论文标题
通过文档语义图提高了对话的知识选择
Enhanced Knowledge Selection for Grounded Dialogues via Document Semantic Graphs
论文作者
论文摘要
已经证明，提供对话模型，可以使开放域的对话更加丰富和吸引人。现有模型将知识选择视为单独处理每个句子的句子排名或分类问题，而忽略了后台文档中句子之间的内部语义连接。在这项工作中，我们建议将背景知识文档自动转换为文档语义图，然后在此类图上执行知识选择。我们的文档语义图通过使用句子节点来保留句子级信息，并提供句子之间的概念连接。我们共同将多任务学习应用于句子级别和概念级知识选择，并表明它改善了句子级别的选择。我们的实验表明，基于语义图的知识选择可以改善知识选择任务和HOLLE端到端响应生成任务的句子选择基线，并改善了WOW中看不见的主题的概括。
Providing conversation models with background knowledge has been shown to make open-domain dialogues more informative and engaging. Existing models treat knowledge selection as a sentence ranking or classification problem where each sentence is handled individually, ignoring the internal semantic connection among sentences in the background document. In this work, we propose to automatically convert the background knowledge documents into document semantic graphs and then perform knowledge selection over such graphs. Our document semantic graphs preserve sentence-level information through the use of sentence nodes and provide concept connections between sentences. We jointly apply multi-task learning for sentence-level and concept-level knowledge selection and show that it improves sentence-level selection. Our experiments show that our semantic graph-based knowledge selection improves over sentence selection baselines for both the knowledge selection task and the end-to-end response generation task on HollE and improves generalization on unseen topics in WoW.
