natural-language-processing-7

Dialogue Management

3260 papers • 126 benchmarks • 313 datasets

( Image credit: Bocklisch et al. )

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in dialogue-management-14

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find dialogue-management-14 models and implementations

Datasets

DialoGLUE

Subtasks

No subtasks available.

Most implemented papers

Rethinking Action Spaces for Reinforcement Learning in End-to-end Dialog Agents with Latent Variable Models

M. Eskénazi, Tiancheng Zhao, Kaige Xie•Thu Jan 31 2019

A novel latent action framework that treats the action spaces of an end-to-end dialog agent as latent variables and develops unsupervised methods in order to induce its own action space from the data is proposed.

143

Content

0

Paper Graph

End-to-end optimization of goal-driven and visually grounded dialogue systems

Aaron C. Courville, Bilal Piot, O. Pietquin, H. D. Vries, Florian Strub, Jérémie Mary•Tue Mar 14 2017

This paper introduces a Deep Reinforcement Learning method to optimize visually grounded task-oriented dialogues, based on the policy gradient algorithm, which provides encouraging results at solving both the problem of generating natural dialogues and the task of discovering a specific object in a complex picture.

141 0

Paper Graph

Strategic Dialogue Management via Deep Reinforcement Learning

H. Cuayáhuitl, Oliver Lemon, Simon Keizer•Tue Nov 24 2015

A successful application of Deep Reinforcement Learning with a high-dimensional state space to the strategic board game of Settlers of Catan is described, which supports the claim that DRL is a promising framework for training dialogue systems, and strategic agents with negotiation abilities.

94 0

Paper Graph

Evaluating Natural Language Understanding Services for Conversational Question Answering Systems

Daniel Braun, F. Matthes, Adrian Hernandez-Mendez, Manfred Langen•Mon Jul 31 2017

This paper presents a method to evaluate the classification performance of NLU services, and presents two new corpora, one consisting of annotated questions with the corresponding answers, to enable both, researchers and companies to make more educated decisions about which service they should use.

191 0

Paper Graph

Rasa: Open Source Language Understanding and Dialogue Management

Tom Bocklisch, Joe Faulkner, Nick Pawlowski, Alan Nichol•Wed Dec 13 2017

A pair of tools, Rasa NLU and Rasa Core, which are open source python libraries for building conversational software, are introduced to make machine-learning based dialogue management and language understanding accessible to non-specialist software developers.

470 0

Paper Graph

An Ontology-Based Dialogue Management System for Banking and Finance Dialogue Systems

Duygu Altinok•Thu Apr 12 2018

An ontology-based dialogue manage (OntoDM) is introduced, a dialogue manager that keeps the state of the conversation, provides a basis for anaphora resolution and drives the conversation via domain ontologies.

45 0

Paper Graph

Towards Learning Transferable Conversational Skills using Multi-dimensional Dialogue Modelling

Verena Rieser, Simon Keizer•Fri Mar 30 2018

This paper presents a multi-dimensional, statistical dialogue management framework, in which transferable conversational skills can be learnt by separating out domain-independent dimensions of communication and using multi-agent reinforcement learning.

9 0

Paper Graph

MultiWOZ - A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling

Tsung-Hsien Wen, Paweł Budzianowski, Bo-Hsiang Tseng, I. Casanueva, Stefan Ultes, Osman Ramadan, Milica Gasic•Fri Aug 31 2018

The Multi-Domain Wizard-of-Oz dataset (MultiWOZ), a fully-labeled collection of human-human written conversations spanning over multiple domains and topics is introduced, at a size of 10k dialogues, at least one order of magnitude larger than all previous annotated task-oriented corpora.

1429 0

Paper Graph

Fully Statistical Neural Belief Tracking

N. Mrksic, Ivan Vulic•Mon May 28 2018

An improvement to the existing data-driven Neural Belief Tracking framework for Dialogue State Tracking, which shows that dialogue dynamics can be modelled with a very small number of additional model parameters and provides a robust framework for building resource-light DST models.

28 0

Paper Graph

Adding a benchmark result helps the community track progress.