講座內容：Questions answering system and BERT（問答系統和BERT）
講座人👨🏿🦱🦹🏼♂️：Hamido Fujita 教授
講座時間😑🔽：11月23日 13:00-14:00
騰訊會議：510863300
Abstract：
Questions answering system is an important direction in the field of natural language processing, which has attracted great attention in recent years. At the same time, Bert, as a pre training language model, has achieved SOTA results on a number of natural language processing tasks, which is worthy of extensive research. In this lecture, I will talk about the network structure of Bert and the development, application scenario, main tasks and classification of QA system, including text QA, knowledge graph QA, community QA and table QA, as well as the use of Bert pre-training model to make fine-tune in domain knowledge, embed the natural language texts in the questions answering system, and what contribution it will make to the QA effect. Questions answering system contains challenges worthy of research, including complex logic problems QA, multi-hop QA and QA with insufficient domain knowledge.
Short Bio：
Dr. Hamido Fujita is professor at Iwate Prefectural University (IPU), Japan, as a director of Intelligent Software Systems. He is the Editor-in-Chief of Knowledge-Based Systems, Elsevier of impact factor (3.325) for 2015. He is vice president of International Society of Applied Intelligence, and also associate Editor-in-chief of Applied Intelligence Journal (Springer). He has given many keynotes in many prestigious international conferences on intelligent system and subjective intelligence. He headed a number of projects including Intelligent HCI, a project related to Mental Cloning as an intelligent user interface between human user and computers and SCOPE project on Virtual Doctor Systems for medical applications.
