论文标题
文档级别关系提取的粗到定义实体表示
Coarse-to-Fine Entity Representations for Document-level Relation Extraction
论文作者
论文摘要
文档级别的关系提取（RE）需要提取在句子内和跨句子内表达的关系。最近的作品表明，基于图的方法通常构建捕获文档感知交互的文档级图，可以获得有用的实体表示，从而有助于解决文档级别的re。这些方法要么更多地关注整个图表，要么更多地关注图形的一部分，例如目标实体对之间的路径。但是，我们发现文档级RE可能会同时关注它们。因此，为了获得更全面的实体表示形式，我们提出了采用涉及两个阶段的粗到精细策略的粗到十个实体表示模型（CFER）。首先，CFER使用图形神经网络将整个图表中的全局信息集成在粗级别上。接下来，CFER利用全局信息作为指导，以良好的级别在目标实体对之间有选择性地汇总路径信息。在分类中，我们将两个级别的实体表示形式结合到更全面的关系提取。对两个文档级RE数据集（DOCRED和CDR）的实验结果表明，CFER表现优于现有模型，并且对不均匀的标签分布非常有力。
Document-level Relation Extraction (RE) requires extracting relations expressed within and across sentences. Recent works show that graph-based methods, usually constructing a document-level graph that captures document-aware interactions, can obtain useful entity representations thus helping tackle document-level RE. These methods either focus more on the entire graph, or pay more attention to a part of the graph, e.g., paths between the target entity pair. However, we find that document-level RE may benefit from focusing on both of them simultaneously. Therefore, to obtain more comprehensive entity representations, we propose the Coarse-to-Fine Entity Representation model (CFER) that adopts a coarse-to-fine strategy involving two phases. First, CFER uses graph neural networks to integrate global information in the entire graph at a coarse level. Next, CFER utilizes the global information as a guidance to selectively aggregate path information between the target entity pair at a fine level. In classification, we combine the entity representations from both two levels into more comprehensive representations for relation extraction. Experimental results on two document-level RE datasets, DocRED and CDR, show that CFER outperforms existing models and is robust to the uneven label distribution.
