English
Related papers

Related papers: End-to-End Optimization of Task-Oriented Dialogue …

200 papers

Open-ended dialogue agents aim to deliver engaging, personalized interactions by adapting to users' traits, but existing methods face critical limitations: over-reliance on pre-collected user data, and short-horizon biases in reinforcement…

Artificial Intelligence · Computer Science 2026-02-11 Kun Peng , Conghui Tan , Yu Liu , Guohua Tang , Zhongqian Sun , Wei Yang , Zining Zhu , Lei Jiang , Yanbing Liu , Hao Peng

Making sophisticated, robust, and safe sequential decisions is at the heart of intelligent systems. This is especially critical for planning in complex multi-agent environments, where agents need to anticipate other agents' intentions and…

Robotics · Computer Science 2020-01-29 Yichuan Charlie Tang

End-to-end training of neural networks is a promising approach to automatic construction of dialog systems using a human-to-human dialog corpus. Recently, Vinyals et al. tested neural conversation models using OpenSubtitles. Lowe et al.…

Computation and Language · Computer Science 2018-01-31 Chiori Hori , Takaaki Hori

Many studies have applied reinforcement learning to train a dialog policy and show great promise these years. One common approach is to employ a user simulator to obtain a large number of simulated user experiences for reinforcement…

Computation and Language · Computer Science 2020-04-24 Ryuichi Takanobu , Runze Liang , Minlie Huang

Task oriented dialogue systems (TOD) complete particular tasks based on user preferences across natural language interactions. Considering the impressive performance of large language models (LLMs) in natural language processing (NLP)…

Computation and Language · Computer Science 2025-10-08 Arezoo Saedi , Afsaneh Fatemi , Mohammad Ali Nematbakhsh , Sophie Rosset , Anne Vilnat

Task-oriented dialogue systems help users accomplish tasks such as booking a movie ticket and ordering food via conversation. Generative models parameterized by a deep neural network are widely used for next turn response generation in such…

Computation and Language · Computer Science 2020-10-13 Prasanna Parthasarathi , Arvind Neelakantan , Sharan Narang

In a dialog, there can be multiple valid next utterances at any point. The present end-to-end neural methods for dialog do not take this into account. They learn with the assumption that at any time there is only one correct next utterance.…

Computation and Language · Computer Science 2018-08-31 Janarthanan Rajendran , Jatin Ganhotra , Satinder Singh , Lazaros Polymenakos

A dialogue policy module is an essential part of task-completion dialogue systems. Recently, increasing interest has focused on reinforcement learning (RL)-based dialogue policy. Its favorable performance and wise action decisions rely on…

Computation and Language · Computer Science 2024-04-16 Chang Tian , Wenpeng Yin , Marie-Francine Moens

Dialogue policy plays an important role in task-oriented spoken dialogue systems. It determines how to respond to users. The recently proposed deep reinforcement learning (DRL) approaches have been used for policy optimization. However,…

Computation and Language · Computer Science 2019-05-28 Lu Chen , Zhi Chen , Bowen Tan , Sishan Long , Milica Gasic , Kai Yu

Task-oriented dialogue (ToD) systems are designed to help users achieve specific goals through natural language interaction. While recent advances in large language models (LLMs) have significantly improved linguistic fluency and contextual…

Computation and Language · Computer Science 2025-07-03 Shutong Feng , Hsien-chin Lin , Nurul Lubis , Carel van Niekerk , Michael Heck , Benjamin Ruppik , Renato Vukovic , Milica Gašić

This paper deals with distributed policy optimization in reinforcement learning, which involves a central controller and a group of learners. In particular, two typical settings encountered in several applications are considered:…

Machine Learning · Computer Science 2021-04-21 Tianyi Chen , Kaiqing Zhang , Georgios B. Giannakis , Tamer Başar

Robot assistants for older adults and people with disabilities need to interact with their users in collaborative tasks. The core component of these systems is an interaction manager whose job is to observe and assess the task, and infer…

Despite widespread interests in reinforcement-learning for task-oriented dialogue systems, several obstacles can frustrate research and development progress. First, reinforcement learners typically require interaction with the environment,…

Machine Learning · Computer Science 2017-11-15 Xiujun Li , Zachary C. Lipton , Bhuwan Dhingra , Lihong Li , Jianfeng Gao , Yun-Nung Chen

This paper describes our submission for the End-to-end Multi-domain Task Completion Dialog shared task at the 9th Dialog System Technology Challenge (DSTC-9). Participants in the shared task build an end-to-end task completion dialog system…

Computation and Language · Computer Science 2021-02-10 Boliang Zhang , Ying Lyu , Ning Ding , Tianhao Shen , Zhaoyang Jia , Kun Han , Kevin Knight

Traditional task-oriented dialog systems are unable to evolve from ongoing interactions or adapt to new domains after deployment, that is a critical limitation in real-world dynamic environments. Continual learning approaches depend on…

Multiagent Systems · Computer Science 2026-04-15 Shuyu Zhang , Yujie Liu , Xinru Wang , Cheng Zhang , Yanmin Zhu , Bin Li

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

This paper proposes a novel end-to-end architecture for task-oriented dialogue systems. It is based on a simple and practical yet very effective sequence-to-sequence approach, where language understanding and state tracking tasks are…

Computation and Language · Computer Science 2019-08-08 Lei Shu , Piero Molino , Mahdi Namazifar , Hu Xu , Bing Liu , Huaixiu Zheng , Gokhan Tur

This work investigates the task-oriented dialogue problem in mixed-domain settings. We study the effect of alternating between different domains in sequences of dialogue turns using two related state-of-the-art dialogue systems. We first…

Computation and Language · Computer Science 2019-09-06 Tho Luong Chi , Phuong Le-Hong

Recently advancements in deep learning allowed the development of end-to-end trained goal-oriented dialog systems. Although these systems already achieve good performance, some simplifications limit their usage in real-life scenarios. In…

Computation and Language · Computer Science 2018-03-16 Stefan Constantin , Jan Niehues , Alex Waibel

In end-to-end dialogue modeling and agent learning, it is important to (1) effectively learn knowledge from data, and (2) fully utilize heterogeneous information, e.g., dialogue act flow and utterances. However, the majority of existing…

Computation and Language · Computer Science 2019-11-12 Zhuoxuan Jiang , Ziming Huang , Dong Sheng Li , Xian-Ling Mao