Commonsense Knowledge Aware Conversation Generation with Graph Attention
Commonsense Knowledge Aware Conversation Generation with Graph Attention
复制标题
DOI：
10.24963/ijcai.2018/643
复制
发表时间：
2018-07
期刊：
影响因子：
--
通讯作者：
Hao Zhou;Tom Young;Minlie Huang;Haizhou Zhao;Jingfang Xu;Xiaoyan Zhu
中科院分区：
文献类型：
--
作者：
Hao Zhou;Tom Young;Minlie Huang;Haizhou Zhao;Jingfang Xu;Xiaoyan Zhu
常识知识对于许多自然语言处理任务至关重要。在本文中，我们提出了一个新的开放域会话生成模型，以证明如何大规模的常识知识可以促进语言的理解和生成。给定一个用户帖子，该模型从知识库中检索相关的知识图，然后使用静态图注意机制对图进行编码，这增加了帖子的语义信息，从而支持对帖子的更好理解。然后，在单词生成过程中，该模型通过动态图注意机制，认真地读取检索到的知识图和每个图中的知识三元组，以促进更好的生成。这是第一次尝试使用大规模的常识知识在会话生成。此外，与单独和独立地使用知识三元组（实体）的现有模型不同，我们的模型将每个知识图视为一个整体，从而在图中编码更多结构化的、连接的语义信息。实验表明，该模型可以产生更适当的和翔实的反应比国家的最先进的基线。
Commonsense knowledge is vital to many natural language processing tasks. In this paper, we present a novel open-domain conversation generation model to demonstrate how large-scale commonsense knowledge can facilitate language understanding and generation. Given a user post, the model retrieves relevant knowledge graphs from a knowledge base and then encodes the graphs with a static graph attention mechanism, which augments the semantic information of the post and thus supports better understanding of the post. Then, during word generation, the model attentively reads the retrieved knowledge graphs and the knowledge triples within each graph to facilitate better generation through a dynamic graph attention mechanism. This is the first attempt that uses large-scale commonsense knowledge in conversation generation. Furthermore, unlike existing models that use knowledge triples (entities) separately and independently, our model treats each knowledge graph as a whole, which encodes more structured, connected semantic information in the graphs. Experiments show that the proposed model can generate more appropriate and informative responses than state-of-the-art baselines.