English
Related papers

Related papers: Dialogue Evaluation with Offline Reinforcement Lea…

200 papers

User-centric evaluation has become a key paradigm for assessing Conversational Recommender Systems (CRS), aiming to capture subjective qualities such as satisfaction, trust, and rapport. To enable scalable evaluation, recent work…

Information Retrieval · Computer Science 2026-02-20 Michael Müller , Amir Reza Mohammadi , Andreas Peintner , Beatriz Barroso Gstrein , Günther Specht , Eva Zangerle

Human-computer interactive systems that rely on machine learning are becoming paramount to the lives of millions of people who use digital assistants on a daily basis. Yet, further advances are limited by the availability of data and the…

Machine Learning · Computer Science 2020-04-29 Katya Kudashkina , Valliappa Chockalingam , Graham W. Taylor , Michael Bowling

Deep reinforcement learning (RL) methods have significant potential for dialogue policy optimisation. However, they suffer from a poor performance in the early stages of learning. This is especially problematic for on-line learning with…

Computation and Language · Computer Science 2017-07-06 Pei-Hao Su , Pawel Budzianowski , Stefan Ultes , Milica Gasic , Steve Young

Task-oriented dialog systems have been applied in various tasks, such as automated personal assistants, customer service providers and tutors. These systems work well when users have clear and explicit intentions that are well-aligned to…

Computation and Language · Computer Science 2018-01-09 Zhou Yu , Alan W Black , Alexander I. Rudnicky

Policy learning (PL) is a module of a task-oriented dialogue system that trains an agent to make actions in each dialogue turn. Imitating human action is a fundamental problem of PL. However, both supervised learning (SL) and reinforcement…

Computation and Language · Computer Science 2023-05-09 Zhoujian Sun , Chenyang Zhao , Zhengxing Huang , Nai Ding

Dialog policy decides what and how a task-oriented dialog system will respond, and plays a vital role in delivering effective conversations. Many studies apply Reinforcement Learning to learn a dialog policy with the reward function which…

Computation and Language · Computer Science 2019-08-29 Ryuichi Takanobu , Hanlin Zhu , Minlie Huang

Evaluation is crucial in the development process of task-oriented dialogue systems. As an evaluation method, user simulation allows us to tackle issues such as scalability and cost-efficiency, making it a viable choice for large-scale…

Information Retrieval · Computer Science 2021-05-11 Weiwei Sun , Shuo Zhang , Krisztian Balog , Zhaochun Ren , Pengjie Ren , Zhumin Chen , Maarten de Rijke

In this paper, we present a deep reinforcement learning (RL) framework for iterative dialog policy optimization in end-to-end task-oriented dialog systems. Popular approaches in learning dialog policy with RL include letting a dialog agent…

Computation and Language · Computer Science 2017-09-20 Bing Liu , Ian Lane

Despite many recent advances for the design of dialogue systems, a true bottleneck remains the acquisition of data required to train its components. Unlike many other language processing applications, dialogue systems require interactions…

Computation and Language · Computer Science 2018-10-03 Matthieu Riou , Bassam Jabaian , Stéphane Huet , Fabrice Lefèvre

User simulators are essential for training reinforcement learning (RL) based dialog models. The performance of the simulator directly impacts the RL policy. However, building a good user simulator that models real user behaviors is…

Computation and Language · Computer Science 2019-09-05 Weiyan Shi , Kun Qian , Xuewei Wang , Zhou Yu

In contrast with goal-oriented dialogue, social dialogue has no clear measure of task success. Consequently, evaluation of these systems is notoriously hard. In this paper, we review current evaluation methods, focusing on automatic…

Computation and Language · Computer Science 2017-09-14 Amanda Cercas Curry , Helen Hastie , Verena Rieser

Reliable automatic evaluation of dialogue systems under an interactive environment has long been overdue. An ideal environment for evaluating dialog systems, also known as the Turing test, needs to involve human interaction, which is…

Computation and Language · Computer Science 2021-09-23 Haoming Jiang , Bo Dai , Mengjiao Yang , Tuo Zhao , Wei Wei

The goal of offline reinforcement learning (RL) is to find an optimal policy given prerecorded trajectories. Many current approaches customize existing off-policy RL algorithms, especially actor-critic algorithms in which policy evaluation…

Machine Learning · Computer Science 2021-10-07 Wonjoon Goo , Scott Niekum

Existing Conversational Recommender Systems (CRS) predominantly utilize user simulators for training and evaluating recommendation policies. These simulators often oversimplify the complexity of user interactions by focusing solely on…

Information Retrieval · Computer Science 2024-09-10 Gangyi Zhang , Chongming Gao , Hang Pan , Runzhe Teng , Ruizhe Li

Automatic dialogue response evaluator has been proposed as an alternative to automated metrics and human evaluation. However, existing automatic evaluators achieve only moderate correlation with human judgement and they are not robust. In…

Computation and Language · Computer Science 2020-04-27 Tianyu Zhao , Divesh Lala , Tatsuya Kawahara

Critique-guided reinforcement learning (RL) has emerged as a powerful paradigm for training LLM agents by augmenting sparse outcome rewards with natural-language feedback. However, current methods often rely on static or offline critic…

Artificial Intelligence · Computer Science 2026-04-15 Zhicong Li , Lingjie Jiang , Yulan Hu , Xingchen Zeng , Yixia Li , Xiangwen Zhang , Guanhua Chen , Zheng Pan , Xin Li , Yong Liu

There is a growing interest in developing goal-oriented dialog systems which serve users in accomplishing complex tasks through multi-turn conversations. Although many methods are devised to evaluate and improve the performance of…

Computation and Language · Computer Science 2020-05-18 Ryuichi Takanobu , Qi Zhu , Jinchao Li , Baolin Peng , Jianfeng Gao , Minlie Huang

Offline zero-shot reinforcement learning (RL) aims to learn agents that optimize unseen reward functions without additional environment interaction. The standard approach to this problem trains task-conditioned policies by sampling task…

Artificial Intelligence · Computer Science 2026-04-29 Nazim Bendib , Nicolas Perrin-Gilbert , Olivier Sigaud

In task-oriented dialogs (TOD), reinforcement learning (RL) algorithms train a model to directly optimize response for task-related metrics. However, RL needs to perform exploration, which can be time-consuming due to the slow…

Computation and Language · Computer Science 2023-10-23 Xiao Yu , Qingyang Wu , Kun Qian , Zhou Yu

An important aspect of developing conversational agents is to give a bot the ability to improve through communicating with humans and to learn from the mistakes that it makes. Most research has focused on learning from fixed training sets…

Artificial Intelligence · Computer Science 2017-01-17 Jiwei Li , Alexander H. Miller , Sumit Chopra , Marc'Aurelio Ranzato , Jason Weston