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 implementationsMost implemented papers
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.
Action-Based Conversations Dataset: A Corpus for Building More In-Depth Task-Oriented Dialogue Systems
Existing goal-oriented dialogue datasets focus mainly on identifying slots and values.
Metaphorical User Simulators for Evaluating Task-oriented Dialogue Systems
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
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
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
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
Teaching machines to accomplish tasks by conversing naturally with humans is challenging.
Scalable Multi-Domain Dialogue State Tracking
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
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
End-to-end task-oriented dialog systems usually suffer from the challenge of incorporating knowledge bases.