Non-Autoregressive Text Generation with Pre-trained Language Models

Abstract

Non-autoregressive generation (NAG) has recently attracted great attention due to its fast inference speed. However, the generation quality of existing NAG models still lags behind their autoregressive counterparts. In this work, we show that BERT can be employed as the backbone of a NAG model to greatly improve performance. Additionally, we devise mechanisms to alleviate the two common problems of vanilla NAG models: the inflexibility of prefixed output length and the conditional independence of individual token predictions. Lastly, to further increase the speed advantage of the proposed model, we propose a new decoding strategy, ratio-first, for applications where the output lengths can be approximately estimated beforehand. For a comprehensive evaluation, we test the proposed model on three text generation tasks, including text summarization, sentence compression and machine translation. Experimental results show that our model significantly outperforms existing non-autoregressive baselines and achieves competitive performance with many strong autoregressive models. In addition, we also conduct extensive analysis experiments to reveal the effect of each proposed component.

Accepted to EACL 2021

References in corpus (1)

• Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation

Cited by in corpus (4)

• BANG: Bridging Autoregressive and Non-autoregressive Generation with Large Scale Pretraining
• Geo-FuB: A Method for Constructing an Operator-Function Knowledge Base for Geospatial Code Generation Tasks Using Large Language Models
• Progressive Multi-Granularity Training for Non-Autoregressive Translation
• Tail-to-Tail Non-Autoregressive Sequence Prediction for Chinese Grammatical Error Correction