Jose Manuel Gomez-Perez
August 15th, 2022
Jose Manuel Gomez-Perez is the Director of Language Technology Research at expert.ai. He works in the intersection of several areas of artificial intelligence, combining structured knowledge and neural models to enable machine understanding of unstructured data as an analogous process to human comprehension. Jose Manuel collaborates with organizations like the European Space Agency and has advised several tech startups. A former Marie Curie fellow, he holds a Ph.D. in Computer Science and Artificial Intelligence based on his work during project Halo, an initiative of Microsoft co-founder Paul Allen to create a Digital Aristotle for life and physical sciences.
He regularly publishes in areas of AI, natural language processing and knowledge graphs, and has given invited seminars at different universities in Europe and the USA. Recently, he published the book A Practical Guide to Hybrid Natural Language Processing. Magazines like Nature and Scientific American, as well as newspapers like El Pa?s have collected his views on AI, language and vision understanding, and their applications.
Towards AI that Reasons with Scientific Text and Images
Reading a textbook in a particular discipline and being able to answer the questions at the end of each chapter is one of the grand challenges of artificial intelligence, which requires advances in language, vision, problem-solving, and learning theory. Such challenges are best illustrated in the scientific domain, where complex information is presented over a variety of modalities involving not only language but also visual information, like diagrams and figures.
In this talk, we will analyze the specific challenges entailed in understanding scientific documents and share some of the recent advances in the area that enable the development of AI systems capable to answer scientific questions. In addition, we will reflect on what new developments will be required to address the next grand challenge: to create an AI system that can make major scientific discoveries by itself.