Goal-Oriented Multi-Task BERT-Based Dialogue State Tracker

Dialogue State Tracking (DST) is a core component of virtual assistants such as Alexa or Siri. To accomplish various tasks, these assistants need to support an increasing number of services and APIs. The Schema-Guided State Tracking track of the 8th Dialogue System Technology Challenge highlighted the DST problem for unseen services. The organizers introduced the Schema-Guided Dialogue (SGD) dataset with multi-domain conversations and released a zero-shot dialogue state tracking model. In this work, we propose a GOaL-Oriented Multi-task BERT-based dialogue state tracker (GOLOMB) inspired by architectures for reading comprehension question answering systems. The model "queries" dialogue history with descriptions of slots and services as well as possible values of slots. This allows to transfer slot values in multi-domain dialogues and have a capability to scale to unseen slot types. Our model achieves a joint goal accuracy of 53.97% on the SGD dataset, outperforming the baseline model.

[1]  Mihail Eric,et al.  MultiWOZ 2. , 2019 .

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

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

[4]  Raghav Gupta,et al.  Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Dataset , 2020, AAAI.

[5]  Danna Zhou,et al.  d. , 1934, Microbial pathogenesis.

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

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

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

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

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

[11]  Ido Dagan,et al.  The Negochat Corpus of Human-agent Negotiation Dialogues , 2016, LREC.

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

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

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

[15]  George R. Doddington,et al.  The ATIS Spoken Language Systems Pilot Corpus , 1990, HLT.

[16]  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.

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

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

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

[20]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

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

[22]  Jian Zhang,et al.  SQuAD: 100,000+ Questions for Machine Comprehension of Text , 2016, EMNLP.

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

[24]  Stefan Ultes,et al.  MultiWOZ - A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling , 2018, EMNLP.