ACL Findings2021
Constraint based Knowledge Base Distillation in End-to-End Task Oriented Dialogs
Dinesh Raghu, Atishya Jain, Mausam, Sachindra Joshi
Abstract
End-to-End task-oriented dialogue systems generate responses based on dialog history and an accompanying knowledge base (KB). Inferring those KB entities that are most relevant for an utterance is crucial for response generation. Existing state of the art scales to large KBs by softly filtering over irrelevant KB information. In this paper, we propose a novel filtering technique that consists of (1) a pairwise similarity based filter that identifies relevant information by respecting the n-ary structure in a KB record. and, (2) an auxiliary loss that helps in separating contextually unrelated KB information. We also propose a new metric -multiset entity F1 which fixes a correctness issue in the existing entity F1 metric. Experimental results on three publicly available task-oriented dialog datasets show that our proposed approach outperforms existing state-ofthe-art models.
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.
11 top-tier papers have 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
- End-to-end Task-oriented Dialogue: A Survey of Tasks, Methods, and Future Directions cites Q-TOD: A Query-driven Task-oriented Dialogue System
- End-to-end Task-oriented Dialogue: A Survey of Tasks, Methods, and Future Directions cites Multi-Grained Knowledge Retrieval for End-to-End Task-Oriented Dialog
- End-to-end Task-oriented Dialogue: A Survey of Tasks, Methods, and Future Directions cites Dynamic Fusion Network for Multi-Domain End-to-end Task-Oriented Dialog
- End-to-end Task-oriented Dialogue: A Survey of Tasks, Methods, and Future Directions cites Amalgamating Knowledge from Two Teachers for Task-oriented Dialogue System with Adversarial Training
- Q-TOD: A Query-driven Task-oriented Dialogue System cites Dynamic Fusion Network for Multi-Domain End-to-end Task-Oriented Dialog
- Multi-Grained Knowledge Retrieval for End-to-End Task-Oriented Dialog cites Dynamic Fusion Network for Multi-Domain End-to-end Task-Oriented Dialog
- UniTranSeR: A Unified Transformer Semantic Representation Framework for Multimodal Task-Oriented Dialog System cites Dynamic Fusion Network for Multi-Domain End-to-end Task-Oriented Dialog
Cited by top-tier papers11
- UniTranSeR: A Unified Transformer Semantic Representation Framework for Multimodal Task-Oriented Dialog SystemZhiyuan Ma, Jianjun Li, Guohui Li, Yongjing ChengACL 2022 · 29 citations
- Multi-Grained Knowledge Retrieval for End-to-End Task-Oriented DialogFanqi Wan, Weizhou Shen, Ke Yang, Xiaojun Quan et al.ACL 2023 · 14 citations
- Q-TOD: A Query-driven Task-oriented Dialogue SystemXin Tian, Yingzhan Lin, Mengfei Song, Siqi Bao et al.EMNLP 2022 · 13 citations
- End-to-End Learning of Flowchart Grounded Task-Oriented DialogsDinesh Raghu, Shantanu Agarwal, Sachindra Joshi, MausamEMNLP 2021 · 12 citations
- End-to-end Task-oriented Dialogue: A Survey of Tasks, Methods, and Future DirectionsLibo Qin, Wenbo Pan, Qiguang Chen, Lizi Liao et al.EMNLP 2023 · 12 citations
Builds on2
- 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
- Amalgamating Knowledge from Two Teachers for Task-oriented Dialogue System with Adversarial TrainingWanwei He, Min Yang, Rui Yan, Chengming Li et al.EMNLP 2020 · 22 citations
Related papers
- 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
- From Retrieval to Generation: A Simple and Unified Generative Model for End-to-End Task-Oriented DialogueZeyuan Ding, Zhihao Yang, Ling Luo, Yuanyuan Sun et al.AAAI 2024 · 6 citations
- GraphDialog: Integrating Graph Knowledge into End-to-End Task-Oriented Dialogue SystemsShiquan Yang, Rui Zhang, Sarah M. ErfaniEMNLP 2020 · 46 citations
- Contextualize Knowledge Bases with Transformer for End-to-end Task-Oriented Dialogue SystemsYanjie Gou, Yinjie Lei, Lingqiao Liu, Yong Dai et al.EMNLP 2021 · 11 citations
- Topic-Aware Response Generation in Task-Oriented Dialogue with Unstructured Knowledge AccessYue Feng, Gerasimos Lampouras, Ignacio IacobacciEMNLP Findings 2022 · 6 citations
