To predict the next most likely participant to interact in a multi-party conversation is a difficult problem. In a text-based chat group, the only information available is the sender, the content of the text and the dialogue history. In this paper we present our study on how these information can be used on the prediction task through a corpus and architecture that integrates turn-taking classifiers based on Maximum Likelihood Expectation (MLE), Convolutional Neural Networks (CNN) and Finite State Automata (FSA). The corpus is a synthetic adaptation of the Multi-Domain Wizard-of-Oz dataset (MultiWOZ) to a multiple travel service-based bots scenario with dialogue errors and was created to simulate user's interaction and evaluate the architecture. We present experimental results which show that the CNN approach achieves better performance than the baseline with an accuracy of 92.34%, but the integrated solution with MLE, CNN and FSA achieves performance even better, with 95.65%.
Is ChatGPT a Good Multi-Party Conversation Solver?
National Engineering Research Center of Speech and Language Information Processing（国家语音与语言信息处理工程技术研究中心）；University of Science and Technology of China（中国科学技术大学）
A Role-Selected Sharing Network for Joint Machine-Human Chatting Handoff and Service Satisfaction Analysis
Wuhan University（武汉大学）；Northeastern University（东北大学）；Alibaba Group（阿里巴巴集团）；East China Normal University（华东师范大学）；Zhejiang University（浙江大学）；Worcester Polytechnic Institute（伍斯特理工学院）
Towards Proactive Information Probing: Customer Service Chatbots Harvesting Value from Conversation
Institute of Data Science, National University of Singapore（新加坡国立大学数据科学研究所）；College of Computer Science, Sichuan University（四川大学计算机学院）；Engineering Research Center of Machine Learning and Industry Intelligence, Ministry of Education, China（教育部机器学习与产业智能工程研究中心）
Attacks on Third-Party APIs of Large Language Models
University of Cambridge（剑桥大学）；Indian Institute of Technology, Bombay（印度理工学院孟买分校）；University of Melbourne（墨尔本大学）；University College London（伦敦大学学院）；Macquarie University（麦考瑞大学）
SCALM: Towards Semantic Caching for Automated Chat Services with Large Language Models
School of Computing Science, Simon Fraser University（西蒙菲莎大学计算科学学院）；University of Mississippi（密西西比大学）；Jiangxing Intelligence Inc.（江兴智联公司）；The University of Hong Kong（香港大学）
HeterMPC: A Heterogeneous Graph Neural Network for Response Generation in Multi-Party Conversations
Microsoft（微软）
近年来，各种针对两方会话的响应生成模型已经取得了令人瞩目的进步，但对于更实用、更复杂的多方会话（MPC）响应生成模型的研究较少。与对话上下文是一系列话语的双方对话相比，构建MPC的响应生成模型更具挑战性，因为存在复杂的上下文结构并且生成的响应严重依赖于两个对话者（即，说话人和受话人）和历史话语。为了解决这些挑战，我们提出了HeterMPC，异构图形为基础的神经网络的响应生成MPC模型的语义的话语和对话者同时与两种类型的节点在一个图中。此外，我们还设计了六种类型的Meta关系与节点边类型相关的参数来表征图中的异构交互。通过多跳更新，HeterMPC可以充分利用会话的结构知识来生成响应。在Ubuntu Internet Relay Chat（IRC）信道基准测试上的实验结果表明，HeterMPC优于MPC中响应生成的各种基线模型。
COSPLAY: Concept Set Guided Personalized Dialogue Generation Across Both Party Personas
Beijing University of Technology（北京工业大学）；Tencent AI Lab（腾讯AI实验室）；Tsinghua University（清华大学）；The Chinese University of Hong Kong（香港中文大学）；University of Southern California（南加州大学）
