Dialogue State Tracking with Incremental Reasoning

Abstract Tracking dialogue states to better interpret user goals and feed downstream policy learning is a bottleneck in dialogue management. Common practice has been to treat it as a problem of classifying dialogue content into a set of pre-defined slot-value pairs, or generating values for different slots given the dialogue history. Both have limitations on considering dependencies that occur on dialogues, and are lacking of reasoning capabilities. This paper proposes to track dialogue states gradually with reasoning over dialogue turns with the help of the back-end data. Empirical results demonstrate that our method outperforms the state-of-the-art methods in terms of joint belief accuracy for MultiWOZ 2.1, a large-scale human--human dialogue dataset across multiple domains.

[1]  Jason Weston,et al.  A unified architecture for natural language processing: deep neural networks with multitask learning , 2008, ICML '08.

[2]  Philip S. Yu,et al.  Find or Classify? Dual Strategy for Slot-Value Predictions on Multi-Domain Dialog State Tracking , 2019, STARSEM.

[3]  Richard Socher,et al.  Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems , 2019, ACL.

[4]  George Kurian,et al.  Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation , 2016, ArXiv.

[5]  Matthew Henderson,et al.  Word-Based Dialog State Tracking with Recurrent Neural Networks , 2014, SIGDIAL Conference.

[6]  Ilya Sutskever,et al.  Language Models are Unsupervised Multitask Learners , 2019 .

[7]  Lu Chen,et al.  The SJTU System for Dialog State Tracking Challenge 2 , 2014, SIGDIAL Conference.

[8]  Alexander J. Smola,et al.  Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning , 2017, ICLR.

[9]  Rajeev Motwani,et al.  The PageRank Citation Ranking : Bringing Order to the Web , 1999, WWW 1999.

[10]  Ian Lane,et al.  BERT-DST: Scalable End-to-End Dialogue State Tracking with Bidirectional Encoder Representations from Transformer , 2019, INTERSPEECH.

[11]  Gyuwan Kim,et al.  Efficient Dialogue State Tracking by Selectively Overwriting Memory , 2020, ACL.

[12]  Jason D. Williams,et al.  Web-style ranking and SLU combination for dialog state tracking , 2014, SIGDIAL Conference.

[13]  Tat-Seng Chua,et al.  Multi-domain Dialogue State Tracking with Recursive Inference , 2021, WWW.

[14]  Lu Chen,et al.  Towards Universal Dialogue State Tracking , 2018, EMNLP.

[15]  Shujian Huang,et al.  Dialogue State Tracking with Explicit Slot Connection Modeling , 2020, ACL.

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

[17]  Tat-Seng Chua,et al.  Neural Multimodal Belief Tracker with Adaptive Attention for Dialogue Systems , 2019, WWW.

[18]  Tat-Seng Chua,et al.  Neural Collaborative Filtering , 2017, WWW.

[19]  Filip Jurcícek,et al.  Incremental LSTM-based dialog state tracker , 2015, 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU).

[20]  David Vandyke,et al.  A Network-based End-to-End Trainable Task-oriented Dialogue System , 2016, EACL.

[21]  Maxine Eskénazi,et al.  Recipe For Building Robust Spoken Dialog State Trackers: Dialog State Tracking Challenge System Description , 2013, SIGDIAL Conference.

[22]  Ehsan Hosseini-Asl,et al.  Toward Scalable Neural Dialogue State Tracking Model , 2018, ArXiv.

[23]  Chi Wang,et al.  Schema-Guided Multi-Domain Dialogue State Tracking with Graph Attention Neural Networks , 2020, AAAI.

[24]  Jianmo Ni,et al.  Scalable and Accurate Dialogue State Tracking via Hierarchical Sequence Generation , 2019, EMNLP.

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

[26]  Michael I. Jordan,et al.  Loopy Belief Propagation for Approximate Inference: An Empirical Study , 1999, UAI.

[27]  Dilek Z. Hakkani-Tür,et al.  MultiWOZ 2.1: Multi-Domain Dialogue State Corrections and State Tracking Baselines , 2019, ArXiv.

[28]  Jie Zhou,et al.  A Contextual Hierarchical Attention Network with Adaptive Objective for Dialogue State Tracking , 2020, ACL.

[29]  Wenhan Xiong,et al.  DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning , 2017, EMNLP.

[30]  Lu Chen,et al.  A generalized rule based tracker for dialogue state tracking , 2014, 2014 IEEE Spoken Language Technology Workshop (SLT).

[31]  Richard Socher,et al.  A Simple Language Model for Task-Oriented Dialogue , 2020, NeurIPS.

[32]  Matthew Henderson,et al.  The Second Dialog State Tracking Challenge , 2014, SIGDIAL Conference.

[33]  Fei Liu,et al.  Dialog state tracking, a machine reading approach using Memory Network , 2016, EACL.

[34]  Nurul Lubis,et al.  TripPy: A Triple Copy Strategy for Value Independent Neural Dialog State Tracking , 2020, SIGdial.

[35]  Oliver Lemon,et al.  A Simple and Generic Belief Tracking Mechanism for the Dialog State Tracking Challenge: On the believability of observed information , 2013, SIGDIAL Conference.

[36]  Lu Chen,et al.  Cost-Sensitive Active Learning for Dialogue State Tracking , 2018, SIGDIAL Conference.

[37]  Dilek Z. Hakkani-Tür,et al.  Dialog State Tracking: A Neural Reading Comprehension Approach , 2019, SIGdial.

[38]  Steve J. Young,et al.  Bayesian update of dialogue state: A POMDP framework for spoken dialogue systems , 2010, Comput. Speech Lang..

[39]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[40]  Dilek Z. Hakkani-Tür,et al.  Scalable multi-domain dialogue state tracking , 2017, 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).

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

[42]  Pawel Budzianowski,et al.  Large-Scale Multi-Domain Belief Tracking with Knowledge Sharing , 2018, ACL.

[43]  Steve J. Young,et al.  Partially observable Markov decision processes for spoken dialog systems , 2007, Comput. Speech Lang..

[44]  Dilek Z. Hakkani-Tür,et al.  HyST: A Hybrid Approach for Flexible and Accurate Dialogue State Tracking , 2019, INTERSPEECH.

[45]  Tat-Seng Chua,et al.  Knowledge-aware Multimodal Dialogue Systems , 2018, ACM Multimedia.

[46]  Tsung-Hsien Wen,et al.  Neural Belief Tracker: Data-Driven Dialogue State Tracking , 2016, ACL.

[47]  Richard Socher,et al.  Learned in Translation: Contextualized Word Vectors , 2017, NIPS.

[48]  Qi Hu,et al.  An End-to-end Approach for Handling Unknown Slot Values in Dialogue State Tracking , 2018, ACL.