Dialog System Technology Challenge 7
Koichiro Yoshino, Chiori Hori, Julien Perez, Luis Fernando D’Haro, Lazaros Polymenakos, Chulaka Gunasekara, Walter S. Lasecki, Jonathan K. Kummerfeld, Michel Galley, Chris Brockett, Jianfeng Gao, Bill Dolan, Xiang Gao, Huda Alamari, Tim K. Marks, Devi Parikh and Dhruv Batra Every author has equal contribution. http://workshop.colips.org/dstc7
Abstract
This paper introduces the Seventh Dialog System Technology Challenges (DSTC), which use shared datasets to explore the problem of building dialog systems. Recently, end-to-end dialog modeling approaches have been applied to various dialog tasks. The seventh DSTC (DSTC7) focuses on developing technologies related to end-to-end dialog systems for (1) sentence selection, (2) sentence generation and (3) audio visual scene aware dialog. This paper summarizes the overall setup and results of DSTC7, including detailed descriptions of the different tracks and provided datasets. We also describe overall trends in the submitted systems and the key results. Each track introduced new datasets and participants achieved impressive results using state-of-the-art end-to-end technologies.
中文速览
对话系统长期面临一个核心难题：如何让机器真正理解并生成自然、有用的对话回复，而不只是死记硬背固定脚本。第七届对话系统技术挑战赛（DSTC7）围绕这一难题设置了三条赛道：句子选择（从大量候选回复中找出最合适的那条）、句子生成（结合外部知识生成有内容、有信息量的回复）以及音视频场景感知对话（让系统看懂视频后与用户展开对话）。各赛道引入了全新数据集，吸引了数十支队伍参赛，最优系统在句子选择任务上取得了 Recall@1 达 0.645 的亮眼成绩，生成和视觉对话赛道也涌现出多种有竞争力的端到端方案。这项挑战赛的意义在于推动对话技术走向更贴近真实场景的应用——处理海量候选、融合外部知识、理解多模态信息——为整个领域的下一步发展划定了新的研究基准。
原文 arXiv:1901.03461;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1901.03461v1