论文标题
提示提示？ PAIE：提示事件参数提取的参数交互
Prompt for Extraction? PAIE: Prompting Argument Interaction for Event Argument Extraction
论文作者
论文摘要
在本文中，我们为句子级别和文档级事件参数提取（EAE）提出了一个有效而有效的模型PAIE，当缺乏培训数据时，它也可以很好地概括。一方面，Paie利用提取目标的及时调整来利用预训练的语言模型（PLM）的最佳优势。它根据提示来介绍两个跨度选择器，以选择每个角色的输入文本之间的启动/结束令牌。另一方面，它通过多角色提示捕获了参数交互，并通过两部分匹配损失进行最佳跨度分配进行关节优化。此外，通过灵活的及时设计，PAIE可以提取具有相同角色的多个参数，而不是传统的启发式阈值调整。我们已经对包括句子和文档级的EAE在内的三个基准进行了广泛的实验。结果呈现出PAIE的有希望的改善（分别为PAIE-BASE和PAIE-RARGE的三个基准分别在三个基准测试基准上平均增加了）。进一步的分析证明了对几个弹药设置的效率，概括以及不同提取及时调整策略的有效性。我们的代码可从https://github.com/mayubo2333/paie获得。
In this paper, we propose an effective yet efficient model PAIE for both sentence-level and document-level Event Argument Extraction (EAE), which also generalizes well when there is a lack of training data. On the one hand, PAIE utilizes prompt tuning for extractive objectives to take the best advantages of Pre-trained Language Models (PLMs). It introduces two span selectors based on the prompt to select start/end tokens among input texts for each role. On the other hand, it captures argument interactions via multi-role prompts and conducts joint optimization with optimal span assignments via a bipartite matching loss. Also, with a flexible prompt design, PAIE can extract multiple arguments with the same role instead of conventional heuristic threshold tuning. We have conducted extensive experiments on three benchmarks, including both sentence- and document-level EAE. The results present promising improvements from PAIE (3.5\% and 2.3\% F1 gains in average on three benchmarks, for PAIE-base and PAIE-large respectively). Further analysis demonstrates the efficiency, generalization to few-shot settings, and effectiveness of different extractive prompt tuning strategies. Our code is available at https://github.com/mayubo2333/PAIE.
