COLING 2020main32 citations

Augmenting NLP models using Latent Feature Interpolations

Amit Jindal, Arijit Ghosh Chowdhury, Aniket Didolkar, Di Jin, Ramit Sawhney, Rajiv Ratn Shah

Abstract

Models with a large number of parameters are prone to over-fitting and often fail to capture the underlying input distribution. We introduce Emix, a data augmentation method that uses interpolations of word embeddings and hidden layer representations to construct virtual examples. We show that Emix shows significant improvements over previously used interpolation based regularizers and data augmentation techniques. We also demonstrate how our proposed method is more robust to sparsification. We highlight the merits of our proposed methodology by performing thorough quantitative and qualitative assessments.

BibTeX
@inproceedings{jindal-etal-2020-augmenting,
    title = "Augmenting {NLP} models using Latent Feature Interpolations",
    author = "Jindal, Amit  and
      Ghosh Chowdhury, Arijit  and
      Didolkar, Aniket  and
      Jin, Di  and
      Sawhney, Ramit  and
      Shah, Rajiv Ratn",
    editor = "Scott, Donia  and
      Bel, Nuria  and
      Zong, Chengqing",
    booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
    month = dec,
    year = "2020",
    address = "Barcelona, Spain (Online)",
    publisher = "International Committee on Computational Linguistics",
    url = "https://aclanthology.org/2020.coling-main.611/",
    doi = "10.18653/v1/2020.coling-main.611",
    pages = "6931--6936"
}
Augmenting NLP models using Latent Feature Interpolations · COLING 2020