Dialogue Management
24 papers with code • 0 benchmarks • 1 datasets
( Image credit: Bocklisch et al. )
Benchmarks
These leaderboards are used to track progress in Dialogue Management
DialoGLUE
Most implemented papers
Rethinking Action Spaces for Reinforcement Learning in End-to-end Dialog Agents with Latent Variable Models
snakeztc/NeuralDialog-LaRL
•
•
NAACL 2019
Defining action spaces for conversational agents and optimizing their decision-making process with reinforcement learning is an enduring challenge.
End-to-end optimization of goal-driven and visually grounded dialogue systems
End-to-end design of dialogue systems has recently become a popular research topic thanks to powerful tools such as encoder-decoder architectures for sequence-to-sequence learning.
Conversation Graph: Data Augmentation, Training and Evaluation for Non-Deterministic Dialogue Management
We propose the Conversation Graph (ConvGraph), a graph-based representation of dialogues that can be exploited for data augmentation, multi-reference training and evaluation of non-deterministic agents.
Strategic Dialogue Management via Deep Reinforcement Learning
This paper describes a successful application of Deep Reinforcement Learning (DRL) for training intelligent agents with strategic conversational skills, in a situated dialogue setting.
Evaluating Natural Language Understanding Services for Conversational Question Answering Systems
Conversational interfaces recently gained a lot of attention.
Rasa: Open Source Language Understanding and Dialogue Management
We introduce a pair of tools, Rasa NLU and Rasa Core, which are open source python libraries for building conversational software.
Towards Learning Transferable Conversational Skills using Multi-dimensional Dialogue Modelling
Recent statistical approaches have improved the robustness and scalability of spoken dialogue systems.
An Ontology-Based Dialogue Management System for Banking and Finance Dialogue Systems
We introduce an ontology-based dialogue manage(OntoDM), a dialogue manager that keeps the state of the conversation, provides a basis for anaphora resolution and drives the conversation via domain ontologies.
Fully Statistical Neural Belief Tracking
nmrksic/neural-belief-tracker
•
•
ACL 2018
This paper proposes an improvement to the existing data-driven Neural Belief Tracking (NBT) framework for Dialogue State Tracking (DST).
MultiWOZ - A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling
budzianowski/multiwoz
•
•
EMNLP 2018
Even though machine learning has become the major scene in dialogue research community, the real breakthrough has been blocked by the scale of data available. To address this fundamental obstacle, we introduce the Multi-Domain Wizard-of-Oz dataset (MultiWOZ), a fully-labeled collection of human-human written conversations spanning over multiple domains and topics. At a size of 10k dialogues, it is at least one order of magnitude larger than all previous annotated task-oriented corpora. The contribution of this work apart from the open-sourced dataset is two-fold:firstly, a detailed description of the data collection procedure along with a summary of data structure and analysis is provided.
