CorefDRE: Document-level Relation Extraction with coreference resolution
This work improves relation extraction for documents with cross-sentence pronouns, offering a domain-specific advancement in natural language processing.
The paper tackles document-level relation extraction by addressing pronoun ambiguity across sentences, introducing a mention-pronoun coreference resolution and noise suppression mechanism to enhance graph-based semantic representation. Experiments on datasets like DocRED show it outperforms state-of-the-art methods.
Document-level relation extraction is to extract relation facts from a document consisting of multiple sentences, in which pronoun crossed sentences are a ubiquitous phenomenon against a single sentence. However, most of the previous works focus more on mentions coreference resolution except for pronouns, and rarely pay attention to mention-pronoun coreference and capturing the relations. To represent multi-sentence features by pronouns, we imitate the reading process of humans by leveraging coreference information when dynamically constructing a heterogeneous graph to enhance semantic information. Since the pronoun is notoriously ambiguous in the graph, a mention-pronoun coreference resolution is introduced to calculate the affinity between pronouns and corresponding mentions, and the noise suppression mechanism is proposed to reduce the noise caused by pronouns. Experiments on the public dataset, DocRED, DialogRE and MPDD, show that Coref-aware Doc-level Relation Extraction based on Graph Inference Network outperforms the state-of-the-art.