arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2404.01722cs.CL
收藏

基于事件关系图的句子级媒体偏见分析

Sentence-level Media Bias Analysis with Event Relation Graph

Texas A&M University(德克萨斯农工大学)

Yuanyuan Lei, Ruihong Huang

AI总结:

本文提出构建事件关系图以显式建模事件间的共指、时间、因果和子事件关系,并结合事件感知语言模型与关系感知图注意力网络,在句子级别提升媒体偏见句识别的精确率与召回率。

摘要:

如今,媒体机构正变得越来越党派化和极化。在本文中,我们在句子级别识别媒体偏见,并定位那些意图左右读者观点的偏见句。由于偏见句往往以中立、事实性的方式表达,考虑句子之外的更广泛语境有助于揭示偏见。我们特别观察到,偏见句中的事件需要与文档中的其他事件关联起来理解。因此,我们提出构建一个事件关系图,以显式推理事件-事件关系,用于句子级偏见识别。所设计的事件关系图以事件为节点,包含四种常见的事件关系类型:共指关系、时间关系、因果关系和子事件关系。然后,我们通过两个步骤将事件关系图融入偏见句识别:构建一个事件感知语言模型,通过软标签将事件和事件关系知识注入基础语言模型;进一步设计一个关系感知图注意力网络,基于硬标签利用事件和事件关系信息更新句子嵌入。在两个基准数据集上的实验表明,借助事件关系图,我们的方法同时提高了偏见句识别的精确率和召回率。

英文摘要:

Media outlets are becoming more partisan and polarized nowadays. In this paper, we identify media bias at the sentence level, and pinpoint bias sentences that intend to sway readers' opinions. As bias sentences are often expressed in a neutral and factual way, considering broader context outside a sentence can help reveal the bias. In particular, we observe that events in a bias sentence need to be understood in associations with other events in the document. Therefore, we propose to construct an event relation graph to explicitly reason about event-event relations for sentence-level bias identification. The designed event relation graph consists of events as nodes and four common types of event relations: coreference, temporal, causal, and subevent relations. Then, we incorporate event relation graph for bias sentences identification in two steps: an event-aware language model is built to inject the events and event relations knowledge into the basic language model via soft labels; further, a relation-aware graph attention network is designed to update sentence embedding with events and event relations information based on hard labels. Experiments on two benchmark datasets demonstrate that our approach with the aid of event relation graph improves both precision and recall of bias sentence identification.

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。

↑