arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2109.04673cs.CL
收藏

DIALKI:基于对话-文档语境化的会话系统知识识别

DIALKI: Knowledge Identification in Conversational Systems through Dialogue-Document Contextualization

University of Washington(华盛顿大学);Allen Institute for AI(艾伦人工智能研究院)

Zeqiu Wu, Bo-Ru Lu, Hannaneh Hajishirzi, Mari Ostendorf

摘要:

识别在长文档基础上的会话系统中使用的相关知识对于有效的响应生成至关重要。我们引入了一个知识识别模型,利用文档结构提供对话上下文化的通道编码,并更好地定位与对话相关的知识。辅助丢失捕获对话框-文档连接的历史记录。我们证明了我们的模型在两个基于文档的会话数据集上的有效性,并提供了对看不见的文档和长对话上下文的泛化分析。

英文摘要:

Identifying relevant knowledge to be used in conversational systems that are grounded in long documents is critical to effective response generation. We introduce a knowledge identification model that leverages the document structure to provide dialogue-contextualized passage encodings and better locate knowledge relevant to the conversation. An auxiliary loss captures the history of dialogue-document connections. We demonstrate the effectiveness of our model on two document-grounded conversational datasets and provide analyses showing generalization to unseen documents and long dialogue contexts.

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。

↑