Keynote Speaker 2024
Keynote Speaker Ⅰ
Prof. Huiyu Zhou
University of Leicester, United Kingdom
Brief Introduction: Dr. Huiyu Zhou received a Bachelor of Engineering degree in Radio Technology from Huazhong University of Science and Technology of China, and a Master of Science degree in Biomedical Engineering from University of Dundee of United Kingdom, respectively. He was awarded a Doctor of Philosophy degree in Computer Vision from Heriot-Watt University, Edinburgh, United Kingdom. Dr. Zhou currently is a full Professor at School of Computing and Mathematical Sciences, University of Leicester, United Kingdom. He has published over 380 peer-reviewed papers in the field. He was the recipient of "CVIU 2012 Most Cited Paper Award", “MIUA 2020 Best Paper Award”, “ICPRAM 2016 Best Paper Award” and was nominated for “ICPRAM 2017 Best Student Paper Award” and "MBEC 2006 Nightingale Prize". His research work has been or is being supported by UK EPSRC, ESRC, AHRC, MRC, EU, Royal Society, Leverhulme Trust, Invest NI, Puffin Trust, Alzheimer’s Research UK, Invest NI and industry. Homepage: https://www2.le.ac.uk/departments/informatics/people/huiyu-zhou.
Speech Title: Inhibition Adaption on Pre-trained Language Models
Abstract: Fine-tuning pre-trained language models (LMs) may not always be the most practical approach for downstream tasks. While adaptation fine-tuning methods have shown promising results, a clearer explanation of their mechanisms and further inhibition of the transmission of information is needed. To address this, we propose an Inhibition Adaptation (InA) fine-tuning method that aims to reduce the number of added tunable weights and appropriately reweight knowledge derived from pre-trained LMs. The InA method involves (1) inserting a small trainable vector into each Transformer attention architecture and (2) setting a threshold to directly eliminate irrelevant knowledge. This approach draws inspiration from the shunting inhibition, which allows the inhibition of specific neurons to gate other functional neurons. With the inhibition mechanism, InA achieves competitive or even superior performance compared to other fine-tuning methods on BERT-large, RoBERTa-large, and DeBERTa-large for text classification and question-answering tasks.
Keynote Speaker Ⅱ
Prof. Yue Zhang
Westlake University, China
Brief Introduction: Yue Zhang is a tenured Professor at Westlake University. His research interests include NLP and its underlying machine learning algorithms. His major contributions to the field include psycholinguistically motivated machine learning algorithm, learning-guided beam search for structured prediction, pioneering neural NLP models including graph LSTM, and OOD generalization for NLP. He authored the Cambridge University Press book ``Natural Language Processing -- a Machine Learning Perspective''. He is the PC co-chair for CCL 2020 and EMNLP 2022, and action editor for Transactios for ACL. He also served as associate editor for IEEE/ACM Transactions of Audio Speech and Language Processing (TASLP), ACM Transactions on Asian and Low-Resource Languages (TALLIP), IEEE Transactions on Big Data (TBD) and Computer, Speech and Language (CSL). He won the best paper awards of IALP 2017 and COLING 2018, best paper honorable mention of SemEval 2020, and best paper nomination for ACL 2018 and ACL 2023.
Speech Title: On Detection of Machine Generated Text
Abstract: With advances in large language models, machine generated text have been seen increasing rapidly over the Internet and in business and educational settings. However, it is not always desirable to have them, and in some situations maliciously generated text can cause harm in society. We consider the task of automatically detecting machine generated text in the open domain setting, where a detector does not need to know the model generating textual content, the domain of the content, or the language. We discuss both supervised settings and unsupervised settings, where the detection system learns from human labeled data and makes decision without receiving supervised tuning, respectively. Both evaluation settings and detection algorithms are discussed. Our final model fulfills the task with over 96% accuracy on detecting ChatGPT.
Keynote Speaker Ⅲ
Prof. Zhen Wang
Fellow of IEEE, IOP, AAIA
Northwestern Polytechnical University, China
Brief Introduction: Professor, Doctoral Supervisor, Secretary of the Party Branch of the School of Cyberspace Security of Northwestern Polytechnical University, Executive Vice President of the National Academy of Secrecy, Elected Member of Academia Europaea/The Academy of Europe (AE), European Academy of Sciences and Arts (EASA), IEEE/IOP/AAIA Fellow, globally highly cited scientist, national leading talent, and the chief scientist of a national science and technology innovation team. He mainly engaged in basic and applied research on artificial intelligence, cyberspace intelligent confrontation, and intelligent unmanned systems. The developed systems are used in multiple models and major tasks. He has published a series of contributions in journals including Nature Communications, PNAS, PRL, Science Advances, IEEE Transactions, WWW, AAAI, IJCAI, etc., and has been cited more than 20,000 times by WoS.
Speech Title: TBD
Abstract: TBD
Invited Speaker
Asst. Prof. Jicong Fan
The Chinese University of Hong Kong, Shenzhen, China
Brief Introduction: Jicong Fan is an Assistant Professor at the School of Data Science, The Chinese University of Hong Kong, Shenzhen. He obtained his Ph.D. from the Department of Electronic Engineering, City University of Hong Kong in 2018. Before joining CUHK-Shenzhen, he was a postdoc associate at Cornell University. He also held research positions at The University of Wisconsin-Madison and The University of Hong Kong in 2018 and 2015, respectively. His research interests lie in Artificial Intelligence and Machine Learning, with a particular focus on matrix and tensor methods, clustering algorithms, anomaly detection, and graph learning. His work has been published in prestigious journals and at renowned conferences, such as IEEE TSP/TNNLS/TII, Pattern Recognition, NeurIPS, ICLR, ICML, KDD, CVPR, AAAI, and IJCAI. He is a senior member of IEEE and is serving as an associate editor for international journals Pattern Recognition and Neural Processing Letters. He is the PI of NSFC Youth Programme, NSFC General Programme, and NSF Guangdong General Programme. He won Zhang Zhong-Jun Academician Outstanding Paper Award and First Prize of the Natural Science Award of Chinese Association of Automation. He was on the list of “World’s Top 2% Scientists” by Stanford University.
Speech Title: Recent Advances in Deep Anomaly Detection and Their Applications on Text Data
Abstract: Anomaly detection plays a crucial role across a wide range of applications, including medical diagnosis, autonomous driving, fraud detection in finance, fault detection in chemical engineering, and the identification of sudden natural disasters. This talk first briefly reviews unsupervised anomaly detection and then introduces several state-of-the-art deep learning methods for diverse data types such as images, tabular data, and graphs. Finally, the talk will explore the applications of unsupervised anomaly detection in text data and multi-modality data, encompassing areas like medical diagnosis, large language models, and social science.
