arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2404.08263cs.CLcs.AIcs.LGcs.SI
收藏

用于社会事件检测的基于关系提示的预训练语言模型

Relational Prompt-based Pre-trained Language Models for Social Event Detection

Kunming University of Science and Technology(昆明理工大学);Beijing Institute of Technology(北京理工大学);Beihang University(北京航空航天大学);North China Electric Power University(华北电力大学);University of Illinois at Chicago(伊利诺伊大学芝加哥分校)

Pu Li, Xiaoyan Yu, Hao Peng, Yantuan Xian, Linqin Wang, Li Sun, Jingyun Zhang, Philip S. Yu

AI总结:

针对GNN社会事件检测中边噪声及文本与关系难以联合学习的问题,提出RPLM_SED,通过成对多关系消息建模、关系提示学习和聚类约束提升表示区分度,并在多场景取得SOTA。

摘要:

社会事件检测(SED)旨在从社交流中识别重大事件,并在从舆论分析到风险管理的广泛领域中得到应用。近年来,基于图神经网络(GNN)的解决方案取得了最先进的性能。然而,基于GNN的方法常常受到消息之间缺失边和噪声边的困扰,从而影响所学消息嵌入的质量。此外,这些方法在训练前静态初始化节点嵌入,这反过来限制了同时从消息文本和关系中学习的能力。本文从基于预训练语言模型(PLM)的新视角处理社会事件检测,并提出RPLM_SED(用于社会事件检测的基于关系提示的预训练语言模型)。首先,我们提出一种新的成对消息建模策略,将社会消息构造成具有多关系序列的消息对。其次,提出一种新的基于多关系提示的成对消息学习机制,利用PLM从带有多关系提示的消息对中学习更全面的消息表示。第三,我们设计了一种新的聚类约束,通过增强簇内紧凑性和簇间分离度来优化编码过程,使消息表示更具区分性。我们在三个真实世界数据集上评估RPLM_SED,结果表明RPLM_SED模型在社会事件检测任务的离线、在线、低资源和长尾分布场景中均取得最先进性能。

英文摘要:

Social Event Detection (SED) aims to identify significant events from social streams, and has a wide application ranging from public opinion analysis to risk management. In recent years, Graph Neural Network (GNN) based solutions have achieved state-of-the-art performance. However, GNN-based methods often struggle with missing and noisy edges between messages, affecting the quality of learned message embedding. Moreover, these methods statically initialize node embedding before training, which, in turn, limits the ability to learn from message texts and relations simultaneously. In this paper, we approach social event detection from a new perspective based on Pre-trained Language Models (PLMs), and present RPLM_SED (Relational prompt-based Pre-trained Language Models for Social Event Detection). We first propose a new pairwise message modeling strategy to construct social messages into message pairs with multi-relational sequences. Secondly, a new multi-relational prompt-based pairwise message learning mechanism is proposed to learn more comprehensive message representation from message pairs with multi-relational prompts using PLMs. Thirdly, we design a new clustering constraint to optimize the encoding process by enhancing intra-cluster compactness and inter-cluster dispersion, making the message representation more distinguishable. We evaluate the RPLM_SED on three real-world datasets, demonstrating that the RPLM_SED model achieves state-of-the-art performance in offline, online, low-resource, and long-tail distribution scenarios for social event detection tasks.

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。

↑