An Imitation Learning Curriculum for Text Editing with Non-Autoregressive Models

TL;DR

This paper introduces a curriculum-based imitation learning framework for non-autoregressive text editing models, improving their training and generalization for tasks like text simplification and summarization.

Contribution

It proposes a novel training strategy combining roll-in policies and curriculum learning to enhance non-autoregressive editing models.

Findings

Significant quality improvements on text simplification and summarization tasks.

Better control over output complexity in text simplification.

Addresses training-inference mismatch issues in editing models.

Abstract

We propose a framework for training non-autoregressive sequence-to-sequence models for editing tasks, where the original input sequence is iteratively edited to produce the output. We show that the imitation learning algorithms designed to train such models for machine translation introduces mismatches between training and inference that lead to undertraining and poor generalization in editing scenarios. We address this issue with two complementary strategies: 1) a roll-in policy that exposes the model to intermediate training sequences that it is more likely to encounter during inference, 2) a curriculum that presents easy-to-learn edit operations first, gradually increasing the difficulty of training samples as the model becomes competent. We show the efficacy of these strategies on two challenging English editing tasks: controllable text simplification and abstractive summarization. Our approach significantly improves output quality on both tasks and controls output complexity better on the simplification task.