arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1905.13637cs.CLcs.LG
收藏

GSN:一种用于多方对话的图结构网络

GSN: A Graph-Structured Network for Multi-Party Dialogues

Peking University(北京大学);University of Illinois at Chicago(伊利诺伊大学芝加哥分校)

Wenpeng Hu, Zhangming Chan, Bing Liu, Dongyan Zhao, Jinwen Ma, Rui Yan

摘要:

现有的神经模型的对话响应生成假设的话语顺序组织。然而,许多现实世界的对话涉及多个对话者(即,多方对话),而这一假设并不成立,因为不同对话者的发言可能“并行”发生。“本文将现有的基于序列的模型推广到用于对话建模的图结构神经网络(GSN)。GSN的核心是一个基于图的编码器,它可以对图结构对话中的信息流进行建模(两方顺序对话是一种特殊情况)。实验结果表明,GSN显著优于现有的基于序列的模型。

英文摘要:

Existing neural models for dialogue response generation assume that utterances are sequentially organized. However, many real-world dialogues involve multiple interlocutors (i.e., multi-party dialogues), where the assumption does not hold as utterances from different interlocutors can occur "in parallel." This paper generalizes existing sequence-based models to a Graph-Structured neural Network (GSN) for dialogue modeling. The core of GSN is a graph-based encoder that can model the information flow along the graph-structured dialogues (two-party sequential dialogues are a special case). Experimental results show that GSN significantly outperforms existing sequence-based models.

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。

↑