一种基于transformer的POI级社交帖子地理定位框架
A Transformer-based Framework for POI-level Social Post Geolocation
摘要:
社交帖子的POI级地理信息对于许多基于位置的应用和服务至关重要。然而,社交媒体数据及其平台的多模态、复杂性和多样性限制了推断这种细粒度位置及其后续应用的性能。为了解决这个问题,我们提出了一个基于transformer的通用框架,该框架建立在预先训练的语言模型的基础上,并考虑非文本数据,用于POI级别的社交帖子地理定位。为此,对输入进行分类以处理不同的社交数据,并为特征表示提供最佳组合策略。此外,提出了一种统一的层次表示来学习时间信息,并采用级联版本的编码来更好地捕获特征位置。在各种社交数据集上的实验结果表明,我们提出的框架的三个变体在准确性和距离误差指标方面大大优于多个最先进的基线。
英文摘要:
POI-level geo-information of social posts is critical to many location-based applications and services. However, the multi-modality, complexity and diverse nature of social media data and their platforms limit the performance of inferring such fine-grained locations and their subsequent applications. To address this issue, we present a transformer-based general framework, which builds upon pre-trained language models and considers non-textual data, for social post geolocation at the POI level. To this end, inputs are categorized to handle different social data, and an optimal combination strategy is provided for feature representations. Moreover, a uniform representation of hierarchy is proposed to learn temporal information, and a concatenated version of encodings is employed to capture feature-wise positions better. Experimental results on various social datasets demonstrate that three variants of our proposed framework outperform multiple state-of-art baselines by a large margin in terms of accuracy and distance error metrics.
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。