arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2102.08220cs.CL
收藏

基于预训练语言模型的非自回归文本生成

Non-Autoregressive Text Generation with Pre-trained Language Models

University of Cambridge(剑桥大学);The Chinese University of Hong Kong(香港中文大学);Tencent AI Lab(腾讯人工智能实验室);Apple(苹果公司)

Yixuan Su, Deng Cai, Yan Wang, David Vandyke, Simon Baker, Piji Li, Nigel Collier

摘要:

非自回归生成(NAG)由于其快速的推理速度,近年来引起了人们的极大关注。然而,现有的NAG模型的生成质量仍然落后于自回归模型。在这项工作中,我们表明,BERT可以作为一个NAG模型的骨干,大大提高性能。此外,我们设计的机制,以减轻香草NAG模型的两个常见问题:前缀输出长度的可扩展性和条件独立的个人令牌预测。最后,为了进一步提高所提出的模型的速度优势,我们提出了一种新的解码策略,比率优先,用于输出长度可以预先近似估计的应用。为了进行全面的评估,我们测试了三个文本生成任务,包括文本摘要,句子压缩和机器翻译所提出的模型。实验结果表明,我们的模型显着优于现有的非自回归基线,并取得了竞争力的性能与许多强自回归模型。此外,我们还进行了广泛的分析实验,以揭示每个建议的组件的效果。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑