• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International joint conference on natural language processing;Conference on empirical methods in natural language processing >Knowledge Aware Conversation Generation with Explainable Reasoning over Augmented Graphs
【24h】

Knowledge Aware Conversation Generation with Explainable Reasoning over Augmented Graphs

机译：扩展图上具有可解释推理的知识感知会话生成

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Two types of knowledge, triples from knowledge graphs and texts from documents, have been studied for knowledge aware open-domain conversation generation, in which graph paths can narrow down vertex candidates for knowledge selection decision, and texts can provide rich information for response generation. Fusion of a knowledge graph and texts might yield mutually reinforcing advantages, but there is less study on that. To address this challenge, we propose a knowledge aware chatting machine with three components, an augmented knowledge graph with both triples and texts, knowledge selector, and knowledge aware response generator. For knowledge selection on the graph, we formulate it as a problem of multi-hop graph reasoning to effectively capture conversation flow, which is more explainable and flexible in comparison with previous work. To fully leverage long text information that differentiates our graph from others, we improve a state of the art reasoning algorithm with machine reading comprehension technology. We demonstrate the effectiveness of our system on two datasets in comparison with state-of-the-art models~1.
机译：已经研究了两种类型的知识，即来自知识图的三重和来自文档的文本，用于知识感知的开放域对话生成，其中图路径可以缩小用于知识选择决策的顶点候选，而文本可以为响应生成提供丰富的信息。知识图和文本的融合可能会产生相辅相成的优势，但是对此的研究很少。为了解决这一挑战，我们提出了一种具有三个组件的知识感知型聊天机，即具有三元组和文本的增强型知识图，知识选择器以及知识感知型响应生成器。对于图上的知识选择，我们将其表示为有效地捕获对话流的多跳图推理问题，与以前的工作相比，它更具解释性和灵活性。为了充分利用长文本信息，可以将我们的图形与其他图形区分开，我们使用机器阅读理解技术改进了最新的推理算法。与最先进的模型相比，我们在两个数据集上证明了我们系统的有效性。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号