SEARNN: Training RNNs with global-local losses

Rémi Leblond, Jean-Baptiste Alayrac, Anton Osokin, Simon Lacoste-Julien

Abstract: We propose SEARNN, a novel training algorithm for recurrent neural networks (RNNs) inspired by the "learning to search" (L2S) approach to structured prediction. RNNs have been widely successful in structured prediction applications such as machine translation or parsing, and are commonly trained using maximum likelihood estimation (MLE). Unfortunately, this training loss is not always an appropriate surrogate for the test error: by only maximizing the ground truth probability, it fails to exploit the wealth of information offered by structured losses. Further, it introduces discrepancies between training and predicting (such as exposure bias) that may hurt test performance. Instead, SEARNN leverages test-alike search space exploration to introduce global-local losses that are closer to the test error. We first demonstrate improved performance over MLE on two different tasks: OCR and spelling correction. Then, we propose a subsampling strategy to enable SEARNN to scale to large vocabulary sizes. This allows us to validate the benefits of our approach on a machine translation task.

TL;DR: We introduce SeaRNN, a novel algorithm for RNN training, inspired by the learning to search approach to structured prediction, in order to avoid the limitations of MLE training.

Keywords: Structured prediction, RNNs

Code: [ RemiLeblond/SeaRNN-open](https://github.com/RemiLeblond/SeaRNN-open)