arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2501.00152cs.CLcs.AI
收藏

社交媒体中时间线摘要的时间推理

Temporal reasoning for timeline summarisation in social media

Queen Mary University of London(伦敦女王学院);Bar-Ilan University(巴伊兰大学);The Alan Turing Institute(艾伦·图灵研究所)

Jiayu Song, Mahmud Elahi Akhter, Dana Atzil Slonim, Maria Liakata

AI总结:

本文提出通过知识蒸馏将时间推理能力融入LLM,并构建NarrativeReason数据集,以提升社交媒体长线程时间线摘要质量,在心理健康域外任务上验证了其有效性与泛化性。

摘要:

本文探讨了增强大型语言模型(LLMs)的时间推理能力是否能够提升时间线摘要的质量,该任务是对包含事件序列的长文本(如社交媒体线程)进行摘要。我们首先引入了NarrativeReason,这是一个专注于叙事中顺序事件之间时间关系的新数据集,将其与现有主要处理成对事件关系的时间推理数据集区分开来。我们的方法随后通过知识蒸馏框架将时间推理与时间线摘要相结合,在该框架中,我们首先在时间推理任务上微调一个教师模型,然后将该知识蒸馏到学生模型中,同时训练其执行时间线摘要任务。实验结果表明,我们的模型在域外心理健康相关的时间线摘要任务上取得了优越的性能,这些任务涉及长社交媒体线程,其中包含事件的重复和多种情绪的混合,这凸显了利用时间推理来改进时间线摘要的重要性和泛化能力。

英文摘要:

This paper explores whether enhancing temporal reasoning capabilities in Large Language Models (LLMs) can improve the quality of timeline summarisation, the task of summarising long texts containing sequences of events, such as social media threads. We first introduce NarrativeReason, a novel dataset focused on temporal relationships among sequential events within narratives, distinguishing it from existing temporal reasoning datasets that primarily address pair-wise event relationships. Our approach then combines temporal reasoning with timeline summarisation through a knowledge distillation framework, where we first fine-tune a teacher model on temporal reasoning tasks and then distill this knowledge into a student model while simultaneously training it for the task of timeline summarisation. Experimental results demonstrate that our model achieves superior performance on out-of-domain mental health-related timeline summarisation tasks, which involve long social media threads with repetitions of events and a mix of emotions, highlighting the importance and generalisability of leveraging temporal reasoning to improve timeline summarisation.

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。

↑