Gajbhiye, Amit and Jaf, Sardar and Al-Moubayed, Noura and McGough, A. Stephen and Bradley, Steven (2018) 'An exploration of dropout with RNNs for natural language inference.', in Artificial neural networks and machine learning - ICANN 2018 : 27th international Conference on Artificial Neural Networks, Rhodes, Greece, October 4-7, 2018, proceedings. Part III. Cham: Springer, pp. 157-167. Lecture notes in computer science. (11141).
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.
|Item Type:||Book chapter|
|Full text:||(AM) Accepted Manuscript|
Download PDF (423Kb)
|Publisher Web site:||https://doi.org/10.1007/978-3-030-01424-7_16|
|Publisher statement:||The final publication is available at Springer via https://doi.org/10.1007/978-3-030-01424-7_16.|
|Date accepted:||10 July 2018|
|Date deposited:||03 August 2018|
|Date of first online publication:||01 October 2018|
|Date first made open access:||No date available|
Save or Share this output
|Look up in GoogleScholar|