ACL Findings2023
NewsDialogues: Towards Proactive News Grounded Conversation
Siheng Li, Yichun Yin, Cheng Yang, Wangjie Jiang, Yiwei Li, Zesen Cheng, Lifeng Shang, Xin Jiang, Qun Liu, Yujiu Yang
Abstract
Hot news is one of the most popular topics in daily conversations. However, news grounded conversation has long been stymied by the lack of well-designed task definition and scarce data. In this paper, we propose a novel task, Proactive News Grounded Conversation, in which a dialogue system can proactively lead the conversation based on some key topics of the news. In addition, both information-seeking and chitchat scenarios are included realistically, where the user may ask a series of questions about the news details or express their opinions and be eager to chat. To further develop this novel task, we collect a human-to-human Chinese dialogue dataset NEWSDIALOGUES, which includes 1K conversations with a total of 14.6K utterances and detailed annotations for target topics and knowledge spans. Furthermore, we propose a method named Predict-Generate-Rank, consisting of a generator for grounded knowledge prediction and response generation, and a ranker for the ranking of multiple responses to alleviate the exposure bias. We conduct comprehensive experiments to demonstrate the effectiveness of the proposed method and further present several key findings and challenges to prompt future research. 1
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
1 top-tier paper has cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- Towards Conversational Recommendation over Multi-Type Dialogs cites KdConv: A Chinese Multi-domain Dialogue Dataset Towards Multi-turn Knowledge-driven Conversation
- KdConv: A Chinese Multi-domain Dialogue Dataset Towards Multi-turn Knowledge-driven Conversation cites The Curious Case of Neural Text Degeneration
- Language Models are Few-Shot Learners cites The Curious Case of Neural Text Degeneration
Cited by top-tier papers1
Builds on13
- Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
- The Curious Case of Neural Text DegenerationAri Holtzman, Jan Buys, Li Du, Maxwell Forbes et al.ICLR 2020 · 4,112 citations
- Towards Conversational Recommendation over Multi-Type DialogsZeming Liu, Haifeng Wang, Zheng-Yu Niu, Hua Wu et al.ACL 2020 · 157 citations
- KdConv: A Chinese Multi-domain Dialogue Dataset Towards Multi-turn Knowledge-driven ConversationHao Zhou, Chujie Zheng, Kaili Huang, Minlie Huang et al.ACL 2020 · 106 citations
- doc2dial: A Goal-Oriented Document-Grounded Dialogue DatasetSong Feng, Hui Wan, R. Chulaka Gunasekara, Siva Sankalp Patel et al.EMNLP 2020 · 87 citations
Related papers
- KPT: Keyword-Guided Pre-training for Grounded Dialog GenerationQi Zhu, Fei Mi, Zheng Zhang, Yasheng Wang et al.AAAI 2023 · 5 citations
- Dynamic Knowledge Routing Network for Target-Guided Open-Domain ConversationJinghui Qin, Zheng Ye, Jianheng Tang, Xiaodan LiangAAAI 2020 · 36 citations
- Knowledge-Grounded Dialogue Generation with Pre-trained Language ModelsXueliang Zhao, Wei Wu, Can Xu, Chongyang Tao et al.EMNLP 2020 · 153 citations
- Converse, Focus and Guess - Towards Multi-Document Driven DialogueHan Liu, Caixia Yuan, Xiaojie Wang, Yushu Yang et al.AAAI 2021 · 1 citation
- Sequential Topic Selection Model with Latent Variable for Topic-Grounded DialogueXiaofei Wen, Wei Wei, Xian-Ling MaoEMNLP Findings 2022 · 1 citation
