This year's conference is dedicated to the memory of Prof. Lotfi Zadeh, Honorary Chair and Prof. Thouraya Bouabana-Tebibel. Both Thouraya and Lotfi were among the warmest of personalities. They will be missed, but not forgotten.Read More
Professor Lotfi Zadeh was a frequent keynote speaker at IRI conferences. He showed us how reuse was an inherently fuzzy concept – setting the stage for knowledge acquisition. He taught us that when someone insults you, you take it as a compliment. Moreover, Professor Zadeh entwined a sense of humor, hard work, and good science with a sense of adventure. Fuzzy numbers were extensions of logic. Computing with words was an extension of speech. He held that nothing is worth doing unless you believed in it; and, if you don’t believe in yourself, the outside world will not believe in your words either. Professor Zadeh will be missed; albeit, he will be by our side in death as in life.
Professor Thouraya Bouabana-Tebibel ran the conferences formal workshop for many years. She was a kind soul, an ardent researcher, and an excellent educator. She published many conference papers and pursued formal approaches to data science. Professor Tebibel will be remembered for her tireless efforts, her many students, and her pursuit of AI through reuse and randomization. The conference cannot be the same without her; but, her teachings surely put us all on the road to success. Professor Tebibel was a great woman, a role model, and a source of inspiration for us all. She will be sadly missed.
Machine learning has become a widespread technique in computer science to take advantage of vast amounts of data and train systems to solve difficult tasks such as image understanding, conversation, and robotics. The prospect of new applications such as self-driving cars leads to large scale investment in research and product development in this field. Trained components become part of many IT systems. However, the machine learning process and the models it creates also entail new vulnerabilities that can be exploited by sophisticated attackers, potentially causing issues from malfunction of cars to fraud to theft of models and data. In this talk we will discuss this emergent threat model and ways to solve this problem.
Identifying sentiment in natural language text is useful for a multitude of applications, including review mining for products and services, business reputation tracking, social and political science, mental health studies, and government policy making. Consequently, sentiment analysis has been an active area of research in natural language processing, leading to the development of many sentiment lexicons and classification techniques. However, most work in this area has focused on recognizing explicitly expressed sentiments. In this talk, we discuss several ways that sentiment can be implicitly expressed in language through phenomena such as affective events, sarcasm, and similes. Affective events are central, which are stereotypically positive or negative activities and experiences, such as being hired (positive) or being fired (negative). We will describe weakly supervised learning methods to automatically induce affective events with polarity values from large text collections. We will also discuss recent work to classify affective events with respect to Human Need categories that indicate the reason for an event's polarity.
The submission link is on-line, please refer: EasyChair IEEE IRI 2018
Given the emerging global Information-centric IT landscape that has tremendous social and economic implications, effectively processing and integrating humungous volumes of information from diverse sources to enable effective decision making and knowledge generation have become one of the most significant challenges of current times. Information Reuse and Integration for Data Science (IRI) seeks to maximize the reuse of information by creating simple, rich, and reusable knowledge representations and consequently explores strategies for integrating this knowledge into systems and applications. IRI plays a pivotal role in the capture, representation, maintenance, integration, validation, and extrapolation of information; and applies both information and knowledge for enhancing decision-making in various application domains.
This conference explores three major tracks: information reuse, information integration, and reusable systems. Information reuse explores theory and practice of optimizing representation; information integration focuses on innovative strategies and algorithms for applying integration approaches in novel domains; and reusable systemsfocus on developing and deploying models and corresponding processes that enable Information Reuse and Integration to play a pivotal role in enhancing decision-making processes in various application domains.
The IEEE IRI conference serves as a forum for researchers and practitioners from academia, industry, and government to present, discuss, and exchange ideas that address real-world problems with real-world solutions. Theoretical and applied papers are both included. The conference program will include special sessions, open forum workshops, panels and keynote speeches.