arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1805.09461cs.LGstat.ML
收藏

序列到序列模型的深度强化学习

Deep Reinforcement Learning For Sequence to Sequence Models

Virginia Tech(弗吉尼亚理工学院)

Yaser Keneshloo, Tian Shi, Naren Ramakrishnan, Chandan K. Reddy

摘要:

近年来,序列到序列(seq 2seq)模型已经获得了很大的普及,并且在诸如机器翻译、标题生成、文本摘要、语音到文本转换以及图像字幕生成等各种各样的任务中提供了最先进的性能。所有这些模型的底层框架通常是包括编码器和解码器的深度神经网络。尽管简单的编码器-解码器模型产生有竞争力的结果,但许多研究人员已经提出了对这些序列到序列模型的额外改进,例如,在输入上使用基于注意力的模型、指针生成模型和自我注意力模型。然而,这种seq 2seq模型存在两个常见问题:1)暴露偏差和2)训练/测试测量之间的不一致。最近,在seq 2seq模型中解决这两个问题时出现了一个全新的观点,利用了强化学习(RL)的方法。在这项调查中,我们认为seq 2seq问题从RL的角度来看,并提供了一个配方结合RL方法在决策的权力与序列到序列模型,使记住长期记忆。我们提出了一些最新的框架,这些框架结合了RL和深度神经网络的概念,并解释了这两个领域如何在解决复杂的seq 2seq任务时相互受益。我们的工作旨在深入了解当前方法固有的一些问题,以及我们如何使用更好的RL模型来解决这些问题。我们还提供了实现本文中讨论的大多数RL模型的源代码,以支持抽象文本摘要的复杂任务。

英文摘要:

In recent times, sequence-to-sequence (seq2seq) models have gained a lot of popularity and provide state-of-the-art performance in a wide variety of tasks such as machine translation, headline generation, text summarization, speech to text conversion, and image caption generation. The underlying framework for all these models is usually a deep neural network comprising an encoder and a decoder. Although simple encoder-decoder models produce competitive results, many researchers have proposed additional improvements over these sequence-to-sequence models, e.g., using an attention-based model over the input, pointer-generation models, and self-attention models. However, such seq2seq models suffer from two common problems: 1) exposure bias and 2) inconsistency between train/test measurement. Recently, a completely novel point of view has emerged in addressing these two problems in seq2seq models, leveraging methods from reinforcement learning (RL). In this survey, we consider seq2seq problems from the RL point of view and provide a formulation combining the power of RL methods in decision-making with sequence-to-sequence models that enable remembering long-term memories. We present some of the most recent frameworks that combine concepts from RL and deep neural networks and explain how these two areas could benefit from each other in solving complex seq2seq tasks. Our work aims to provide insights into some of the problems that inherently arise with current approaches and how we can address them with better RL models. We also provide the source code for implementing most of the RL models discussed in this paper to support the complex task of abstractive text summarization.

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。

↑