Joint Extraction of Entities, Relations, and Events via Modeling Inter-Instance and Inter-Label Dependencies
Joint Extraction of Entities, Relations, and Events via Modeling Inter-Instance and Inter-Label Dependencies
复制标题
DOI：
10.18653/v1/2022.naacl-main.324
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Minh Le Nguyen;Bonan Min;Franck Dernoncourt;Thien Huu Nguyen
中科院分区：
文献类型：
--
作者：
Minh Le Nguyen;Bonan Min;Franck Dernoncourt;Thien Huu Nguyen
事件触发器检测、实体提及识别、事件变元提取和关系提取是信息提取中的四个重要任务，它们已经联合执行（联合信息提取- JointIE）以避免错误传播并利用任务实例之间的依赖性（即，事件触发器、实体提及、关系和事件变元）。然而，以前的JointIE模型往往假设启发式手动设计的依赖关系之间的任务实例和平均场因子分解的联合分布的实例标签，从而无法捕捉最佳的依赖关系之间的实例和标签，以提高表示学习和IE性能。为了克服这些限制，我们建议从数据中诱导任务实例之间的依赖图，以促进表示学习。为了更好地捕捉实例标签之间的依赖关系，我们建议通过条件随机场直接估计它们的联合分布。引入噪声对比估计来解决模型训练中难以处理的联合似然最大化问题。最后，为了改进先前工作中使用贪婪或波束搜索的解码，我们提出了模拟退火，以便在解码时更好地找到实例标签的全局最优分配。实验结果表明，我们提出的模型优于以前的模型在多个IE任务在5个数据集和2种语言。
Event trigger detection, entity mention recognition, event argument extraction, and relation extraction are the four important tasks in information extraction that have been performed jointly (Joint Information Extraction - JointIE) to avoid error propagation and leverage dependencies between the task instances (i.e., event triggers, entity mentions, relations, and event arguments). However, previous JointIE models often assume heuristic manually-designed dependency between the task instances and mean-field factorization for the joint distribution of instance labels, thus unable to capture optimal dependencies among instances and labels to improve representation learning and IE performance. To overcome these limitations, we propose to induce a dependency graph among task instances from data to boost representation learning. To better capture dependencies between instance labels, we propose to directly estimate their joint distribution via Conditional Random Fields. Noise Contrastive Estimation is introduced to address the maximization of the intractable joint likelihood for model training. Finally, to improve the decoding with greedy or beam search in prior work, we present Simulated Annealing to better find the globally optimal assignment for instance labels at decoding time. Experimental results show that our proposed model outperforms previous models on multiple IE tasks across 5 datasets and 2 languages.