MSVD-Turkish: a comprehensive multimodal video dataset for integrated vision and language research in Turkish

Automatic generation of video descriptions in natural language, also called captioning, aims to understand the visual content and produce a language sentence depicting objects actions scene. This challenging integrated vision problem, however, has been predominantly addressed for English. The lack data linguistic properties other languages limit success existing approaches such languages. In this paper we target Turkish, morphologically rich agglutinative that very different compared To do so, create first large-scale captioning dataset by carefully translating English videos MSVD (Microsoft Research Video Description Corpus) into Turkish. addition enabling research parallel English–Turkish enable study role context (multimodal) machine translation. our experiments, build models both multimodal translation investigate effect word segmentation neural architectures better address We hope MSVD-Turkish results reported work will lead Turkish morphology