Learning Profiles in Duplicate Question Detection

This paper presents the results of systematic and comparative experimentation with major types of methodologies for automatic duplicate question detection when these are applied to datasets of progressively larger sizes, thus allowing to study the learning profiles of this task under these different approaches and evaluate their merits. This study was made possible by resorting to the recent release for research purposes, by the Quora online question answering engine, of a new dataset with over 400,000 pairs labeled with respect to their elements being duplicate interrogative segments.