Beyond Classical IR: Conceptual IR

Abstract:

Natural languages exhibit in general phenomena such as hyponymy/hypernymy, synonymy, heteronymy, etc. These linguistic phenomena lead to some problems in the IR field, e.g. term mismatch. In this talk, I show how these phenomena or their related problems make the direct word-based document-query comparison insufficient, which is the case in most classical IR models. More precisely, I talk about using concepts instead of words to represent the content of documents and queries. Consequently, we do matching in a more informative space rather than the word space, where the effects of some linguistic phenomena are limited. I mainly talk about two problems that appear when moving to the conceptual space, namely the document length deformation and inter-concept relations quantification.

Biography:

Karam Abdulahhad is currently a post-doctoral at GESIS (Leibniz-Institute for the Social Sciences) in Cologne. He has a PhD degree in computer sciences from University Grenoble-Alpes in 2014. During his PhD, he proposed an IR model using propositional logic and lattice theory. Before PhD, he received a Master degree from University Grenoble-Alpes in 2010 and an Engineering degree from Damascus University in 2006. His research interests include: IR theory, logic-based IR, Quantum IR, conceptual and semantic IR, machine learning, and text mining. Recently, He is interested in studying the profitability of the modern word-embedding technics in the IR field. He taught in several universities. He also participated in developing several tools.