论文标题
检索提取的生成问题回答事件参数提取
Retrieval-Augmented Generative Question Answering for Event Argument Extraction
论文作者
论文摘要
长期以来，将事件参数提取作为基于提取性方法的顺序预测问题，并以隔离为基础。尽管最近的工作提出了基于生成的方法来捕获跨题词依赖性，但它们需要生成和后处理复杂的目标序列（模板）。这些观察结果和最近验证的语言模型从示范中学习的能力所激发。我们为事件参数提取提出了一个检索式生成质量质量质量质量质量质量质量模型（R-GQA）。它检索了最相似的质量检查对，并将其作为提示将其扩展到当前示例的上下文中，然后将参数解码为答案。我们的方法在各种环境（即完全监督，域转移和少数图的学习）上的表现要优于先前的方法。最后，我们提出了一种基于聚类的抽样策略（联合），并对不同策略如何影响少数学习绩效进行了详尽的分析。该实现可在https：// github.com/xinyadu/rgqa上获得
Event argument extraction has long been studied as a sequential prediction problem with extractive-based methods, tackling each argument in isolation. Although recent work proposes generation-based methods to capture cross-argument dependency, they require generating and post-processing a complicated target sequence (template). Motivated by these observations and recent pretrained language models' capabilities of learning from demonstrations. We propose a retrieval-augmented generative QA model (R-GQA) for event argument extraction. It retrieves the most similar QA pair and augments it as prompt to the current example's context, then decodes the arguments as answers. Our approach outperforms substantially prior methods across various settings (i.e. fully supervised, domain transfer, and fewshot learning). Finally, we propose a clustering-based sampling strategy (JointEnc) and conduct a thorough analysis of how different strategies influence the few-shot learning performance. The implementations are available at https:// github.com/xinyadu/RGQA
