论文标题
探测和微调阅读理解模型，用于几次事件提取
Probing and Fine-tuning Reading Comprehension Models for Few-shot Event Extraction
论文作者
论文摘要
我们研究了从文本数据中提取事件的问题，这既需要检测目标事件类型及其参数。通常，事件检测和参数检测子任务均以监督序列标记问题进行配制。我们认为，如此受过训练的事件提取模型本质上是渴望的标签，并且可以在域和文本类型中概括不佳。我们为事件提取提出了一个阅读理解框架。特别是，我们将事件检测作为文本构成预测问题，而参数检测是一个问题答案问题。通过构建适当的查询模板，我们的方法可以有效地提炼有关任务的丰富知识，并从预读的阅读理解模型中标记语义。此外，我们的模型可以通过少量数据进行微调以提高其性能。我们的实验结果表明，我们的方法对零射击和少量事件提取的性能强烈，并且在接受全面监督培训时，它可以在ACE 2005基准中实现最先进的性能。
We study the problem of event extraction from text data, which requires both detecting target event types and their arguments. Typically, both the event detection and argument detection subtasks are formulated as supervised sequence labeling problems. We argue that the event extraction models so trained are inherently label-hungry, and can generalize poorly across domains and text genres.We propose a reading comprehension framework for event extraction.Specifically, we formulate event detection as a textual entailment prediction problem, and argument detection as a question answer-ing problem. By constructing proper query templates, our approach can effectively distill rich knowledge about tasks and label semantics from pretrained reading comprehension models. Moreover, our model can be fine-tuned with a small amount of data to boost its performance. Our experiment results show that our method performs strongly for zero-shot and few-shot event extraction, and it achieves state-of-the-art performance on the ACE 2005 benchmark when trained with full supervision.
