Discourse relation classification is an especially difficult task without explicit context markers \cite{Prasad2008ThePD}. Current approaches to implicit relation prediction solely rely on two neighboring sentences being targeted, ignoring the broader context of their surrounding environments \cite{Atwell2021WhereAW}. In this research, we propose three new methods in which to incorporate context in the task of sentence relation prediction: (1) Direct Neighbors (DNs), (2) Expanded Window Neighbors (EWNs), and (3) Part-Smart Random Neighbors (PSRNs). Our findings indicate that the inclusion of context beyond one discourse unit is harmful in the task of discourse relation classification.

翻译：话语关系分类是一项尤其困难的任务，缺乏明确的语境标记\cite{Prasad2008ThePD}。当前隐式关系预测方法仅依赖两个相邻的目标句子，忽略了其周围环境的更广泛语境\cite{Atwell2021WhereAW}。在本研究中，我们提出三种新方法将语境融入句子关系预测任务：（1）直接邻句（DNs），（2）扩展窗口邻句（EWNs），（3）部分智能随机邻句（PSRNs）。我们的研究结果表明，在话语关系分类任务中引入超出单一话语单位的语境会产生负面影响。