HyKnow: End-to-End Task-Oriented Dialog Modeling with Hybrid Knowledge Management

Task-oriented dialog (TOD) systems typically manage structured knowledge (e.g. ontologies and databases) to guide the goal-oriented conversations. However, they fall short of handling dialog turns grounded on unstructured knowledge (e.g. reviews and documents). In this paper, we formulate a task of modeling TOD grounded on both structured and unstructured knowledge. To address this task, we propose a TOD system with hybrid knowledge management, HyKnow. It extends the belief state to manage both structured and unstructured knowledge, and is the first end-to-end model that jointly optimizes dialog modeling grounded on these two kinds of knowledge. We conduct experiments on the modified version of MultiWOZ 2.1 dataset, where dialogs are grounded on hybrid knowledge. Experimental results show that HyKnow has strong end-to-end performance compared to existing TOD systems. It also outperforms the pipeline knowledge management schemes, with higher unstructured knowledge retrieval accuracy.

[1]  Alon Lavie,et al.  METEOR: An Automatic Metric for MT Evaluation with Improved Correlation with Human Judgments , 2005, IEEvaluation@ACL.

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

[3]  Maxine Eskénazi,et al.  Generative Encoder-Decoder Models for Task-Oriented Spoken Dialog Systems with Chatting Capability , 2017, SIGDIAL Conference.

[4]  Nobuhiro Kaji,et al.  Chat Detection in an Intelligent Assistant: Combining Task-oriented and Non-task-oriented Spoken Dialogue Systems , 2017, ACL.

[5]  Zhijian Ou,et al.  Task-Oriented Dialog Systems that Consider Multiple Appropriate Responses under the Same Context , 2019, AAAI.

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

[7]  Doyen Sahoo,et al.  UniConv: A Unified Conversational Neural Architecture for Multi-domain Task-oriented Dialogues , 2020, EMNLP.

[8]  Antoine Raux,et al.  The Dialog State Tracking Challenge , 2013, SIGDIAL Conference.

[9]  Dilek Z. Hakkani-Tür,et al.  Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Access , 2020, SIGDIAL.

[10]  Jianfeng Gao,et al.  Multi-Domain Task-Completion Dialog Challenge , 2019 .

[11]  Jeffrey Pennington,et al.  GloVe: Global Vectors for Word Representation , 2014, EMNLP.

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

[13]  Christopher D. Manning,et al.  Introduction to Information Retrieval , 2010, J. Assoc. Inf. Sci. Technol..

[14]  Zhijian Ou,et al.  A Probabilistic End-To-End Task-Oriented Dialog Model with Latent Belief States towards Semi-Supervised Learning , 2020, EMNLP.

[15]  Luyao Chen,et al.  CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databases , 2019, EMNLP.

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

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

[18]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

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

[20]  Hugo Zaragoza,et al.  The Probabilistic Relevance Framework: BM25 and Beyond , 2009, Found. Trends Inf. Retr..

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

[22]  Maxine Eskénazi,et al.  Structured Fusion Networks for Dialog , 2019, SIGdial.

[23]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[24]  Luis A. Lastras,et al.  Doc2Dial: A Goal-Oriented Document-Grounded Dialogue Dataset , 2020, EMNLP.

[25]  Alexander I. Rudnicky,et al.  Learning Conversational Systems that Interleave Task and Non-Task Content , 2017, IJCAI.

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

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

[28]  Chin-Yew Lin,et al.  ROUGE: A Package for Automatic Evaluation of Summaries , 2004, ACL 2004.

[29]  Hang Li,et al.  “ Tony ” DNN Embedding for “ Tony ” Selective Read for “ Tony ” ( a ) Attention-based Encoder-Decoder ( RNNSearch ) ( c ) State Update s 4 SourceVocabulary Softmax Prob , 2016 .

[30]  Zhou Yu,et al.  MOSS: End-to-End Dialog System Framework with Modular Supervision , 2019, AAAI.

[31]  Jianfeng Gao,et al.  SOLOIST: Few-shot Task-Oriented Dialog with A Single Pre-trained Auto-regressive Model , 2020, ArXiv.

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

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

[34]  Hannes Schulz,et al.  Frames: a corpus for adding memory to goal-oriented dialogue systems , 2017, SIGDIAL Conference.

[35]  Tat-Seng Chua,et al.  Deep Conversational Recommender in Travel , 2019, ArXiv.

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