A Knowledge-Grounded Neural Conversation Model (2017-02-07T00:00:00.000000Z)

TL;DR

This paper presents a novel, fully data-driven, and knowledge-grounded neural conversation model aimed at producing more contentful responses, generalizing the widely-used Sequence-to-Sequence (Seq2Seq) approach by conditioning responses on both conversation history and external “facts”, allowing the model to be versatile and applicable in an open-domain setting.

Abstract

Neural network models are capable of generating extremely natural sounding conversational interactions. However, these models have been mostly applied to casual scenarios (e.g., as “chatbots”) and have yet to demonstrate they can serve in more useful conversational applications. This paper presents a novel, fully data-driven, and knowledge-grounded neural conversation model aimed at producing more contentful responses. We generalize the widely-used Sequence-to-Sequence (Seq2Seq) approach by conditioning responses on both conversation history and external “facts”, allowing the model to be versatile and applicable in an open-domain setting. Our approach yields significant improvements over a competitive Seq2Seq baseline. Human judges found that our outputs are significantly more informative.

Authors

Michel Galley

8 papers

Jianfeng Gao

39 papers

Wen-tau Yih

9 papers

TL;DR

Abstract

Authors

References44 items

Visually Grounded Word Embeddings and Richer Visual Features for Improving Multimodal Neural Machine Translation

Generative Encoder-Decoder Models for Task-Oriented Spoken Dialog Systems with Chatting Capability

Learning Symmetric Collaborative Dialogue Agents with Dynamic Knowledge Graph Embeddings

Attention-based Multimodal Neural Machine Translation

Dialog state tracking, a machine reading approach using Memory Network

Incorporating Side Information into Recurrent Neural Network Language Models

Learning End-to-End Goal-Oriented Dialog

How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation

A Persona-Based Neural Conversation Model

Multi-domain Neural Network Language Generation for Spoken Dialogue Systems

A Survey of Available Corpora for Building Data-Driven Dialogue Systems

Multi-task Sequence to Sequence Learning

A Diversity-Promoting Objective Function for Neural Conversation Models

Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems

Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models

Multi-Task Learning for Multiple Language Translation

deltaBLEU: A Discriminative Metric for Generation Tasks with Intrinsically Diverse Targets

A Neural Network Approach to Context-Sensitive Generation of Conversational Responses

A Neural Conversational Model

Representation Learning Using Multi-Task Deep Neural Networks for Semantic Classification and Information Retrieval

End-To-End Memory Networks

Neural Responding Machine for Short-Text Conversation

Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks

Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling

Memory Networks

Sequence to Sequence Learning with Neural Networks

Luke, I am Your Father: Dealing with Out-of-Domain Requests by Using Movies Subtitles

IRIS: a Chat-oriented Dialogue System based on the Vector Space Model

Data-Driven Response Generation in Social Media

Minimum Error Rate Training in Statistical Machine Translation

Example Selection for Bootstrapping Statistical Parsers

Bleu: a Method for Automatic Evaluation of Machine Translation

Trainable approaches to surface natural language generation and their application to conversational dialog systems

Stochastic Language Generation for Spoken Dialogue Systems

Long Short-Term Memory

Multitask Learning

Latent intent dialog models

and Perez

Accurate Evaluation of Segment-level Machine Translation Metrics

Developing Non-goal Dialog System Based on Examples of Drama Television

and Li

Ofﬁcial results of the nist 2008 metrics for machine translation challenge

and Schmidhuber

one purely conversational, where we expose the model without fact encoder to ( S, R )

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names