Towards Complex Scenarios: Building End-to-End Task-Oriented Dialogue System across Multiple Knowledge Bases

With the success of the sequence-to-sequence model, end-to-end task-oriented dialogue systems (EToDs) have obtained remarkable progress. However, most existing EToDs are limited to single KB settings where dialogues can be supported by a single KB, which is still far from satisfying the requirements of some complex applications (multi-KBs setting). In this work, we first empirically show that the existing single-KB EToDs fail to work on multi-KB settings that require models to reason across various KBs. To solve this issue, we take the first step to consider the multi-KBs scenario in EToDs and introduce a KB-over-KB Heterogeneous Graph Attention Network (KoK-HAN) to facilitate model to reason over multiple KBs. The core module is a triple-connection graph interaction layer that can model different granularity levels of interaction information across different KBs (i.e., intra-KB connection, inter-KB connection and dialogue-KB connection). Experimental results confirm the superiority of our model for multiple KBs reasoning.

[1]  Jey Han Lau,et al.  An Interpretable Neuro-Symbolic Reasoning Framework for Task-Oriented Dialogue Generation , 2022, ACL.

[2]  Tianwei Zhang,et al.  GNN-LM: Language Modeling based on Global Contexts via GNN , 2021, ICLR.

[3]  Erik Cambria,et al.  Aspect-based sentiment analysis via affective knowledge enhanced graph convolutional networks , 2021, Knowl. Based Syst..

[4]  Hanghang Tong,et al.  Multiplex Graph Neural Network for Extractive Text Summarization , 2021, EMNLP.

[5]  Baolin Peng,et al.  Soloist: Building Task Bots at Scale with Transfer Learning and Machine Teaching , 2021, Transactions of the Association for Computational Linguistics.

[6]  Xiao Xu,et al.  GL-GIN: Fast and Accurate Non-Autoregressive Model for Joint Multiple Intent Detection and Slot Filling , 2021, ACL.

[7]  Wei Peng,et al.  HyKnow: End-to-End Task-Oriented Dialog Modeling with Hybrid Knowledge Management , 2021, FINDINGS.

[8]  Libo Qin,et al.  Co-GAT: A Co-Interactive Graph Attention Network for Joint Dialog Act Recognition and Sentiment Classification , 2020, AAAI.

[9]  Xiaojun Quan,et al.  UBAR: Towards Fully End-to-End Task-Oriented Dialog Systems with GPT-2 , 2020, AAAI.

[10]  Xiaocheng Feng,et al.  Dialogue Discourse-Aware Graph Model and Data Augmentation for Meeting Summarization , 2020, IJCAI.

[11]  Jian Wang,et al.  Dual Dynamic Memory Network for End-to-End Multi-turn Task-oriented Dialog Systems , 2020, COLING.

[12]  Chengming Li,et al.  Amalgamating Knowledge from Two Teachers for Task-oriented Dialogue System with Adversarial Training , 2020, EMNLP.

[13]  Qian Cao,et al.  RiSAWOZ: A Large-Scale Multi-Domain Wizard-of-Oz Dataset with Rich Semantic Annotations for Task-Oriented Dialogue Modeling , 2020, EMNLP.

[14]  C. Bayan Bruss,et al.  DLGNet-Task: An End-to-end Neural Network Framework for Modeling Multi-turn Multi-domain Task-Oriented Dialogue , 2020, ArXiv.

[15]  Rui Zhang,et al.  GraphDialog: Integrating Graph Knowledge into End-to-End Task-Oriented Dialogue Systems , 2020, EMNLP.

[16]  Kee-Eung Kim,et al.  End-to-End Neural Pipeline for Goal-Oriented Dialogue Systems using GPT-2 , 2020, ACL.

[17]  R. Socher,et al.  A Simple Language Model for Task-Oriented Dialogue , 2020, Neural Information Processing Systems.

[18]  Jian Chen,et al.  Fg2seq: Effectively Encoding Knowledge for End-To-End Task-Oriented Dialog , 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[19]  Chongruo Wu,et al.  PRAL: A Tailored Pre-Training Model for Task-Oriented Dialog Generation , 2020, ACL.

[20]  Wanxiang Che,et al.  Dynamic Fusion Network for Multi-Domain End-to-end Task-Oriented Dialog , 2020, ACL.

[21]  Zheng Zhang,et al.  CrossWOZ: A Large-Scale Chinese Cross-Domain Task-Oriented Dialogue Dataset , 2020, Transactions of the Association for Computational Linguistics.

[22]  Pascale Fung,et al.  Attention over Parameters for Dialogue Systems , 2020, ArXiv.

[23]  Houfeng Wang,et al.  Text Level Graph Neural Network for Text Classification , 2019, EMNLP.

[24]  Yangming Li,et al.  Entity-Consistent End-to-end Task-Oriented Dialogue System with KB Retriever , 2019, EMNLP.

[25]  Yangming Li,et al.  A Stack-Propagation Framework with Token-Level Intent Detection for Spoken Language Understanding , 2019, EMNLP.

[26]  Richard Socher,et al.  Global-to-local Memory Pointer Networks for Task-Oriented Dialogue , 2019, ICLR.

[27]  Danish Contractor,et al.  Multi-Level Memory for Task Oriented Dialogs , 2018, NAACL.

[28]  Min-Yen Kan,et al.  Sequicity: Simplifying Task-oriented Dialogue Systems with Single Sequence-to-Sequence Architectures , 2018, ACL.

[29]  Libo Qin,et al.  Sequence-to-Sequence Learning for Task-oriented Dialogue with Dialogue State Representation , 2018, COLING.

[30]  Richard Socher,et al.  Global-Locally Self-Attentive Encoder for Dialogue State Tracking , 2018, ACL.

[31]  Pascale Fung,et al.  Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Oriented Dialog Systems , 2018, ACL.

[32]  Frank Hutter,et al.  Decoupled Weight Decay Regularization , 2017, ICLR.

[33]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[34]  Christopher D. Manning,et al.  Key-Value Retrieval Networks for Task-Oriented Dialogue , 2017, SIGDIAL Conference.

[35]  Christopher D. Manning,et al.  A Copy-Augmented Sequence-to-Sequence Architecture Gives Good Performance on Task-Oriented Dialogue , 2017, EACL.

[36]  Jason Weston,et al.  End-To-End Memory Networks , 2015, NIPS.

[37]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[38]  Milica Gasic,et al.  POMDP-Based Statistical Spoken Dialog Systems: A Review , 2013, Proceedings of the IEEE.

[39]  Salim Roukos,et al.  Bleu: a Method for Automatic Evaluation of Machine Translation , 2002, ACL.

[40]  Phil Cohen,et al.  Dialogue modeling , 1997 .

[41]  Yohan Lee,et al.  Improving End-to-End Task-Oriented Dialog System with A Simple Auxiliary Task , 2021, EMNLP.

[42]  Ondrej Dusek,et al.  AuGPT: Dialogue with Pre-trained Language Models and Data Augmentation , 2021, ArXiv.