NC-DRE: Leveraging Non-entity Clue Information for Document-level Relation Extraction
This work improves document-level relation extraction for natural language processing applications by enhancing reasoning over complex inter-sentence relations, though it is incremental as it builds on existing graph-based frameworks.
The paper tackles the problem of document-level relation extraction by addressing the limitation of existing graph-based methods that ignore non-entity clue words, proposing NC-DRE which introduces a decoder-to-encoder attention mechanism to leverage this information, achieving state-of-the-art performance on benchmark datasets (e.g., 63.5 F1 on DocRED).
Document-level relation extraction (RE), which requires reasoning on multiple entities in different sentences to identify complex inter-sentence relations, is more challenging than sentence-level RE. To extract the complex inter-sentence relations, previous studies usually employ graph neural networks (GNN) to perform inference upon heterogeneous document-graphs. Despite their great successes, these graph-based methods, which normally only consider the words within the mentions in the process of building graphs and reasoning, tend to ignore the non-entity clue words that are not in the mentions but provide important clue information for relation reasoning. To alleviate this problem, we treat graph-based document-level RE models as an encoder-decoder framework, which typically uses a pre-trained language model as the encoder and a GNN model as the decoder, and propose a novel graph-based model NC-DRE that introduces decoder-to-encoder attention mechanism to leverage Non-entity Clue information for Document-level Relation Extraction.