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 2101.09698cs.CLcs.AIcs.CVcs.MM
收藏

基于多智能体强化学习的快速序列生成

Fast Sequence Generation with Multi-Agent Reinforcement Learning

Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);University of Chinese Academy of Sciences(中国科学院大学)

Longteng Guo, Jing Liu, Xinxin Zhu, Hanqing Lu

摘要:

自回归序列生成模型在机器翻译和图像描述等领域已经达到了最先进的性能。这些模型是自回归的,因为它们通过调节先前生成的单词来生成每个单词,这导致推理过程中的严重延迟。最近,在机器翻译中已经提出了非自回归解码,以通过并行地生成所有单词来加快推理时间。通常,这些模型使用单词级交叉熵损失来独立地优化每个单词。然而,这样的学习过程中没有考虑的一致性,从而导致这些非自回归模型的生成质量较差。在本文中,我们提出了一种简单有效的非自回归序列生成(NAG)模型,并采用了一种新型训练范式:反事实临界多智能体学习(CMAL)。CMAL将NAG表述为一个多智能体强化学习系统,在该系统中,目标序列中的元素位置被视为学习合作最大化奖励水平的智能体。在MSCOCO图像描述基准测试中,我们的NAG方法达到了与最先进的自回归模型相当的性能,同时带来了13.9倍的解码加速比。在WMT 14 EN-DE机器翻译数据集上,我们的方法比交叉熵训练的基线提高了6.0个BLEU点,同时实现了17.46倍的最大解码加速比。

英文摘要:

Autoregressive sequence Generation models have achieved state-of-the-art performance in areas like machine translation and image captioning. These models are autoregressive in that they generate each word by conditioning on previously generated words, which leads to heavy latency during inference. Recently, non-autoregressive decoding has been proposed in machine translation to speed up the inference time by generating all words in parallel. Typically, these models use the word-level cross-entropy loss to optimize each word independently. However, such a learning process fails to consider the sentence-level consistency, thus resulting in inferior generation quality of these non-autoregressive models. In this paper, we propose a simple and efficient model for Non-Autoregressive sequence Generation (NAG) with a novel training paradigm: Counterfactuals-critical Multi-Agent Learning (CMAL). CMAL formulates NAG as a multi-agent reinforcement learning system where element positions in the target sequence are viewed as agents that learn to cooperatively maximize a sentence-level reward. On MSCOCO image captioning benchmark, our NAG method achieves a performance comparable to state-of-the-art autoregressive models, while brings 13.9x decoding speedup. On WMT14 EN-DE machine translation dataset, our method outperforms cross-entropy trained baseline by 6.0 BLEU points while achieves the greatest decoding speedup of 17.46x.

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。

↑