arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.00786cs.IRcs.SI
收藏

利用对比学习实现社交帖子的少样本地理定位

Leveraging Contrastive Learning for Few-shot Geolocation of Social Posts

Menglin Li, Kwan Hui Lim

AI总结:

针对社交帖子地理定位中标签稀缺与数据不平衡问题,提出对比学习框架 ContrastGeo,通过推文—位置对比、匹配目标、在线难负例挖掘及多融合策略提升少样本定位性能。

摘要:

社交地理定位是预测社交媒体帖子始发位置的一个重要问题。然而,由于需要大量训练数据以及标注良好的标签,这项任务颇具挑战性。对于标签不足的新兴或较冷门地点,这些问题会进一步加剧,进而导致数据集不平衡。本文提出 ContrastGeo,这是一个采用对比学习增强的少样本社交地理定位框架。具体而言,作者引入了 Tweet-Location Contrastive learning(推文—位置对比学习)目标,用于对齐推文—位置对中推文与位置的表示。为捕捉推文与位置之间的相关性,框架进一步采用 Tweet-Location Matching(推文—位置匹配)目标,并通过在线难负例挖掘方法加以改进。作者还开发了三种融合策略,配合不同的融合编码器,以更好地生成推文和位置的联合表示。在三个社交媒体数据集上的综合实验表明,在少样本社交地理定位任务中,ContrastGeo 相较若干最先进基线具有更优越的性能。

英文摘要:

Social geolocation is an important problem of predicting the originating locations of social media posts. However, this task is challenging due to the need for a substantial volume of training data, alongside well-annotated labels. These issues are further exacerbated by new or less popular locations with insufficient labels, further leading to an imbalanced dataset. In this paper, we propose \textbf{ContrastGeo}, a \textbf{Contrast}ive learning enhanced framework for few-shot social \textbf{Geo}location. Specifically, a Tweet-Location Contrastive learning objective is introduced to align representations of tweets and locations within tweet-location pairs. To capture the correlations between tweets and locations, a Tweet-Location Matching objective is further adopted into the framework and refined via an online hard negative mining approach. We also develop three fusion strategies with various fusion encoders to better generate joint representations of tweets and locations. Comprehensive experiments on three social media datasets highlight ContrastGeo's superior performance over several state-of-the-art baselines in few-shot social geolocation.

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。

↑