Reasoning with Latent Structure Refinement for Document-Level Relation Extraction
Preprint
Abstract
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.Keywords
All Related Versions
This publication has 13 references indexed in Scilit:
- Densely Connected Graph Convolutional Networks for Graph-to-Sequence LearningTransactions of the Association for Computational Linguistics, 2019
- Constructing Datasets for Multi-hop Reading Comprehension Across DocumentsTransactions of the Association for Computational Linguistics, 2018
- Learning Structured Text RepresentationsTransactions of the Association for Computational Linguistics, 2018
- An effective neural model extracting document level chemical-induced disease relations from biomedical literatureJournal of Biomedical Informatics, 2018
- Linguistic Properties Matter for Implicit Discourse Relation Recognition: Combining Semantic Interaction, Topic Continuity and AttributionProceedings of the AAAI Conference on Artificial Intelligence, 2018
- Cross-Sentence N-ary Relation Extraction with Graph LSTMsTransactions of the Association for Computational Linguistics, 2017
- Chemical-induced disease relation extraction via convolutional neural networkDatabase: The Journal of Biological Databases and Curation, 2017
- Improving chemical disease relation extraction with rich features and weakly labeled dataJournal of Cheminformatics, 2016
- BioCreative V CDR task corpus: a resource for chemical disease relation extractionDatabase: The Journal of Biological Databases and Curation, 2016
- Semantic Relation Classification via Convolutional Neural Networks with Simple Negative Sampling2015