End-to-End Learning of Flowchart Grounded Task-Oriented Dialogs

We propose a novel problem within end-toend learning of task oriented dialogs (TOD), in which the dialog system mimics a troubleshooting agent who helps a user by diagnosing their problem (e.g., car not starting). Such dialogs are grounded in domain-specific flowcharts, which the agent is supposed to follow during the conversation. Our task exposes novel technical challenges for neural TOD, such as grounding an utterance to the flowchart without explicit annotation, referring to additional manual pages when user asks a clarification question, and ability to follow unseen flowcharts at test time. We release a dataset (FLODIAL) consisting of 2,738 dialogs grounded on 12 different troubleshooting flowcharts. We also design a neural model, FLONET, which uses a retrieval-augmented generation architecture to train the dialog agent. Our experiments find that FLONET can do zero-shot transfer to unseen flowcharts, and sets a strong baseline for future research.

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

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

[3]  Yejin Choi,et al.  The Curious Case of Neural Text Degeneration , 2019, ICLR.

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

[5]  Natalia Gimelshein,et al.  PyTorch: An Imperative Style, High-Performance Deep Learning Library , 2019, NeurIPS.

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

[7]  Guillaume Bouchard,et al.  Interpretation of Natural Language Rules in Conversational Machine Reading , 2018, EMNLP.

[8]  Thomas Wolf,et al.  TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational Agents , 2019, ArXiv.

[9]  David Vandyke,et al.  Conditional Generation and Snapshot Learning in Neural Dialogue Systems , 2016, EMNLP.

[10]  Yann LeCun,et al.  Dimensionality Reduction by Learning an Invariant Mapping , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[11]  Danish Contractor,et al.  2019 Formatting Instructions for Authors Using LaTeX , 2018 .

[12]  Walter S. Lasecki,et al.  Understanding Task Design Trade-offs in Crowdsourced Paraphrase Collection , 2017, ACL.

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

[14]  Fabio Petroni,et al.  Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks , 2020, NeurIPS.

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

[16]  Jianfeng Gao,et al.  DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation , 2020, ACL.

[17]  Ming-Wei Chang,et al.  REALM: Retrieval-Augmented Language Model Pre-Training , 2020, ICML.

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

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

[20]  Boualem Benatallah,et al.  A Study of Incorrect Paraphrases in Crowdsourced User Utterances , 2019, NAACL.

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

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

[23]  Jason Weston,et al.  Learning End-to-End Goal-Oriented Dialog , 2016, ICLR.

[24]  R. Likert.  “Technique for the Measurement of Attitudes, A” , 2022, The SAGE Encyclopedia of Research Design.

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

[26]  J. F. Kelley,et al.  An iterative design methodology for user-friendly natural language office information applications , 1984, TOIS.

[27]  Joelle Pineau,et al.  Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models , 2015, AAAI.

[28]  Gökhan Tür,et al.  Building a Conversational Agent Overnight with Dialogue Self-Play , 2018, ArXiv.

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

[30]  Jakob Grue Simonsen,et al.  A Hierarchical Recurrent Encoder-Decoder for Generative Context-Aware Query Suggestion , 2015, CIKM.

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

[32]  Quoc V. Le,et al.  A Neural Conversational Model , 2015, ArXiv.

[33]  Bill Byrne,et al.  Taskmaster-1: Toward a Realistic and Diverse Dialog Dataset , 2019, EMNLP.

[34]  Mausam,et al.  Constraint based Knowledge Base Distillation in End-to-End Task Oriented Dialogs , 2021, FINDINGS.

[35]  Beth Ann Hockey,et al.  Yes/No Questions and Answers in the Map Task Corpus , 1997 .

[36]  Maxine Eskénazi,et al.  Zero-Shot Dialog Generation with Cross-Domain Latent Actions , 2018, SIGDIAL Conference.

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

[38]  Nikhil Gupta,et al.  Disentangling Language and Knowledge in Task-Oriented Dialogs , 2018, NAACL.