From Probability Ranking Principle to Strong Separation Principle

Separability is a highly desirable property for constructing and operating autonomous information systems, and especially classifiers. In this post, I present a step by step argument which shows that based on the classification principles, having better separability in the feature space leads to better accuracy in the classification results. Based on the Probability Ranking Principle […]

Building a multi-domain comparable corpus using a learning to rank method

Our paper "Building a multi-domain comparable corpus using a learning to rank method", with Razieh Rahimi, Azadeh Shakery, Javid Dadashkarimi, Mozhdeh Ariannezhad, and Hossein Nasr Esfahani has been published at the Journal of Natural Language Engineering. \o/ Multilingual nature of the Web makes interlingual translation a crucial requirement for information management applications. Bilingual humanly constructed […]

Two-Way Parsimonious Classification Models for Evolving Hierarchies

Our paper "Two-Way Parsimonious Classification Models for Evolving Hierarchies", with Hosein Azarbonyad, Jaap Kamps, and Maarten Marx, has been accepted as a long paper at the Conference and Labs of the Evaluation Forum (CLEF'16). \o/ Modern web data is highly structured in terms of entities and relations from large knowledge bases, geo-temporal references, and social […]