Data-Efficient Methods for Dialogue Systems

Abstract

Conversational User Interface (CUI) has become ubiquitous in everyday life, in consumer-focused products like Siri and Alexa or business-oriented solutions. Deep learning underlies many recent breakthroughs in dialogue systems but requires very large amounts of training data, often annotated by experts. Trained with smaller data, these methods end up severely lacking robustness (e.g. to disfluencies and out-of-domain input), and often just have too little generalisation power. In this thesis, we address the above issues by introducing a series of methods for training robust dialogue systems from minimal data. Firstly, we study two orthogonal approaches to dialogue: linguistically informed and machine learning-based - from the data efficiency perspective. We outline the steps to obtain data-efficient solutions with either approach. We then introduce two data-efficient models for dialogue response generation: the Dialogue Knowledge Transfer Network based on latent variable dialogue representations, and the hybrid Generative-Retrieval Transformer model (ranked first at the DSTC 8 Fast Domain Adaptation task). Next, we address the problem of robustness given minimal data. As such, propose a multitask LSTM-based model for domain-general disfluency detection. For the problem of out-of-domain input, we present Turn Dropout, a data augmentation technique for anomaly detection only using in-domain data, and introduce autoencoder-augmented models for efficient training with Turn Dropout. Finally, we focus on social dialogue and introduce a neural model for response ranking in social conversation used in Alana, the 3rd place winner in the Amazon Alexa Prize 2017 and 2018. We employ a novel technique of predicting the dialogue length as the main ranking objective and show that this approach improves upon the ratings-based counterpart in terms of data efficiency while matching it in performance.

PhD thesis submitted at Heriot-Watt University. Contains previously published work (see the list in Section 1.4)

References in corpus (18)

• Sequence to Sequence Learning with Neural Networks
• On the Properties of Neural Machine Translation: Encoder-Decoder Approaches
• Optimizing Dialogue Management with Reinforcement Learning: Experiments with the NJFun System
• Chameleons in imagined conversations: A new approach to understanding coordination of linguistic style in dialogs
• TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational Agents
• A Deep Reinforcement Learning Chatbot
• Conversational AI: The Science Behind the Alexa Prize
• Relevance of Unsupervised Metrics in Task-Oriented Dialogue for Evaluating Natural Language Generation
• An Information Retrieval Approach to Short Text Conversation
• Building a Conversational Agent Overnight with Dialogue Self-Play
• Two are Better than One: An Ensemble of Retrieval- and Generation-Based Dialog Systems
• ConvLab: Multi-Domain End-to-End Dialog System Platform
• Toward Continual Learning for Conversational Agents
• An End-to-End Dialogue State Tracking System with Machine Reading Comprehension and Wide & Deep Classification
• RubyStar: A Non-Task-Oriented Mixture Model Dialog System
• A practical approach to dialogue response generation in closed domains
• Contextual Out-of-Domain Utterance Handling With Counterfeit Data Augmentation
• Strongly Incremental Repair Detection