Leveraging Order-Free Tag Relations for Context-Aware Recommendation
This work provides an improved tag recommendation system for users on platforms like Instagram and Stack Overflow, offering more context-aware and accurate tag suggestions.
This paper addresses the problem of tag recommendation by proposing a sequence-oblivious generation method that accounts for both the orderless nature and inter-dependency of tag sets. The method significantly outperforms previous approaches on Instagram and Stack Overflow datasets.
Tag recommendation relies on either a ranking function for top-$k$ tags or an autoregressive generation method. However, the previous methods neglect one of two seemingly conflicting yet desirable characteristics of a tag set: orderlessness and inter-dependency. While the ranking approach fails to address the inter-dependency among tags when they are ranked, the autoregressive approach fails to take orderlessness into account because it is designed to utilize sequential relations among tokens. We propose a sequence-oblivious generation method for tag recommendation, in which the next tag to be generated is independent of the order of the generated tags and the order of the ground truth tags occurring in training data. Empirical results on two different domains, Instagram and Stack Overflow, show that our method is significantly superior to the previous approaches.