natural-language-processing-7

End-To-End Dialogue Modelling

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in end-to-end-dialogue-modelling-14

Trend

Dataset

Best Model

Actions

MULTIWOZ 2.0

MULTIWOZ 2.1

Libraries

i

Use these libraries to find end-to-end-dialogue-modelling-14 models and implementations

Datasets

MultiWOZ

BiToD

Arabic-ToD

Subtasks

No subtasks available.

Most implemented papers

Task-Oriented Dialog Systems that Consider Multiple Appropriate Responses under the Same Context

Zhou Yu, Zhijian Ou, Yichi Zhang•Sat Nov 23 2019

A Multi-Action Data Augmentation (MADA) framework to utilize the one-to-many property to generate diverse appropriate dialog responses, which consistently improves dialog policy diversity, and results in improved response diversity and appropriateness.

191

Content

0

Paper Graph

Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System

Yixuan Su, Elman Mansimov, Lei Shu, Deng Cai, Yi Zhang, Arshit Gupta, Yi-An Lai•Tue Sep 28 2021

This study presents PPTOD, a unified plug-and-play model for task-oriented dialogue, and introduces a new dialogue multi-task pre-training strategy that allows the model to learn the primary TOD task completion skills from heterogeneous dialog corpora.

210 0

Paper Graph

A Simple Language Model for Task-Oriented Dialogue

R. Socher, Chien-Sheng Wu, Semih Yavuz, Bryan McCann, Ehsan Hosseini-Asl•Fri May 01 2020

SimpleTOD is a simple approach to task-oriented dialogue that uses a single causal language model trained on all sub-tasks recast as a single sequence prediction problem, which allows it to fully leverage transfer learning from pre-trained, open domain, causal language models such as GPT-2.

558 0

Paper Graph

Soloist: Building Task Bots at Scale with Transfer Learning and Machine Teaching

Jianfeng Gao, Chunyuan Li, Jinchao Li, Baolin Peng, Shahin Shayandeh, Lars Lidén•Sat Jul 31 2021

A new method that uses transfer learning and machine teaching to build task bots at scale, Soloist, is presented, which parameterize classical modular task-oriented dialog systems using a Transformer-based auto-regressive language model, which subsumes different dialog modules into a single neural model.

216 0

Paper Graph

Maintaining Common Ground in Dynamic Environments

Takuma Udagawa, Akiko Aizawa•Fri May 28 2021

This work proposes a novel task setting to study the ability of both creating and maintaining common ground in dynamic environments, and collects a large-scale dataset of 5,617 dialogues to enable fine-grained evaluation and analysis of various dialogue systems.

15 0

Paper Graph

A Probabilistic End-To-End Task-Oriented Dialog Model with Latent Belief States towards Semi-Supervised Learning

Zhijian Ou, Yichi Zhang, Junlan Feng, Huixin Wang•Wed Sep 16 2020

This paper proposes a probabilistic dialog model, called the LAtent BElief State (LABES) model, where belief states are represented as discrete latent variables and jointly modeled with system responses given user inputs to develop semi-supervised learning under the principled variational learning framework.

70 0

Paper Graph

AuGPT: Auxiliary Tasks and Data Augmentation for End-To-End Dialogue with Pre-Trained Language Models

Ondrej Dusek, Jon'avs Kulh'anek, Vojtvech Hudevcek, Tom'avs Nekvinda•Mon Feb 08 2021

This work introduces modified training objectives for language model finetuning, and employs massive data augmentation via back-translation to increase the diversity of the training data and examines the possibilities of combining data from multiples sources to improve performance on the target dataset.

47 0

Paper Graph

GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-Supervised Learning and Explicit Policy Injection

Luo Si, Yinhe Zheng, Yuchuan Wu, Jian Sun, Wanwei He, Yinpei Dai, Zhen Cao, Dermot Liu, Peng Jiang, Min Yang, Feiling Huang, Yongbin Li•Sun Nov 28 2021

GALAXY is a novel pre-trained dialog model that explicitly learns dialog policy from limited labeled dialogs and large-scale unlabeled dialog corpora via semi-supervised learning and has a stronger few-shot ability than existing models under various low-resource settings.

170 0

Paper Graph

Adding a benchmark result helps the community track progress.