Learning to Deliberate: Multi-Pass Decoding for Document-Grounded Conversations | |
Junyan Qiu1,2![]() ![]() ![]() | |
2024-03 | |
会议名称 | International Joint Conference on Neural Networks |
会议日期 | 2024-07 |
会议地点 | YOKOHAMA, JAPAN |
出版者 | IEEE |
摘要 | Document-grounded conversations are designed to generate and engage in conversations based on specific documents or texts provided as context. The ability to incorporate documents into these conversations enables a deeper understanding of the subject matter, fostering more informed and meaningful discussions. However, prior approaches were predominantly rooted in auto-regressive models, overlooking the need for a comprehensive global perspective and the refinement of responses. In this paper, we introduce an innovative Multi-Pass Decoding (MPD) architecture, which iteratively updates background knowledge and enhances responses in document-grounded conversations. During each iteration, it starts by adaptively combining semantics derived from the context, documents, and previous responses. To address the issue of inadequate response quality, we have also developed two modules dedicated to identifying and refining inappropriate words or phrases in responses generated during the previous iteration. Furthermore, MPD is model-agnostic, enabling seamless integration with conventional sequence-to-sequence frameworks. Our empirical experiments on three document-grounded conversation datasets demonstrate that our methods facilitate the production of more contextually accurate and coherent responses. |
关键词 | dialogue system document-grounded conversations deliberation network sequence-to-sequence framework |
学科门类 | 工学::计算机科学与技术(可授工学、理学学位) |
收录类别 | EI |
七大方向——子方向分类 | 自然语言处理 |
国重实验室规划方向分类 | 语音语言处理 |
是否有论文关联数据集需要存交 | 否 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/57411 |
专题 | 综合信息系统研究中心_视知觉融合及其应用 |
通讯作者 | Junyan Qiu |
作者单位 | 1.University of Chinese Academy of Sciences 2.Institute of Automation, Chinese Academy of Sciences 3.Meituan |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Junyan Qiu,Haitao Wang,Yiping Yang. Learning to Deliberate: Multi-Pass Decoding for Document-Grounded Conversations[C]:IEEE,2024. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
a69-qiu final.pdf(1033KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论