We use cookies to ensure that we give you the best experience on our website. You can change your cookie settings at any time. Otherwise, we'll assume you're OK to continue.

Durham University

Research & business

View Profile

Publication details

Gajbhiye, Amit, Jaf, Sardar, Al-Moubayed, Noura, McGough, A. Stephen & Bradley, Steven (2018), An Exploration of Dropout with RNNs for Natural Language Inference, in Kurková, V., Manolopoulos, Yannis, Hammer, Barbara, Iliadis, Lazaros S. & Maglogiannis, Ilias G. eds, Lecture Notes in Computer Science, 11141 ICANN 2018: 27th International Conference on Artificial Neural Networks. Rhodes, Springer, Cham, 157-167.

Author(s) from Durham


Dropout is a crucial regularization technique for the Recurrent Neural Network (RNN) models of Natural Language Inference (NLI). However, dropout has not been evaluated for the effectiveness at different layers and dropout rates in NLI models. In this paper, we propose a novel RNN model for NLI and empirically evaluate the effect of applying dropout at different layers in the model. We also investigate the impact of varying dropout rates at these layers. Our empirical evaluation on a large (Stanford Natural Language Inference (SNLI)) and a small (SciTail) dataset suggest that dropout at each feed-forward connection severely affects the model accuracy at increasing dropout rates. We also show that regularizing the embedding layer is efficient for SNLI whereas regularizing the recurrent layer improves the accuracy for SciTail. Our model achieved an accuracy 86.14% on the SNLI dataset and 77.05% on SciTail.