Intent Recognition for Human-Machine Interactions

自然互動是人機互動中最熱門的研究議題之一。目前，智能設備（服務機器人、虛擬人物等）迫切需要能夠理解互動對話中的意圖。本書以基於深度學習方法的人機理解為重點，系統地介紹了讀者在人機對話中的意圖識別、未知意圖檢測和新意圖發現。本書是第一本在自然互動背景下介紹互動對話意圖分析的著作。除了幫助讀者掌握人機對話意圖分析的關鍵技術和概念，並了解最新進展，還提供了有價值的參考資料供進一步研究使用。

Hua Xu is a leading expert on multi-modal natural interaction for service robots, evolutionary learning, and intelligent optimization. He is currently a tenured associate professor at Tsinghua University, editor-in-chief of Intelligent Systems with Applications, and associate editor of Expert Systems with Application. Prof. Xu has authored the Chinese books "Data Mining: Methodology and Applications" (2014), "Data Mining: Methods and Applications-Application Cases" (2017), "Evolutionary Machine Learning" (2021), "Data Mining: Methodology and Applications" (2nd edition) (2022), "Natural Interaction for Tri-Co Robots (1) Human-machine Dialogue Intention Understanding" (2022) and "Natural Interaction for Tri-Co Robots (2) Sentiment Analysis of Multimodal Interaction Information" (2023), and published more than 140 papers in top-tier international journals and conferences. He is a core expert of the No. 3 National Science and Technology Major Project of the Ministry of Industry and Information Technology of China, senior member of CCF, member of CAAI and ACM, vice chairman of Tsinghua Collaborative Innovation Alliance of Robotics and Industry, and recipient of numerous awards, including the Second Prize of National Award for Progress in Science and Technology, the First Prize for Technological Invention of CFLP, and First Prize for Science and Technology Progress of CFLP.

Hanlei Zhang obtained his BS degree from the Department of Computer Science and Technology at Beijing Jiaotong University in 2020. He is currently pursuing a PhD in the Department of Computer Science and Technology at Tsinghua University. His research goal focuses on analyzing human intentions in real-world scenarios. Hanlei has published five first-authored peer-reviewed papers in top-tier international conferences and journals, including AAAI, ACM MM, ACL, and IEEE/ACM TASLP. His research interests encompass various areas such as intent analysis, open world classification, clustering, multimodal language understanding, and natural language processing. During his undergraduate studies, Hanlei was the recipient of the National Scholarship twice and was also recognized as a Beijing Excellent graduate. During his PhD career, he has received the first prize of the overall excellence scholarship twice and has been nominated for the Apple Scholars in AL/ML.

Ting-En Lin stands at the forefront of Conversational AI as a senior researcher at Alibaba's prestigious DAMO Academy. With an unwavering commitment to advancing the field of natural language processing, Tony has made significant strides in multimodal understanding, shaping the future of human-computer interaction. Educated at renowned institutions, Tony earned his Bachelor's degree in Electrical and Computer Engineering from National Chiao Tung University (NCTU) before pursuing his MPhil in Computer Science and Technology at Tsinghua University (THU). Under the guidance of Prof. Hua Xu, Tony honed his expertise and embarked on a fruitful research career. As a prolific contributor to the AI community, Tony has published numerous papers in leading conferences such as ACL, EMNLP, KDD, SIGIR, and AAAI. He is also a dedicated member of the program committee, ensuring the growth and development of the field.

华旭（Hua Xu）是服务机器人多模态自然交互、进化学习和智能优化领域的领先专家。他目前是清华大学终身副教授，担任《Intelligent Systems with Applications》的主编和《Expert Systems with Applications》的副主编。华旭教授撰写了中文书籍《数据挖掘：方法与应用》（2014年）、《数据挖掘：方法与应用-应用案例》（2017年）、《进化机器学习》（2021年）、《数据挖掘：方法与应用》（第二版）（2022年）、《三合一机器人的自然交互（1）人机对话意图理解》（2022年）和《三合一机器人的自然交互（2）多模态交互信息情感分析》（2023年），并在顶级国际期刊和会议上发表了140多篇论文。他是中国工业和信息化部第三个国家科技重大专项的核心专家，CCF的高级会员，CAAI和ACM的会员，清华大学机器人与产业协同创新联盟的副主席，曾获得多项奖励，包括国家科技进步二等奖、中国物流与采购联合会技术发明一等奖和科技进步一等奖。

张瀚磊（Hanlei Zhang）于2020年获得北京交通大学计算机科学与技术系学士学位，目前在清华大学计算机科学与技术系攻读博士学位。他的研究目标是分析现实场景中的人类意图。瀚磊在顶级国际会议和期刊（包括AAAI、ACM MM、ACL和IEEE/ACM TASLP）上发表了五篇以他为第一作者的同行评议论文。他的研究兴趣涵盖意图分析、开放世界分类、聚类、多模态语言理解和自然语言处理等多个领域。在本科期间，瀚磊两次获得国家奖学金，并被评为北京市优秀毕业生。在博士期间，他两次获得全优奖学金一等奖，并被提名为苹果AL/ML学者。

林庭恩（Ting-En Lin）作为阿里巴巴著名的DAMO学院高级研究员，站在会话式人工智能的前沿。作为自然语言处理领域的积极推动者，Tony在多模态理解方面取得了重要进展，塑造了人机交互的未来。Tony在著名学府接受教育，他先后在国立交通大学获得电机工程学士学位，然后在清华大学计算机科学与技术系攻读哲学硕士学位。在华旭教授的指导下，Tony磨练了自己的专业知识，并开始了富有成果的研究生涯。作为人工智能社区的多产贡献者，Tony在ACL、EMNLP、KDD、SIGIR和AAAI等顶级会议上发表了众多论文。他还是一个专注于程序委员会工作的成员，确保该领域的成长和发展。