Language and Knowledge Driven Scientific Discovery

语言与知识驱动的科学发现

Language and Knowledge Driven Scientific Discovery

报告简介：
机器学习与大数据技术驱动的科学研究第四范式，在合成生物学、分子与材料、生命健康等多个领域取得了广泛的应用。考虑到各学科领域积累了几十、上百年的专家知识，恰当地利用领域知识，可以提高机器学习模型的泛化性和可解释性。因此，本次报告将针对AI+生物、化学的交叉学科领域，建立知识图谱，研究语言-知识双驱动的预训练大模型，利用领域知识提升低资源学习方法，在蛋白质和化学分子的属性预测、功能判断、合成设计等众多评测任务上取得了良好效果。所研模型将作为人类与自然沟通的桥梁，帮助人类更好地理解并改造自然。

Scientific research has been revolutionized by artificial intelligence, with numerous successes in biology and chemistry. In this talk, I will focus on the interdisciplinary field of AI driven biological and chemical discovery, aiming to establish language and knowledge driven machine learning models. By leveraging the capable language model and symbolic domain knowledge, our team has published a number of AI models that achieve promising results in tasks such as protein and molecular function prediction, and design/generation. The published models serve as a bridge between human and the nature, helping humans better understand and explore the natural world.

个人简介：
张强博士，浙江大学百人计划研究员，曾在英国G5名校的伦敦大学学院（University College London）计算机系攻读博士学位并担任博士后，师从国际著名的信息检索与数据挖掘领域的Emine Yilmaz教授。他的研究主要涉及到机器学习、自然语言处理、知识图谱和AI for Science等方向，在Nature Machine Intelligence、Nature Communications、NeurIPS、ICML、ICLR、AAAI、WWW、ACL等人工智能顶级学术会议和SCI期刊发表三十余篇文章。他担任中国中文信息学会语言与知识计算专委会委员，教育部知识工程虚拟教研室成员，Big Data Research（中科院3区期刊）编辑，主持或参与国家自然科学基金、科技部科技创新2030-“新一代人工智能”重大项目、浙江省“尖兵”“领雁”重点研发计划项目、CCF-腾讯犀牛鸟基金、CAAI-华为MindSpore基金等近10项。曾获得中英教育信托者荣誉和华为MindSpore杰出导师奖。

Dr. Qiang Zhang is a Principal Investigator under the Hundred Talents Program at Zhejiang University. Before that, he obtained his Ph.D. degree and served as a postdoctoral researcher, both at the Department of Computer Science, University College London in the United Kingdom. He was supervised by Prof. Emine Yilmaz, an internationally renowned expert in the field of information retrieval and natural language processing. Dr. Zhang's research focuses on machine learning, human language processing, knowledge graphs, and applications to biochemical language (proteins and molecules) modeling. He has published over thirty articles in top-tier AI academic journals and conferences including Nature Machine Intelligence, Nature Communications, NeurIPS, ICML, ICLR, AAAI and ACL. He also serves as the associate editor of the Big Data Research journal and PC members of AI conferences such as NeurIPS’19-23, ICML’19-23 and AAAI’18-23. He received a number of research fundings from National Natural Science Foundation of China, New Generation AI Development Plan for 2030 of China, Tencent and Huawei. He was awarded the Great Britain-China Educational Trust in 2020 and Huawei MindSpore Outstanding Mentor Award in 2024.