Declarative Learning based Programming for Deep Learning and Reasoning over Natural Language

The UCI Computer Science Seminar Series is proud to present Parisa Kordjamshidi, MSU.

Title:
Declarative Learning based Programming for Deep Learning and Reasoning over Natural Language

Abstract:
The recent research on Natural Language Processing and many other complex problems show that monolithic deep learning models trained on merely large volumes of data suffer from the lack of interpretability and generalizability. While they might surprise us with writing an article that reads fluently given a few keywords, they can easily disappoint us by failing in some basic reasoning skills like understanding that the left is the opposite direction of right. For solving real-world problems, we often need computational models that involve multiple interdependent learners, along with significant levels of composition and reasoning based on additional knowledge beyond available data. In this talk, I will discuss two main directions of my research to deal with the mentioned challenges. One direction is on developing deep learning techniques and architectures that a) operate on structured semantic representations, b) capture high order patterns that enable relational reasoning, c) consider domain knowledge in learning. Another direction is on dealing with the challenges of current libraries and programming paradigms for developing such models. I will introduce the Declarative Learning-based Programming (DeLBP) paradigm as a new level of abstraction that facilitates the design and development of complex intelligent systems. This paradigm is based on explicit representations of the relational structure of data, representation of high order knowledge, and composition of learning models. This paradigm helps in the integration of learning and reasoning, and exploiting both sub-symbolic and symbolic representations for solving complex AI-complete problems.

Speaker Bio:
Parisa Kordjamshidi is an assistant professor of Computer Science & Engineering at Michigan State University. Her research interests are machine learning, natural language processing, and declarative learning-based programming. She has worked on the extraction of formal semantics and structured representations from natural language, with a specific focus on spatial semantics and structured output learning models. She obtained an NSF CAREER award in 2019. She is the leading PI of a project supported by the Office of Naval research to perform basic research and develop a declarative learning-based programming framework for the integration of domain knowledge into statistical/neural learning. She obtained her Ph.D. from KU Leuven, in 2013 and was a post-doc in the University of Illinois at Urbana-Champaign in the Cognitive computation group until 2016. She was a faculty member at Tulane University and a research scientist at Florida Institute for Human and Machine Cognition between 2016-2019 before joining MSU. Kordjamshidi is a member of the Editorial Board of Journal of Artificial Intelligence Research (JAIR), a member of Editorial Board of Machine Learning and Artificial Intelligence, part of the journal of Frontiers in Artificial Intelligence and Frontiers in Big Data. She has published papers, organized international workshops, and served as a (senior) program committee member of conferences such as IJCAI, AAAI, ACL, EMNLP, COLING, ECAI, and a member of the organizing committee of NAACL-2018, ECML-PKDD-2019, and EMNLP-2021 conferences.