End-to-End Task-Completion Neural Dialogue Systems
نویسندگان
چکیده
This paper presents an end-to-end learning framework for task-completion neural dialogue systems, which leverages supervised and reinforcement learning with various deep-learning models. The system is able to interface with a structured database, and interact with users for assisting them to access information and complete tasks such as booking movie tickets. Our experiments in a movie-ticket booking domain show the proposed system outperforms a modular-based dialogue system and is more robust to noise produced by other components in the system.
منابع مشابه
How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation
We investigate evaluation metrics for endto-end dialogue systems where supervised labels, such as task completion, are not available. Recent works in end-to-end dialogue systems have adopted metrics from machine translation and text summarization to compare a model’s generated response to a single target response. We show that these metrics correlate very weakly or not at all with human judgeme...
متن کاملBuilding End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models
We investigate the task of building open domain, conversational dialogue systems based on large dialogue corpora using generative models. Generative models produce system responses that are autonomously generated word-by-word, opening up the possibility for realistic, flexible interactions. In support of this goal, we extend the recently proposed hierarchical recurrent encoder-decoder neural ne...
متن کاملEnd-to-End Optimization of Task-Oriented Dialogue Model with Deep Reinforcement Learning
In this paper, we present a neural network based task-oriented dialogue system that can be optimized end-to-end with deep reinforcement learning (RL). The system is able to track dialogue state, interface with knowledge bases, and incorporate query results into agent’s responses to successfully complete task-oriented dialogues. dialogue policy learning is conducted with a hybrid supervised and ...
متن کاملA Network-based End-to-End Trainable Task-oriented Dialogue System
Teaching machines to accomplish tasks by conversing naturally with humans is challenging. Currently, developing taskoriented dialogue systems requires creating multiple components and typically this involves either a large amount of handcrafting, or acquiring costly labelled datasets to solve a statistical learning problem for each component. In this work we introduce a neural network-based tex...
متن کاملKey-Value Retrieval Networks for Task-Oriented Dialogue
Neural task-oriented dialogue systems often struggle to smoothly interface with a knowledge base. In this work, we seek to address this problem by proposing a new neural dialogue agent that is able to effectively sustain grounded, multi-domain discourse through a novel key-value retrieval mechanism. The model is end-to-end differentiable and does not need to explicitly model dialogue state or b...
متن کامل