图像描述中的跨语言与跨文化差异
Cross-Lingual and Cross-Cultural Variation in Image Descriptions
AI总结：
本研究首次大规模实证分析了图像描述中的跨语言差异，通过多模态数据集开发实体识别方法，揭示了实体提及的普遍性与文化特定模式，并印证了先前小规模研究理论。
摘要：
不同语言的使用者在描述所见事物时是否存在差异？行为与认知研究报告了文化对感知的影响；然而，这些研究大多范围有限且难以复现。在本研究中，我们首次对图像描述中的跨语言差异进行了大规模实证研究。我们使用包含31种语言和来自不同地点图像的多模态数据集，开发了一种方法来准确识别字幕中提及且存在于图像中的实体，然后测量它们在不同语言间的差异。我们的分析表明，在地理或谱系上更接近的语言对倾向于更频繁地提及相同实体。我们还识别出实体类别，其显著性普遍较高（如生命体）、较低（服饰配件）或在不同语言间表现出高方差（景观）。在案例研究中，我们测量了特定语言对中的差异（例如，日语提及服饰的频率远高于英语）。此外，我们的方法印证了先前的小规模研究，包括：1) Rosch等人(1976)的基本层次类别理论，展示了对既不过于泛化也不过于具体的实体的偏好；2) Miyamoto等人(2006)关于环境提供感知模式（如实体计数）的假设。总体而言，我们的工作揭示了实体提及中普遍模式与文化特定模式并存的现象。
英文摘要：
Do speakers of different languages talk differently about what they see? Behavioural and cognitive studies report cultural effects on perception; however, these are mostly limited in scope and hard to replicate. In this work, we conduct the first large-scale empirical study of cross-lingual variation in image descriptions. Using a multimodal dataset with 31 languages and images from diverse locations, we develop a method to accurately identify entities mentioned in captions and present in the images, then measure how they vary across languages. Our analysis reveals that pairs of languages that are geographically or genetically closer tend to mention the same entities more frequently. We also identify entity categories whose saliency is universally high (such as animate beings), low (clothing accessories) or displaying high variance across languages (landscape). In a case study, we measure the differences in a specific language pair (e.g., Japanese mentions clothing far more frequently than English). Furthermore, our method corroborates previous small-scale studies, including 1) Rosch et al. (1976)'s theory of basic-level categories, demonstrating a preference for entities that are neither too generic nor too specific, and 2) Miyamoto et al. (2006)'s hypothesis that environments afford patterns of perception, such as entity counts. Overall, our work reveals the presence of both universal and culture-specific patterns in entity mentions.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
