TY - CHAP
T1 - Set-Aligning Framework for Auto-Regressive Event Temporal Graph Generation
AU - Tan, Xingwei
AU - Zhou, Yuxiang
AU - Pergola, Gabriele
AU - He, Yulan
N1 - Publisher Copyright:
©2024 Association for Computational Linguistics.
PY - 2024
Y1 - 2024
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85198261467&partnerID=8YFLogxK
M3 - Conference paper
AN - SCOPUS:85198261467
T3 - Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2024
SP - 3872
EP - 3892
BT - Long Papers
A2 - Duh, Kevin
A2 - Gomez, Helena
A2 - Bethard, Steven
PB - Association for Computational Linguistics (ACL)
T2 - 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2024
Y2 - 16 June 2024 through 21 June 2024
ER -