Teaching Machines to Converse

Abstract

The ability of a machine to communicate with humans has long been associated with the general success of AI. This dates back to Alan Turing's epoch-making work in the early 1950s, which proposes that a machine's intelligence can be tested by how well it, the machine, can fool a human into believing that the machine is a human through dialogue conversations. Many systems learn generation rules from a minimal set of authored rules or labels on top of hand-coded rules or templates, and thus are both expensive and difficult to extend to open-domain scenarios. Recently, the emergence of neural network models the potential to solve many of the problems in dialogue learning that earlier systems cannot tackle: the end-to-end neural frameworks offer the promise of scalability and language-independence, together with the ability to track the dialogue state and then mapping between states and dialogue actions in a way not possible with conventional systems. On the other hand, neural systems bring about new challenges: they tend to output dull and generic responses; they lack a consistent or a coherent persona; they are usually optimized through single-turn conversations and are incapable of handling the long-term success of a conversation; and they are not able to take the advantage of the interactions with humans. This dissertation attempts to tackle these challenges: Contributions are two-fold: (1) we address new challenges presented by neural network models in open-domain dialogue generation systems; (2) we develop interactive question-answering dialogue systems by (a) giving the agent the ability to ask questions and (b) training a conversation agent through interactions with humans in an online fashion, where a bot improves through communicating with humans and learning from the mistakes that it makes.

phd thesis

References in corpus (42)

• Sequence to Sequence Learning with Neural Networks
• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
• Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
• Playing Atari with Deep Reinforcement Learning
• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
• Recurrent Neural Network Regularization
• Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
• Pixel Recurrent Neural Networks
• A Neural Conversational Model
• Dialogue Act Modeling for Automatic Tagging and Recognition of Conversational Speech
• Character-Aware Neural Language Models
• Recurrent Models of Visual Attention
• Sequence Level Training with Recurrent Neural Networks
• An Empirical Study of Smoothing Techniques for Language Modeling
• Large-scale Simple Question Answering with Memory Networks
• End-to-end Continuous Speech Recognition using Attention-based Recurrent NN: First Results
• Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond
• A Fast and Simple Algorithm for Training Neural Probabilistic Language Models
• Grid Long Short-Term Memory
• A Simple, Fast Diverse Decoding Algorithm for Neural Generation
• Image-Grounded Conversations: Multimodal Context for Natural Question and Response Generation
• Sequence-to-Sequence Learning as Beam-Search Optimization
• Get To The Point: Summarization with Pointer-Generator Networks
• Sequence-Level Knowledge Distillation
• Addressing the Rare Word Problem in Neural Machine Translation
• Continuously Learning Neural Dialogue Management
• Efficient Summarization with Read-Again and Copy Mechanism
• On-line Active Reward Learning for Policy Optimisation in Spoken Dialogue Systems
• Learning through Dialogue Interactions by Asking Questions
• Multiresolution Recurrent Neural Networks: An Application to Dialogue Response Generation
• Massive Exploration of Neural Machine Translation Architectures
• Generative Deep Neural Networks for Dialogue: A Short Review
• Adversarial Evaluation of Dialogue Models
• Conversational Contextual Cues: The Case of Personalization and History for Response Ranking
• Learning from Real Users: Rating Dialogue Success with Neural Networks for Reinforcement Learning in Spoken Dialogue Systems
• Learning to Decode for Future Success
• Dialogue Learning With Human-In-The-Loop
• Latent Intention Dialogue Models
• Data Recombination for Neural Semantic Parsing
• Tracking Initiative in Collaborative Dialogue Interactions
• Conditional Generation and Snapshot Learning in Neural Dialogue Systems

Cited by in corpus (4)

• OpenViDial: A Large-Scale, Open-Domain Dialogue Dataset with Visual Contexts
• Modeling Text-visual Mutual Dependency for Multi-modal Dialog Generation
• Defending Against Backdoor Attacks in Natural Language Generation
• OpenViDial 2.0: A Larger-Scale, Open-Domain Dialogue Generation Dataset with Visual Contexts