检索结果-内蒙古大学图书馆

A multi-agent collaborative algorithm for task-oriented dialogue systems

INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS 2025年第3期16卷 2009-2022页

作者： Sun, Jingtao Kou, Jiayin Shi, Weipeng Hou, Wenyan Xian Univ Posts & Telecommun Sch Comp Sci & Technol Xian 710121 Shaanxi Peoples R China Xian Univ Posts & Telecommun Shaanxi Key Lab Network Data Anal & Intelligent Pr Xian 710121 Shaanxi Peoples R China

In recent years, reinforcement learning has found successful applications in dialogue systems. However, when confronted with task-oriented dialogue systems, optimizing the strategy becomes challenging due to difficulties in state tracking and the complexity of multitasking. task-oriented dialogue systems based on reinforcement learning encounter issues such as poor collaboration, non-unique learning goals, and non-staticity arising from the absence of agent cooperation. To address these challenges, this paper introduces a novel multi-agent cooperative dialogue (MACD) algorithm for task-oriented dialogue systems. In MACD, a deep neural network framework is employed to facilitate information exchange among multiple agents within task-oriented dialogue systems. This integration enables the consolidation of observations from individual agents, leading to the derivation of joint observations and fostering information sharing among the agents. Consequently, MACD aims to mitigate the problem of non-stationarity resulting from the lack of shared information among multiple agents. In the context of multi-agent strategy learning within task-oriented dialogue systems, we employ the MADDPG architecture to address the challenge of inadequate joint strategy learning among multiple agents. By integrating single-agent observations and multi-agent strategy learning, we aim to alleviate the collaborative deficiencies inherent in task-oriented dialogue systems involving multiple agents. Through experimentation with reinforcement learning algorithms such as MACD, DQN, OPPA, JOIE, and QMIX on the MultiWOZ 2.0 corpus, our results demonstrate significant enhancements. Specifically, the proposed algorithm effectively elevates the success rate of multi-agent collaboration in accomplishing dialogue tasks in composite task scenarios. Furthermore, it mitigates the occurrence of ineffective dialogues during the dialogue rounds. Comparative analysis reveals that our approach surpasses convention

关键词： task-oriented dialogue systems Reinforcement learning Multi-agent collaboration Integrated learning

来源：评论

学校读者我要写书评

暂无评论

Evaluating task-oriented dialogue systems with Users 23

Evaluating Task-oriented Dialogue Systems with Users

引用

46th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)

作者： Siro, Clemencia Univ Amsterdam Amsterdam Netherlands

ISBN: (纸本)9781450394086

Evaluation is one of the major concerns when developing information retrieval systems. Especially in the field of conversational AI, this topic has been heavily studied in the setting of both non-task and task-oriented conversational agents (dialogue systems).[1] Recently, several automatic metrics e.g., BLEU and ROUGE, proposed for the evaluation of dialogue systems, have shown poor correlation with human judgment and are thus ineffective for the evaluation of dialogue systems. As a consequence, a significant amount of research relies on human evaluation to estimate the effectiveness of dialogue systems[1, 4}.An emerging approach for evaluating task-oriented dialogue systems (TDS) is to estimate a user's overall satisfaction with the system from explicit and implicit user interaction signals [2, 3]. Though useful and effective, overall user satisfaction does not necessarily give insights into what aspects or dimensions a TDS is performing well on. Understanding why a user is satisfied or dissatisfied helps the TDS recover from an error and optimize towards an individual aspect to avoid total dissatisfaction during an interaction *** a user's satisfaction with TDS is crucial, mainly for two reasons. First, it allows system designers to understand different user perceptions regarding satisfaction, which in turn leads to better user personalization. Secondly, it can be used to avoid total dialogue failure by the system by deploying adaptive conversational approaches, such as failure recovery or switching topics. And, thus, fine-grained evaluation of TDS gives the system an opportunity to learn an individual user's interaction preferences leading to a fulfilled user goal. Therefore in this research, we take the first initiative toward understanding user satisfaction with TDS. We mainly focus on the fine-grained evaluation of conversational systems in a task-oriented setting.

关键词： User satisfaction relevance task-oriented dialogue systems user experience

来源：评论

学校读者我要写书评

暂无评论

A multi-agent curiosity reward model for task-oriented dialogue systems

引用

PATTERN RECOGNITION 2025年 157卷

作者： Sun, Jingtao Kou, Jiayin Hou, Wenyan Bai, Yujei Xian Univ Posts & Telecommun Sch Comp Sci & Technol Xian 710121 Shaanxi Peoples R China Xian Univ Posts & Telecommun Shaanxi Key Lab Network Data Anal & Intelligent Pr Xian Peoples R China

In practical decision-making dialogues, reinforcement learning methods face hurdles due to delays and sparse reward feedback for agents, and in some cases, lack of rewards altogether. These issues can impede efficient learning of dialogue strategies and compromise the performance of the model. To address this challenge, this paper introduces the Multi-Agent Curiosity Reward Model (MACRM) for task-oriented dialog systems. Firstly, in terms of dialog reward mechanisms, a forward dynamics model generates curiosity rewards, which are integrated with extrinsic rewards from the dialog environment feedback to mitigate the problem of sparse rewards resulting from inadequate agent exploration. Secondly, regarding the dialogue strategy training mechanism, an exploration-exploitation approach inspired by organismic exploration is adopted. This approach involves fully exploring the dialogue environment in the early stages and optimally exploiting learned knowledge later, thereby balancing exploration and exploitation and enhancing dialogue strategy learning efficiency. To assess the proposed model's effectiveness, experiments are conducted using the MultiWOZ corpus across three reward environments: (1) extrinsic rewards only, (2) curiosity rewards only, and (3) a combination of both. The experimental results demonstrate that agents employing MACRM exhibit faster learning of dialogue strategies compared to those relying on a single exploratory reward method, effectively addressing reward sparsity and delay issues in practical decision-making scenarios.

关键词： task-oriented dialogue systems Reinforcement learning Curiosity rewards Exploration and exploitation

来源：评论

学校读者我要写书评

暂无评论

Incorporating Specific Knowledge into End-to-End task-oriented dialogue systems

Incorporating Specific Knowledge into End-to-End Task-orient...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Wang, Qingyue Cao, Yanan Jiang, Junyan Wang, Yafang Tong, Lingling Guo, Li Chinese Acad Sci Inst Informat Engn Beijing Peoples R China Univ Chinese Acad Sci Sch Cyber Secur Beijing Peoples R China Ant Financial Serv Grp AI Dept Hangzhou Peoples R China Natl Comp Network Emergency Response Tech Team Beijing Peoples R China

ISBN: (纸本)9780738133669

External knowledge is vital to many natural language processing tasks. However, current end-to-end dialogue systems often struggle to interface knowledge bases(KBs) with response smoothly and effectively. In this paper, we convert the raw knowledge into relation knowledge and integrated knowledge and then incorporate them into end-to-end task-oriented dialogue systems. The relation knowledge extracted from knowledge triples is combined with dialogue history, aiming to enhance semantic inputs and support better language understanding. Integrated knowledge involves entities and relations by graph attention, assisting the model in generating informative responses. The experimental results on three public dialogue datasets show that our model improves over the previous state-of-the-art models in sentence fluency and informativeness.

关键词： task-oriented dialogue systems language understanding and generation external knowledge

来源：评论

学校读者我要写书评

暂无评论

LARGE LANGUAGE MODELS AS USER-AGENTS FOR EVALUATING task-oriented-dialogue systems

LARGE LANGUAGE MODELS AS USER-AGENTS FOR EVALUATING TASK-ORI...

引用

2024 Spoken Language Technology Workshop

作者： Kazi, Taaha Lyu, Ruiliang Zhou, Sizhe Hakkani-Tur, Dilek Tur, Gokhan Univ Illinois Champaign IL 61820 USA

ISBN: (纸本)9798350392265;9798350392258

Traditionally, offline datasets have been used to evaluate task-oriented dialogue (TOD) models. These datasets lack context awareness, making them suboptimal benchmarks for conversational systems. In contrast, user-agents, which are context-aware, can simulate the variability and unpredictability of human conversations, making them better alternatives as evaluators. Prior research has utilized large language models (LLMs) to develop user-agents. Our work builds upon this by using LLMs to create user-agents for the evaluation of TOD systems. This involves prompting an LLM, using in-context examples as guidance, and tracking the user-goal state. Our evaluation of diversity and task completion metrics for the user-agents shows improved performance with the use of better prompts. Additionally, we propose methodologies for the automatic evaluation of TOD models within this dynamic framework. We make our code publicly available 1

关键词： task-oriented dialogue systems user simulation agents task completion large language models

来源：评论

学校读者我要写书评

暂无评论

A Multi-task Based Neural Model to Simulate Users in Goal-oriented dialogue systems 22

A Multi-Task Based Neural Model to Simulate Users in Goal-Or...

引用

45th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)

作者： Kim, To Eun Lipani, Aldo UCL London England

ISBN: (纸本)9781450387323

A human-like user simulator that anticipates users' satisfaction scores, actions, and utterances can help goal-oriented dialogue systems in evaluating the conversation and refining their dialogue strategies. However, little work has experimented with user simulators which can generate users' utterances. In this paper, we propose a deep learning-based user simulator that predicts users' satisfaction scores and actions while also jointly generating users' utterances in a multi-task manner. In particular, we show that 1) the proposed deep text-to-text multi-task neural model achieves state-of-the-art performance in the users' satisfaction scores and actions prediction tasks, and 2) in an ablation analysis, user satisfaction score prediction, action prediction, and utterance generation tasks can boost the performance with each other via positive transfers across the tasks. The source code and model checkpoints used for the experiments run in this paper are available at the following weblink: https://***/kimdanny/user- simulation-t5.

关键词： user simulation multi-task learning user satisfaction prediction user action prediction user utterance generation task-oriented dialogue systems

来源：评论

学校读者我要写书评

暂无评论

Acquiring New Knowledge Without Losing Old Ones for Effective Continual dialogue Policy Learning

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 2024年第12期36卷 7569-7584页

作者： Wang, Huimin Zhang, Yunyan Yang, Yifan Zheng, Yefeng Wong, Kam-Fai Tencent Jarvis Res Ctr Tencent YouTu Lab Shenzhen 518057 Peoples R China Tencent Tencent AI Lab Shenzhen 518057 Peoples R China Chinese Univ Hong Kong Dept Syst Engn & Engn Management Cent Ave Hong Kong Peoples R China

dialogue policy learning is the core decision-making module of a task-oriented dialogue system. Its primary objective is to assist users to achieve their goals effectively in as few turns as possible. A practical dialogue-policy agent must be able to expand its knowledge to handle new scenarios efficiently without affecting its performance. Nevertheless, when adapting to new tasks, existing dialogue-policy agents often fail to retain their existing (old) knowledge. To overcome this predicament, we propose a novel continual dialogue-policy model which tackles the issues of "not forgetting the old" and "acquiring the new" from three different aspects: (1) For effective old-task preservation, we introduce the forgetting preventor which uses a behavior cloning technique to force the agent to take actions consistent with the replayed experience to retain the policy trained on historic tasks. (2) For new-task acquisition, we introduce the adaption accelerator which employs an invariant risk minimization mechanism to produce a stable policy predictor to avoid spurious corrections in training data. (3) For reducing the storage cost of the replayed experience, we introduce a replay manager which helps regularly clean up the old data. The effectiveness of the proposed model is evaluated both theoretically and experimentally and demonstrated favorable results.

关键词： dialogue policy learning Continual learning reinforcement learning task-oriented dialogue systems task-oriented dialogue systems reinforcement learning task-oriented dialogue systems

来源：评论

学校读者我要写书评

暂无评论

A multi-perspective global-local interaction framework for identifying dialogue acts and sentiments of dialogue utterances jointly

引用

INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS 2024年第5期15卷 1995-2011页

作者： Zhang, Qichen Li, Jingmei Harbin Engn Univ Coll Comp Sci & Technol 145 Nantong St Harbin 150001 Heilongjiang Peoples R China

dialogue act recognition (DAR) and sentiment classification (SC) are crucial tasks in dialogue systems, aiming to uncover speakers' implicit intentions and sentiment by analyzing contextual information. Recent approaches have sought to improve accuracy by jointly modeling dialogue acts and sentiments, considering complex relationships and latent structures. However, these methods often neglect two critical challenges. Firstly, real-world dialogues follow a chronological order, with interlocutors discussing one or more topics. Secondly, the joint task of dialogue act recognition and sentiment classification operates at a sentence level, making it essential to effectively utilize fine-grained word-level information from utterances. To tackle these challenges, we propose a multi-perspective global-local interaction framework. It captures overall contextual information and simulates the flow of dialogue acts and sentiments for each speaker. We delve into explicit intra-task interactions, cross-task collaborations, and token-level information reuse from three perspectives. We also incorporate a time span to accommodate real-world scenarios with chronological and multi-topic dialogues. Experimental results on widely-used benchmark datasets demonstrate the superiority of our framework over mainstream approaches. Comprehensive analysis validates the effectiveness of each component, showcasing the potential for enhancing DAR and SC tasks.

关键词： task-oriented dialogue systems dialogue act recognition Sentiment classification Multi-perspective

来源：评论

学校读者我要写书评

暂无评论

Building Conventional "Experts" With a dialogue Logic Programming Language

引用

IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING 2023年 31卷 1784-1796页

作者： Zheng, Xiaoqing Fudan Univ Sch Comp Sci Shanghai 200433 Peoples R China

We describe DiaProlog, a dialogue logic programming language that extends the vanilla Prolog with the features to facilitate the integration of reasoning capabilities into task-oriented dialogue systems. The extended language combines the expressive power of Horn rule and description logic with uncertainty and allows us to describe the specifications for both problem solving and dialogue management in a declarative programming manner. The systems incorporated with DiaProlog are capable of asking appropriate questions when necessary and collecting the answers to direct the line of reasoning and guide the conversation toward the correct solution. Besides, an explanation facility is provided to explain the reasoning behind its conclusion. We also describe a dialogue management framework built upon DiaProlog, which has been validated in multiple implementations providing legal consulting, financial advising, and medical guidance services where many questions require complex inferences about knowledge.

关键词： task analysis Cognition Knowledge based systems Oral communication Law Speech processing Neural networks dialogue management knowledge base logic programming language prolog task-oriented dialogue systems

来源：评论

学校读者我要写书评

暂无评论

Global-chronological graph interactive networks for multi-domain dialogue state tracking

引用

INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS 2023年第8期14卷 2607-2620页

作者： Zhang, Qichen Wang, Shuai Li, Jingmei Harbin Engn Univ Coll Comp Sci & Technol 145 Nantong St Harbin 150001 Heilongjiang Peoples R China

dialogue state tracking (DST) provides necessary information for the policy learning module to decide the next action according to the historical state and the utterance related details of the dialogue, so robust dialogue state tracking is a core part of high-quality task-oriented dialogue systems. The tasks addressed by dialogue state tracking are becoming increasingly complex, and due to the multi-domain switching in the dialogue relevant contexts, the model needs to have the ability to generate appropriate responses to accurately fit the domains, slots and slot values. However, efficient encoding of state information and fundamentally simulating the logical relationship between domains and slots to dynamically extract variation features of the multiple domains are still challenges for DST. In this paper, we propose a novel framework global-chronological graph interactive networks (GCGIN), which encodes both global and chronological information of the dialogue from dual perspectives, and leverages coupling and co-affine modules to interact with the above two different granularities information. Our model adopts the mask mechanism to improve anti-noise ability, and constructs the dynamic schema graph structure to dynamically model domain-slot and domain-value relations via dialogue chronological order to achieve cross-domain features learning and improve model scalability. Extensive experimental results on three benchmark datasets demonstrate that our proposed model outperforms existing mainstream methods, and comprehensive analysis validates the effectiveness of each component.

关键词： task-oriented dialogue systems dialogue state tracking Dual perspective encoding Dynamic schema graph structure

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：