Learning End-to-End Goal-Oriented Dialog (2016-05-24T00:00:00.000000Z)

TL;DR

It is shown that an end-to-end dialog system based on Memory Networks can reach promising, yet imperfect, performance and learn to perform non-trivial operations and be compared to a hand-crafted slot-filling baseline on data from the second Dialog State Tracking Challenge.

Abstract

Traditional dialog systems used in goal-oriented applications require a lot of domain-specific handcrafting, which hinders scaling up to new domains. End-to-end dialog systems, in which all components are trained from the dialogs themselves, escape this limitation. But the encouraging success recently obtained in chit-chat dialog may not carry over to goal-oriented settings. This paper proposes a testbed to break down the strengths and shortcomings of end-to-end dialog systems in goal-oriented applications. Set in the context of restaurant reservation, our tasks require manipulating sentences and symbols, so as to properly conduct conversations, issue API calls and use the outputs of such calls. We show that an end-to-end dialog system based on Memory Networks can reach promising, yet imperfect, performance and learn to perform non-trivial operations. We confirm those results by comparing our system to a hand-crafted slot-filling baseline on data from the second Dialog State Tracking Challenge (Henderson et al., 2014a). We show similar result patterns on data extracted from an online concierge service.

Authors

Antoine Bordes

14 papers

J. Weston

26 papers

TL;DR

Abstract

Authors

References36 items

The Fourth Dialog State Tracking Challenge

End-to-End Memory Networks with Knowledge Carryover for Multi-Turn Spoken Language Understanding

On the Evaluation of Dialogue Systems with Next Utterance Classification

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

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

Evaluating Prerequisite Qualities for Learning End-to-End Dialog Systems

Reward Shaping with Recurrent Neural Networks for Speeding up On-Line Policy Learning in Spoken Dialogue Systems

Learning from real users: rating dialogue success with neural networks for reinforcement learning in spoken dialogue systems

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

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

The Ubuntu Dialogue Corpus: A Large Dataset for Research in Unstructured Multi-Turn Dialogue Systems

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

A Neural Conversational Model

End-To-End Memory Networks

Neural Responding Machine for Short-Text Conversation

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

Memory Networks

The Second Dialog State Tracking Challenge

A Dataset for Research on Short-Text Conversations

A Simple and Generic Belief Tracking Mechanism for the Dialog State Tracking Challenge: On the believability of observed information

Efficient Estimation of Word Representations in Vector Space

POMDP-Based Statistical Spoken Dialog Systems: A Review

A survey on metrics for the evaluation of user simulations

Movie-DiC: a Movie Dialogue Corpus for Research and Development

The conference paper

Data-Driven Response Generation in Social Media

Filter, Rank, and Transfer the Knowledge: Learning to Chat

Supervised semantic indexing

An ISU Dialogue System Exhibiting Reinforcement Learning of Dialogue Policies: Generic Slot-Filling in the TALK In-car System

Cobot in LambdaMOO: A Social Statistics Agent

Expanding the Scope of the ATIS Task: The ATIS-3 Corpus

Published as a conference paper at ICLR 2018 S IMULATING A CTION D YNAMICS WITH N EURAL P ROCESS N ETWORKS

2016), we represent each utterance as a bag-of-words and in memory it is represented as a vector using the embedding matrix A, i.e. the memory is an array with entries

Learning Knowledge Graphs for Question Answering through Conversational Dialog

Word-Based Dialog State Tracking with Recurrent Neural Networks

Incremental on-line adaptation of POMDP-based dialogue managers to extended domains

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names