arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2404.01532cs.CLcs.IR
收藏

面向自回归事件时序图生成的集合对齐框架

Set-Aligning Framework for Auto-Regressive Event Temporal Graph Generation

University of Warwick(华威大学);The Alan Turing Institute(阿兰·图灵研究所)

Xingwei Tan, Yuxiang Zhou, Gabriele Pergola, Yulan He

AI总结:

本文提出集合对齐框架,将事件时序图生成重构为条件集合生成问题,通过数据增强与集合属性正则化缓解线性化图边序列的错位惩罚,从而提升LLM生成事件时序图的效果与零样本泛化能力。

摘要:

事件时序图已被证明是表示文本中事件之间复杂时序关系的一种便捷且有效的表示形式。近期研究采用预训练语言模型以自回归方式生成线性化图来构建事件时序图,已展现出有前景的结果。然而,这些方法往往导致次优的图生成,因为线性化图具有集合特性,而语言模型却将其按序列方式处理。这一差异源于传统的文本生成目标,导致因目标序列中元素错位而对正确预测产生错误惩罚。为应对这些挑战,我们将该任务重新定义为条件集合生成问题,提出了一种专为有效利用大型语言模型(LLMs)而设计的集合对齐框架(Set-aligning Framework)。该框架融合了数据增强和集合属性正则化,旨在减轻与线性化图边序列相关的文本生成损失惩罚,从而鼓励生成更多的关系边。实验结果表明,我们的框架在事件时序图生成上超越了现有基线。此外,在零样本设置下,通过我们的框架引入的结构性知识显著提升了模型泛化能力,尤其是在可用训练样本有限的情况下。

英文摘要:

Event temporal graphs have been shown as convenient and effective representations of complex temporal relations between events in text. Recent studies, which employ pre-trained language models to auto-regressively generate linearised graphs for constructing event temporal graphs, have shown promising results. However, these methods have often led to suboptimal graph generation as the linearised graphs exhibit set characteristics which are instead treated sequentially by language models. This discrepancy stems from the conventional text generation objectives, leading to erroneous penalisation of correct predictions caused by the misalignment of elements in target sequences. To address these challenges, we reframe the task as a conditional set generation problem, proposing a Set-aligning Framework tailored for the effective utilisation of Large Language Models (LLMs). The framework incorporates data augmentations and set-property regularisations designed to alleviate text generation loss penalties associated with the linearised graph edge sequences, thus encouraging the generation of more relation edges. Experimental results show that our framework surpasses existing baselines for event temporal graph generation. Furthermore, under zero-shot settings, the structural knowledge introduced through our framework notably improves model generalisation, particularly when the training examples available are limited.

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。

↑