Small Stickers, Big Meanings: A Multilingual Sticker Semantic Understanding Dataset with a Gamified Approach

摘要

Stickers, though small, are a highly condensed form of visual expression, ubiquitous across messaging platforms and embraced by diverse cultures, genders, and age groups. Despite their popularity, sticker retrieval remains an underexplored task due to the significant human effort and subjectivity involved in constructing high-quality query-sticker datasets. Although large language models (LLMs) excel at general NLP tasks, they falter when confronted with the nuanced, intangible, and highly specific nature of sticker query generation. To address the challenge of collecting diverse and contextually appropriate sticker search queries, we introduce Sticktionary, a gamified annotation framework designed to elicit high-quality, semantically rich queries from contributors. Using this framework, we construct StickerQueries, a multilingual dataset comprising 1,115 English and 615 Chinese sticker search queries, annotated by over 60 contributors across more than 60 hours of annotation. We demonstrate the utility of StickerQueries in several downstream tasks, including query generation and sticker retrieval. Through comprehensive quantitative and qualitative evaluations, we demonstrate that StickerQueries significantly improves the quality of query generation, retrieval accuracy, and semantic understanding within the sticker domain. To support future research, we publicly release the multilingual StickerQueries dataset and two fine-tuned query generation models. Additional experiments and supplementary case studies can be found here.