Augmenting NLP models using Latent Feature Interpolations
Published in COLING, 2020
Recommended citation: Jindal, Amit, Arijit Ghosh Chowdhury, Aniket Didolkar, Di Jin, Ramit Sawhney, and Rajiv Shah. "Augmenting NLP models using Latent Feature Interpolations." In Proceedings of the 28th International Conference on Computational Linguistics, pp. 6931-6936. 2020. https://www.aclweb.org/anthology/2020.coling-main.611.pdf
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.
Recommended citation: Jindal, Amit, Arijit Ghosh Chowdhury, Aniket Didolkar, Di Jin, Ramit Sawhney, and Rajiv Shah. “Augmenting NLP models using Latent Feature Interpolations.” In Proceedings of the 28th International Conference on Computational Linguistics, pp. 6931-6936. 2020.