ACL Findings2022
A Slot Is Not Built in One Utterance: Spoken Language Dialogs with Sub-Slots
Sai Zhang, Yuwei Hu, Yuchuan Wu, Jiaman Wu, Yongbin Li, Jian Sun, Caixia Yuan, Xiaojie Wang
摘要
A slot value might be provided segment by segment over multiple-turn interactions in a dialog, especially for some important information such as phone numbers and names. It is a common phenomenon in daily life, but little attention has been paid to it in previous work. To fill the gap, this paper defines a new task named Sub-Slot based Task-Oriented Dialog (SSTOD) and builds a Chinese dialog dataset SSD for boosting research on SSTOD. The dataset includes a total of 40K dialogs and 500K utterances from four different domains: Chinese names, phone numbers, ID numbers and license plate numbers. The data is well annotated with sub-slot values, slot values, dialog states and actions. We find some new linguistic phenomena and interactive manners in SSTOD which raise critical challenges of building dialog agents for the task. We test three state-of-the-art dialog models on SSTOD and find they cannot handle the task well on any of the four domains. We also investigate an improved model by involving slot knowledge in a plug-in manner. More work should be done to meet the new challenges raised from SSTOD which widely exists in real-life applications.
问 Lune
几分钟读透这篇 Paper,不用再花一下午。
Lune 能读完全文,也能读引用它的顶会 Paper,讲清它的结论、证据和局限,每一点都注明出自哪篇 Paper。不用硬啃,也不靠猜。
已有 2 篇顶会 Paper 引用了它。别等审稿人问起,先弄清它们发现了什么。
脉络
- UniSA: Unified Generative Framework for Sentiment Analysis 引用了 GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-supervised Learning and Explicit Policy Injection
- GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-supervised Learning and Explicit Policy Injection 引用了 A Simple Language Model for Task-Oriented Dialogue
- GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-supervised Learning and Explicit Policy Injection 引用了 Towards Scalable Multi-Domain Conversational Agents: The Schema-Guided Dialogue Dataset
- A Simple Language Model for Task-Oriented Dialogue 引用了 Task-Oriented Dialog Systems That Consider Multiple Appropriate Responses under the Same Context
- CGoDial: A Large-Scale Benchmark for Chinese Goal-oriented Dialog Evaluation 引用了 GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-supervised Learning and Explicit Policy Injection
- CGoDial: A Large-Scale Benchmark for Chinese Goal-oriented Dialog Evaluation 引用了 Towards Scalable Multi-Domain Conversational Agents: The Schema-Guided Dialogue Dataset
引用它的顶会 Paper2
它引用的 Paper5
- Towards Scalable Multi-Domain Conversational Agents: The Schema-Guided Dialogue DatasetAbhinav Rastogi, Xiaoxue Zang, Srinivas Sunkara, Raghav Gupta 等AAAI 2020 · 707 次引用
- A Simple Language Model for Task-Oriented DialogueEhsan Hosseini-Asl, Bryan McCann, Chien-Sheng Wu, Semih Yavuz 等NeurIPS 2020 · 590 次引用
- Task-Oriented Dialog Systems That Consider Multiple Appropriate Responses under the Same ContextYichi Zhang, Zhijian Ou, Zhou YuAAAI 2020 · 198 次引用
- GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-supervised Learning and Explicit Policy InjectionWanwei He, Yinpei Dai, Yinhe Zheng, Yuchuan Wu 等AAAI 2022 · 181 次引用
- End-to-End Neural Pipeline for Goal-Oriented Dialogue Systems using GPT-2DongHoon Ham, Jeong-Gwan Lee, Youngsoo Jang, Kee-Eung KimACL 2020 · 167 次引用
相关 Paper
- RealTalk-CN: A Realistic Chinese Speech Task-Oriented Dialogue Benchmark with Cross-Modal AnalysisEnzhi Wang, Jiaming Zhou, Yuhang Jia, Aobo Kong 等ACL 2026
- RiSAWOZ: A Large-Scale Multi-Domain Wizard-of-Oz Dataset with Rich Semantic Annotations for Task-Oriented Dialogue ModelingJun Quan, Shian Zhang, Qian Cao, Zizhong Li 等EMNLP 2020 · 41 次引用
- TransferTOD: A Generalizable Chinese Multi-Domain Task-Oriented Dialogue System with Transfer CapabilitiesMing Zhang, Caishuang Huang, Yilong Wu, Shichun Liu 等EMNLP 2024
- Novel Slot Detection: A Benchmark for Discovering Unknown Slot Types in the Task-Oriented Dialogue SystemYanan Wu, Zhiyuan Zeng, Keqing He, Hong Xu 等ACL 2021
- Value type: the bridge to a better DST modelQiXiang Gao, Mingyang Sun, Yutao Mou, Chen Zeng 等ACL Findings 2023
