Task-Oriented Dialogue Systems

117 papers with code • 4 benchmarks • 19 datasets

Achieving a pre-defined task through a dialog.

Libraries

Use these libraries to find Task-Oriented Dialogue Systems models and implementations

Subtasks


Most implemented papers

Conversation Graph: Data Augmentation, Training and Evaluation for Non-Deterministic Dialogue Management

huawei-noah/noah-research 29 Oct 2020

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.

Metaphorical User Simulators for Evaluating Task-oriented Dialogue Systems

superbooming/simtester 2 Apr 2022

Employing existing user simulators to evaluate TDSs is challenging as user simulators are primarily designed to optimize dialogue policies for TDSs and have limited evaluation capabilities.

Fantastic Rewards and How to Tame Them: A Case Study on Reward Learning for Task-oriented Dialogue Systems

budzianowski/multiwoz 20 Feb 2023

Prior works mainly focus on adopting advanced RL techniques to train the ToD agents, while the design of the reward function is not well studied.

In-Context Learning User Simulators for Task-Oriented Dialog Systems

telepathylabsai/prompt-based-user-simulator 1 Jun 2023

This paper presents a novel application of large language models in user simulation for task-oriented dialog systems, specifically focusing on an in-context learning approach.

DIALIGHT: Lightweight Multilingual Development and Evaluation of Task-Oriented Dialogue Systems with Large Language Models

cambridgeltl/e2e_tod_toolkit 4 Jan 2024

We present DIALIGHT, a toolkit for developing and evaluating multilingual Task-Oriented Dialogue (ToD) systems which facilitates systematic evaluations and comparisons between ToD systems using fine-tuning of Pretrained Language Models (PLMs) and those utilising the zero-shot and in-context learning capabilities of Large Language Models (LLMs).

A Network-based End-to-End Trainable Task-oriented Dialogue System

ysglh/Task-Oriented-Dialogue-Dataset-Survey EACL 2017

Teaching machines to accomplish tasks by conversing naturally with humans is challenging.

Scalable Multi-Domain Dialogue State Tracking

google-research-datasets/simulated-dialogue 29 Dec 2017

We introduce a novel framework for state tracking which is independent of the slot value set, and represent the dialogue state as a distribution over a set of values of interest (candidate set) derived from the dialogue history or knowledge.

Dialogue Learning with Human Teaching and Feedback in End-to-End Trainable Task-Oriented Dialogue Systems

google-research-datasets/simulated-dialogue NAACL 2018

To address this challenge, we propose a hybrid imitation and reinforcement learning method, with which a dialogue agent can effectively learn from its interaction with users by learning from human teaching and feedback.

Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Oriented Dialog Systems

HLTCHKUST/Mem2Seq ACL 2018

End-to-end task-oriented dialog systems usually suffer from the challenge of incorporating knowledge bases.