Semi-supervised News Discourse Profiling with Contrastive Learning
Semi-supervised News Discourse Profiling with Contrastive Learning
复制标题
DOI：
10.48550/arxiv.2309.11692
复制
发表时间：
2023-09
期刊：
影响因子：
--
通讯作者：
Ming Li;Ruihong Huang
中科院分区：
文献类型：
--
作者：
Ming Li;Ruihong Huang
新闻话语分析旨在仔细审查新闻文章中每个句子与事件相关的角色，并已在各种下游应用程序中被证明是有用的。具体来说，在给定新闻话语的上下文中，每个句子都根据其对新闻事件结构的描述被分配到预定义的类别。然而，由于生成话语级注释的费力和时间密集性，现有方法缺乏可用的人工注释数据。在本文中，我们提出了一种新颖的方法，称为文档内蒸馏对比学习（ICLD），利用其独特的结构特征来解决新闻话语分析任务。值得注意的是，我们是第一个在该任务范式中应用半监督方法的人，并且评估证明了所提出方法的有效性。
News Discourse Profiling seeks to scrutinize the event-related role of each sentence in a news article and has been proven useful across various downstream applications. Specifically, within the context of a given news discourse, each sentence is assigned to a pre-defined category contingent upon its depiction of the news event structure. However, existing approaches suffer from an inadequacy of available human-annotated data, due to the laborious and time-intensive nature of generating discourse-level annotations. In this paper, we present a novel approach, denoted as Intra-document Contrastive Learning with Distillation (ICLD), for addressing the news discourse profiling task, capitalizing on its unique structural characteristics. Notably, we are the first to apply a semi-supervised methodology within this task paradigm, and evaluation demonstrates the effectiveness of the presented approach.