报告题目:  Combining reasoning with machine learning methods for AI tasks and applications
报告人：   Chitta Baral 亚利桑那州立大学教授
主持人:      贺 樑 教授
报告时间：2018年9月17日  周一 14:00
报告地点：中北校区数学馆201报告厅
主办单位：计算机科学与beat365手机中文官方网站
 
报告人简介:
Chitta Baral is a Professor in Computer Science at the Arizona State University with research experience is in various sub-fields of Artificial Intelligence (AI) such as Knowledge Representation and Reasoning,Natural Language Understanding, and Image Understanding; and their applications to Molecular Biology, Health Informatics and Robotics. Chitta is the author of the book "Knowledge Representation, Reasoning and Declarative Problem Solving" published by Cambridge University Press. Chitta's research has been funded by various US federal agencies including NSF, NASA, ONR and IARPA. Chitta has been an Associate Editor of Journal of AI Research and is currently an associate Editor of the AI Journal, the two top journals in the field of AI. Chitta has been the Program Co-Chair  (2014) and general chair (2016) for the Knowledge Representation and Reasoning (KR&R) Conference and is the current President of KR Inc. Chitta has published significantly in major AI journals and conferences and has graduated many Ph.Ds in the field of AI. He has given invited talks at major AI conferences including AAAI and KR&R. Some of the AI packages developed by Chitta and his students include NL2KR, a platform to create systems that can translate natural language to targeted formal and logical languages; Kparser, a semantic knowledge parser for natural language text; and DeepQA, a system to reason about biological pathways. In recent years, Chitta's main research agenda has been to show that machine learning and reasoning needs to be combined to develop robust general AI systems.
 
报告摘要:
Reasoning and learning being two main aspects of “Intelligence” our research group has been working on the combined use of both in various AI tasks and applications. In this talk I will discuss some of our work on this with respect to image understanding, finding deep connection between a set of images, addressing various natural language understanding (NLU) challenges and tasks (Winograd, babi, grid puzzles and arithmetic problems) and inferencing drug interactions from Pubmed text.  I will also discuss what we learned about some of the issues and questions that come up when trying to combine reasoning and machine learning. These include: What kind of knowledge is important for various NLU tasks? How should this knowledge be expressed? Where to get these knowledge from? How much of it and which kinds should be written manually and which kinds are to be obtained automatically? From where to obtain knowledge automatically? What kind of knowledge can we get from reading (text)? How to get them? How best to translate natural language text to a knowledge representation formalism? What kinds of machine learning algorithms will help in the various kinds of knowledge acquisition?
Website: http://www.public.asu.edu/~cbaral/