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.
翻译:自动递增序列 生成模型在机器翻译和图像字幕等领域达到了最先进的性能。 这些模型具有自递增性, 因为它们通过对先前生成的单词进行调制, 产生每个单词, 从而导致在推断过程中出现严重延迟。 最近, 在机器翻译中提出了非自动递减解码, 以通过平行生成所有单词来加快推导时间。 典型地, 这些模型使用字级跨物种流失来独立优化每个单词。 然而, 这种学习过程没有考虑到判决水平的一致性, 从而导致这些非自动递增模式的生成质量不高。 在本文中, 我们提出了一个简单有效的非自动递增序列生成模式(NAG) 。 最近, 在机器翻译过程中, 非自动递增的解调解密模式( CMAL) 。 CMAL 将 NAG 设计成一个多剂强化学习系统, 其中将目标序列中的元素位置视为合作最大化判决级奖赏的代理。 在 MICO 描述这些非自动递增制模型的代号上, 我们的NAG- 9 方法在通过自我递增速度方法实现最大幅度的自动递增的系统。