Document-Level Relation Extraction with Reconstruction

In document-level relation extraction (DocRE), graph structure is generally used to encode information in the input document classify category between each entity pair, and has greatly advanced DocRE task over past several years. However, learned representation universally models all pairs regardless of whether there are relationships these pairs. Thus, those without disperse attention encoder-classifier for ones with relationships, which may further hind improvement DocRE. To alleviate this issue, we propose a novel encoder-classifier-reconstructor model The reconstructor manages reconstruct ground-truth path dependencies from representation, ensure that proposed pays more training. Furthermore, regarded as relationship indicator assist classification inference, can improve performance model. Experimental results on large-scale dataset show significantly accuracy strong heterogeneous graph-based baseline. code publicly available at https://github.com/xwjim/DocRE-Rec.