Document-Level Event Argument Extraction (DocEAE) is an extremely difficult information extraction problem -- with significant limitations in low-resource cross-domain settings. To address this problem, we introduce Mad Lib Aug (MLA), a novel generative DocEAE data augmentation framework. Our approach leverages the intuition that Mad Libs, which are categorically masked documents used as a part of a popular game, can be generated and solved by LLMs to produce data for DocEAE. Using MLA, we achieve a 2.6-point average improvement in overall F1 score. Moreover, this approach achieves a 3.9 and 5.2 point average increase in zero and few-shot event roles compared to augmentation-free baselines across all experiments. To better facilitate analysis of cross-domain DocEAE, we additionally introduce a new metric, Role-Depth F1 (RDF1), which uses statistical depth to identify roles in the target domain which are semantic outliers with respect to roles observed in the source domain. Our experiments show that MLA augmentation can boost RDF1 performance by an average of 5.85 points compared to non-augmented datasets.
翻译:暂无翻译