arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.04461cs.CL
收藏

隐式篇章关系识别的多标签分类

Multi-Label Classification for Implicit Discourse Relation Recognition

University of Edinburgh(爱丁堡大学);The Alan Turing Institute(阿兰·图灵研究所)

Wanqiu Long, N. Siddharth, Bonnie Webber

AI总结:

本文针对PDTB-3中隐式篇章关系可同时具有多个标签的问题,探索多种多标签分类框架,证明其在不降低单标签预测性能的同时能更好建模标签间依赖关系。

摘要:

篇章关系在建立文本内容的连贯性方面发挥着关键作用,将句子和从句连接成连贯的叙述。宾州篇章树库(Penn Discourse Treebank,PDTB)是该领域使用最广泛的数据集之一。在PDTB-3中,当标注者认为存在多种关系时,可以为一个示例分配多个标签。先前的篇章关系识别研究在训练过程中将这些实例视为单独的示例,并且只要有一个示例的标签被正确预测,该实例就被判定为正确。然而,这种方法是不充分的,因为它未能考虑现实情境中标签之间的相互依赖性,也未能区分只有一种语义关系成立的情况与多种关系同时成立的情况。在我们的工作中,我们通过探索各种多标签分类框架来处理隐式篇章关系识别,以应对这一挑战。我们表明,多标签分类方法不会降低单标签预测的性能。此外,我们对结果和数据进行了全面的分析。我们的工作有助于推进对篇章关系的理解和应用,并为未来的研究奠定了基础。

英文摘要:

Discourse relations play a pivotal role in establishing coherence within textual content, uniting sentences and clauses into a cohesive narrative. The Penn Discourse Treebank (PDTB) stands as one of the most extensively utilized datasets in this domain. In PDTB-3, the annotators can assign multiple labels to an example, when they believe that multiple relations are present. Prior research in discourse relation recognition has treated these instances as separate examples during training, and only one example needs to have its label predicted correctly for the instance to be judged as correct. However, this approach is inadequate, as it fails to account for the interdependence of labels in real-world contexts and to distinguish between cases where only one sense relation holds and cases where multiple relations hold simultaneously. In our work, we address this challenge by exploring various multi-label classification frameworks to handle implicit discourse relation recognition. We show that multi-label classification methods don't depress performance for single-label prediction. Additionally, we give comprehensive analysis of results and data. Our work contributes to advancing the understanding and application of discourse relations and provide a foundation for the future study

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。

↑