Kuaipedia: a Large-scale Multi-modal Short-video Encyclopedia

Online encyclopedias, such as Wikipedia, have been well-developed and researched in the last two decades. One can find any attributes or other information of a wiki item on a wiki page edited by a community of volunteers. However, the traditional text along with images can hardly express some other aspects of an item. For example, when we talk about "Shiba Inu", one may care more about "How to feed it" or "How to train it to not protect its food". Currently, short-video platforms have become a hallmark in the online world. Whether you're on TikTok, Instagram, Kuaishou, or YouTube Shorts, short-video apps have changed how we consume and create content today. Except for entertainment short videos, we can find more and more authors sharing insightful knowledge widely across all walks of life. These short videos, which we call knowledge videos, can easily express any aspects (E.g. hair or how-to-feed) consumers want to know about an item (E.g. Shiba Inu), and they can be systematically analyzed and organized like an online encyclopedia. In this paper, we propose Kuaipedia, a massive multi-modal encyclopedia consisting of items, aspects, and short videos linking to them, which is extracted from billions of videos of Kuaishou, a well-known short-video platform in China. We first collected items from multiple sources and mined user-centered aspects from millions of users' queries to build an item-aspect tree. Then we propose a new task called "multi-modal item-aspect linking" as an expansion of "entity linking" to link short videos into item-aspect pairs and build the whole short video encyclopedia. Intrinsic evaluations show that our encyclopedia is of large scale and highly accurate.