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 1610.04211cs.CLstat.ML
收藏

门控端到端内存网络

Gated End-to-End Memory Networks

The University of Melbourne(墨尔本大学);Xerox Research Centre Europe(施乐欧洲研究中心)

Julien Perez, Fei Liu

摘要:

使用可微分推理模型的机器阅读最近取得了显著的进展。在这种情况下,端到端可训练记忆网络MemN 2N在基于简单自然语言的推理任务(如事实推理和基本演绎)上表现出了良好的性能。然而,其他任务,即多事实问题回答,位置推理或对话相关的任务,仍然具有挑战性,特别是由于组成这一系列模型的存储器和控制器模块之间的更复杂的交互的必要性。本文从计算机视觉领域中的连接捷径原理出发,提出了一种新的端到端内存访问调节机制。具体地说,我们开发了一个门控端到端可训练记忆网络架构GMemN 2N。从机器学习的角度来看,这种新的能力是以端到端的方式学习的,而不需要使用任何额外的监督信号,就我们所知,这是同类中的第一个。我们的实验表明,在20 bAbI数据集的最具挑战性的任务显着改善,而不使用任何领域的知识。然后,我们展示了对对话bAbI任务的改进,包括真正的基于人类-机器人转换的对话状态跟踪挑战(DSTC-2)数据集。在这两个数据集上,我们的模型设定了最新的技术水平。

英文摘要:

Machine reading using differentiable reasoning models has recently shown remarkable progress. In this context, End-to-End trainable Memory Networks, MemN2N, have demonstrated promising performance on simple natural language based reasoning tasks such as factual reasoning and basic deduction. However, other tasks, namely multi-fact question-answering, positional reasoning or dialog related tasks, remain challenging particularly due to the necessity of more complex interactions between the memory and controller modules composing this family of models. In this paper, we introduce a novel end-to-end memory access regulation mechanism inspired by the current progress on the connection short-cutting principle in the field of computer vision. Concretely, we develop a Gated End-to-End trainable Memory Network architecture, GMemN2N. From the machine learning perspective, this new capability is learned in an end-to-end fashion without the use of any additional supervision signal which is, as far as our knowledge goes, the first of its kind. Our experiments show significant improvements on the most challenging tasks in the 20 bAbI dataset, without the use of any domain knowledge. Then, we show improvements on the dialog bAbI tasks including the real human-bot conversion-based Dialog State Tracking Challenge (DSTC-2) dataset. On these two datasets, our model sets the new state of the art.

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。

↑