Sequence Level Training with Recurrent Neural Networks

ICLR 2016


Many natural language processing applications use language models to generate text. These models are typically trained to predict the next word in a sequence, given the previous words and some context such as an image. However, at test time the model is expected to generate the entire sequence from scratch. This discrepancy makes generation brittle, as errors may accumulate along the way. We address this issue by proposing a novel sequence level training algorithm that directly optimizes the metric used at test time, such as BLEU or ROUGE. On three different tasks, our approach outperforms several strong baselines for greedy generation. The method is also competitive when these baselines employ beam search, while being several times faster.

Related Publications

All Publications

December 2, 2016


No Authors Listed

NeurIPS - December 10, 2020

Differentiable Expected Hypervolume Improvement for Parallel Multi-Objective Bayesian Optimization

Samuel Daulton, Maximilian Balandat, Eytan Bakshy

IEEE TSE - February 17, 2021

Machine Learning Testing: Survey, Landscapes and Horizons

Jie M. Zhang, Mark Harman, Lei Ma, Yang Liu

AISTATS - April 13, 2021

Multi-armed Bandits with Cost Subsidy

Deeksha Sinha, Karthik Abinav Sankararaman, Abbas Kazerouni, Vashist Avadhanula

To help personalize content, tailor and measure ads, and provide a safer experience, we use cookies. By clicking or navigating the site, you agree to allow our collection of information on and off Facebook through cookies. Learn more, including about available controls: Cookies Policy