Reasoning with Latent Structure Refinement for Document-Level Relation Extraction

ACL 2020  ·  Guoshun Nan, Zhijiang Guo, Ivan Sekulić, Wei Lu ·

Document-level relation extraction requires integrating information within and across multiple sentences of a document and capturing complex interactions between inter-sentence entities. However, effective aggregation of relevant information in the document remains a challenging research question. Existing approaches construct static document-level graphs based on syntactic trees, co-references or heuristics from the unstructured text to model the dependencies. Unlike previous methods that may not be able to capture rich non-local interactions for inference, we propose a novel model that empowers the relational reasoning across sentences by automatically inducing the latent document-level graph. We further develop a refinement strategy, which enables the model to incrementally aggregate relevant information for multi-hop reasoning. Specifically, our model achieves an F1 score of 59.05 on a large-scale document-level dataset (DocRED), significantly improving over the previous results, and also yields new state-of-the-art results on the CDR and GDA dataset. Furthermore, extensive analyses show that the model is able to discover more accurate inter-sentence relations.

PDF Abstract ACL 2020 PDF ACL 2020 Abstract


Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Relation Extraction CDR LSR w/o MDP Nodes F1 64.8 # 9
Relation Extraction DocRED LSR+BERT-base F1 59.05 # 30
Ign F1 56.97 # 30
Relation Extraction DocRED LSR+GloVe F1 54.18 # 46
Ign F1 52.15 # 46
Relation Extraction GDA LSR w/o MDP Nodes F1 82.2 # 9


No methods listed for this paper. Add relevant methods here