = apr,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2021.eacl-main.159/",
    doi = "10.18653/v1/2021.eacl-main.159",
    pages = "1852--1860",
    abstract = "We introduce a data augmentation technique based on byte pair encoding and a BERT-like self-attention model to boost performance on spoken language understanding tasks. We compare and evaluate this method with a range of augmentation techniques encompassing generative models such as VAEs and performance-boosting techniques such as synonym replacement and back-translation. We show our method performs strongly on domain and intent classification tasks for a voice assistant and in a user-study focused on utterance naturalness and semantic similarity."
}