ConvLab: Multi-Domain End-to-End Dialog System Platform

Abstract

We present ConvLab, an open-source multi-domain end-to-end dialog system platform, that enables researchers to quickly set up experiments with reusable components and compare a large set of different approaches, ranging from conventional pipeline systems to end-to-end neural models, in common environments. ConvLab offers a set of fully annotated datasets and associated pre-trained reference models. As a showcase, we extend the MultiWOZ dataset with user dialog act annotations to train all component models and demonstrate how ConvLab makes it easy and effortless to conduct complicated experiments in multi-domain end-to-end dialog settings.

References in corpus (5)

• Sequence to Sequence Learning with Neural Networks
• Playing Atari with Deep Reinforcement Learning
• A Network-based End-to-End Trainable Task-oriented Dialogue System
• Composite Task-Completion Dialogue Policy Learning via Hierarchical Deep Reinforcement Learning
• User Modeling for Task Oriented Dialogues

Cited by in corpus (25)

• SOLOIST: Building Task Bots at Scale with Transfer Learning and Machine Teaching
• Task-Oriented Dialogue System as Natural Language Generation
• MultiWOZ 2.2 : A Dialogue Dataset with Additional Annotation Corrections and State Tracking Baselines
• Recent Advances and Challenges in Task-oriented Dialog System
• Task-Oriented Dialog Systems that Consider Multiple Appropriate Responses under the Same Context
• OpenViDial: A Large-Scale, Open-Domain Dialogue Dataset with Visual Contexts
• Guided Dialog Policy Learning without Adversarial Learning in the Loop
• Show Us the Way: Learning to Manage Dialog from Demonstrations
• Meta Dialogue Policy Learning
• OpenViDial 2.0: A Larger-Scale, Open-Domain Dialogue Generation Dataset with Visual Contexts
• Hybrid Generative-Retrieval Transformers for Dialogue Domain Adaptation
• How to Build User Simulators to Train RL-based Dialog Systems
• Rethinking Supervised Learning and Reinforcement Learning in Task-Oriented Dialogue Systems
• NeurIPS 2021 Competition IGLU: Interactive Grounded Language Understanding in a Collaborative Environment
• How to Evaluate Your Dialogue Models: A Review of Approaches
• Robustness Testing of Language Understanding in Task-Oriented Dialog
• Transferable Dialogue Systems and User Simulators
• Resource Constrained Dialog Policy Learning via Differentiable Inductive Logic Programming
• Imperfect also Deserves Reward: Multi-Level and Sequential Reward Modeling for Better Dialog Management
• Multi-Agent Task-Oriented Dialog Policy Learning with Role-Aware Reward Decomposition
• Semi-Supervised Dialogue Policy Learning via Stochastic Reward Estimation
• ADVISER: A Toolkit for Developing Multi-modal, Multi-domain and Socially-engaged Conversational Agents
• Zero-shot Multi-Domain Dialog State Tracking Using Descriptive Rules
• Every time I fire a conversational designer, the performance of the dialog system goes down
• Data-Efficient Methods for Dialogue Systems