Modeling Situations in Neural Chat Bots
Modeling Situations in Neural Chat Bots
复制标题
DOI：
10.18653/v1/p17-3020
复制
发表时间：
2017-07
期刊：
影响因子：
--
通讯作者：
Shoetsu Sato;Naoki Yoshinaga;Masashi Toyoda;M. Kitsuregawa
中科院分区：
文献类型：
--
作者：
Shoetsu Sato;Naoki Yoshinaga;Masashi Toyoda;M. Kitsuregawa
社交媒体积累了大量的在线对话，使聊天对话的数据驱动建模成为可能。然而，尽管基于神经网络的S情商2S情商模型在机器翻译中取得了公认的成功，但仍然很难将其用于对话建模。主要挑战来自产出(回应)的高度自由度。这篇论文介绍了神经对话模型，它具有处理影响我们反应的各种情况的一般机制。在我们从推特confi收集的大量对话数据上进行的回答选择测试验证了所提出的模型的有效性，这些场景来自于话语、用户或时间。
Social media accumulates vast amounts of online conversations that enable data-driven modeling of chat dialogues. It is, however, still hard to utilize the neural network-based S EQ 2S EQ model for dialogue modeling in spite of its acknowledged success in machine translation. The main challenge comes from the high degrees of freedom of outputs (responses). This paper presents neural conversational models that have general mechanisms for handling a variety of situations that affect our responses. Response selection tests on massive dialogue data we have collected from Twitter confirmed the effectiveness of the proposed models with situations derived from utterances, users or time.