Document-level Relation Extraction with Cross-sentence Reasoning Graph
This work addresses document-level relation extraction for natural language processing applications, representing an incremental improvement over prior graph-based methods.
The paper tackles the problem of document-level relation extraction by addressing redundant information in existing graph-based models and the lack of global cross-sentence entity interactions, proposing GRACR which achieves excellent performance on public datasets and is particularly effective for cross-sentence entity pairs.
Relation extraction (RE) has recently moved from the sentence-level to document-level, which requires aggregating document information and using entities and mentions for reasoning. Existing works put entity nodes and mention nodes with similar representations in a document-level graph, whose complex edges may incur redundant information. Furthermore, existing studies only focus on entity-level reasoning paths without considering global interactions among entities cross-sentence. To these ends, we propose a novel document-level RE model with a GRaph information Aggregation and Cross-sentence Reasoning network (GRACR). Specifically, a simplified document-level graph is constructed to model the semantic information of all mentions and sentences in a document, and an entity-level graph is designed to explore relations of long-distance cross-sentence entity pairs. Experimental results show that GRACR achieves excellent performance on two public datasets of document-level RE. It is especially effective in extracting potential relations of cross-sentence entity pairs. Our code is available at https://github.com/UESTC-LHF/GRACR.