Lune

ACL Findings2023

Domain-specific Attention with Distributional Signatures for Multi-Domain End-to-end Task-Oriented Dialogue

Xing Ma, Peng Zhang, Feifei Zhao

Abstract

The end-to-end task-oriented dialogue system has achieved great success in recent years. Most of these dialogue systems need to accommodate multi-domain dialogue in real-world scenarios. However, due to the high cost of dialogue data annotation and the scarcity of labeled dialogue data, existing methods are difficult to extend to new domains. Therefore, it is essential to use limited data to construct multi-domain dialogue systems. To solve this problem, we propose a novel domain attention module. It uses distributional signatures to construct a multi-domain dialogue system effectively with limited data, which has strong extensibility. We also define an adjacent n-gram pattern to explore potential patterns for dialogue entities. Experimental results show that our approach outperforms the baseline models on most metrics. In the few-shot scenario, we show our method gets a great improvement compared with previous methods while keeping a smaller model scale.

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.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models cites Dynamic Fusion Network for Multi-Domain End-to-end Task-Oriented Dialog
  • Constraint based Knowledge Base Distillation in End-to-End Task Oriented Dialogs cites Dynamic Fusion Network for Multi-Domain End-to-end Task-Oriented Dialog
  • Exploring Auxiliary Reasoning Tasks for Task-oriented Dialog Systems with Meta Cooperative Learning cites Dynamic Fusion Network for Multi-Domain End-to-end Task-Oriented Dialog
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on5

  1. UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language ModelsTianbao Xie, Chen Henry Wu, Peng Shi, Ruiqi Zhong et al.EMNLP 2022 · 222 citations
  2. Few-shot Text Classification with Distributional SignaturesYujia Bao, Menghua Wu, Shiyu Chang, Regina BarzilayICLR 2020 · 183 citations
  3. Dynamic Fusion Network for Multi-Domain End-to-end Task-Oriented DialogLibo Qin, Xiao Xu, Wanxiang Che, Yue Zhang et al.ACL 2020 · 90 citations
  4. Constraint based Knowledge Base Distillation in End-to-End Task Oriented DialogsDinesh Raghu, Atishya Jain, Mausam, Sachindra JoshiACL Findings 2021 · 21 citations
  5. Exploring Auxiliary Reasoning Tasks for Task-oriented Dialog Systems with Meta Cooperative LearningBowen Qin, Min Yang, Lidong Bing, Qingshan Jiang et al.AAAI 2021 · 9 citations

Related papers

  1. Discovering Dialogue Slots with Weak SupervisionVojtech Hudecek, Ondrej Dusek, Zhou YuACL 2021
  2. TOD-BERT: Pre-trained Natural Language Understanding for Task-Oriented DialogueChien-Sheng Wu, Steven C. H. Hoi, Richard Socher, Caiming XiongEMNLP 2020 · 210 citations
  3. Learning to Match Representations is Better for End-to-End Task-Oriented Dialog SystemWanshi Xu, Xuxin Cheng, Zhihong Zhu, Zhanpeng Chen et al.EMNLP Findings 2024
  4. Multijugate Dual Learning for Low-Resource Task-Oriented Dialogue SystemShimin Li, Xiaotian Zhang, Yanjun Zheng, Linyang Li et al.ACL Findings 2023 · 3 citations
  5. Few-shot Natural Language Generation for Task-Oriented DialogBaolin Peng, Chenguang Zhu, Chunyuan Li, Xiujun Li et al.EMNLP Findings 2020 · 164 citations
Dusk over the sea between two cliffs drawn in fine vertical lines