Abstract
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 \textbf{C}oarse-to-\textbf{F}ine \textbf{E}ntity \textbf{R}epresentation model (\textbf{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 a large-scale document-level RE dataset show that CFER achieves better performance than previous baseline models. Further, we verify the effectiveness of our strategy through elaborate model analysis.
Abstract (translated)
URL
https://arxiv.org/abs/2012.02507
