Pan Du
About Pan Du
Pan Du is a Lead Applied Research Scientist at Thomson Reuters, specializing in legal language models and retrieval models. He holds a Master's degree in Computer Software Engineering and a PhD in Web Search and Data Mining, and has contributed significantly to the field through research and publications.
Work at Thomson Reuters
Pan Du currently serves as the Lead Applied Research Scientist at Thomson Reuters, a position he has held since 2023. In this role, he leads a team dedicated to developing advanced legal language models and retrieval models. His work has resulted in significant improvements over existing baselines on key performance metrics. Prior to this role, he worked as a Senior Applied Research Scientist at the same organization from 2021 to 2023, further contributing to the company's research initiatives in legal technology.
Education and Expertise
Pan Du earned his Master's degree in Computer Software Engineering from the Beijing Institute of Technology, studying from 2003 to 2006. He then pursued a Doctor of Philosophy (PhD) at the Institute of Computing Technology, Chinese Academy of Sciences, focusing on web search and data mining from 2006 to 2012. His academic background provides a strong foundation for his expertise in legal language modeling and retrieval systems.
Background
Before joining Thomson Reuters, Pan Du held several academic and research positions. He served as an Assistant Professor at the Chinese Academy of Sciences from 2012 to 2017. He then transitioned to research roles at Université de Montréal from 2017 to 2021 and briefly worked as a Research Consultant at McGill University's Desautels Faculty of Management in 2017. His diverse experiences across different institutions have contributed to his research capabilities.
Achievements
Pan Du has made significant contributions to the field of legal language modeling and retrieval. He has published numerous papers on topics including legal retrieval, document ranking, and sentiment analysis. Additionally, he serves on multiple conference committees related to Information Retrieval and Natural Language Processing, including prestigious conferences such as SIGIR, KDD, and EMNLP. His involvement in these committees highlights his active participation in advancing research in his field.
Research Focus
Pan Du's research focuses on the development and implementation of legal language models and retrieval models. He has verified their potential through various projects across different applications. His work involves extensive experimentation to inspire new ideas aimed at enhancing the performance of these models, reflecting his commitment to innovation in legal technology.