Why not, WINE?

Sourav S. Bhowmick, Aixin Sun, Ba Quan Truong

Abstract: Despite considerable progress in recent years on Tag-based Social Image Retrieval (TagIR), state-of-the-art TagIR systems fail to provide a systematic framework for end users to ask why certain images are not in the result set of a given query and provide an explanation for such missing results. However, such why-not questions are natural when expected images are missing in the query results returned by a TagIR system. In this demonstration, we present a system called WINE (Why-not questIon aNswering Engine) which takes the first step to systematically answer the why-not questions posed by end-users on TagIR systems. It is based on three explanation models, namely result reordering, query relaxation, and query substitution, that enable us to explain a variety of why-not questions. Our answer not only involves the reason why desired images are missing in the results but also suggestion on how the search query can be altered so that the user can view these missing images in sufficient number.