DocRED: A Large-Scale Document-Level Relation Extraction Dataset

Multiple entities in a document generally exhibit complex inter-sentence relations, and cannot be well handled by existing relation extraction (RE) methods that typically focus on extracting intra-sentence relations for single entity pairs. In order to accelerate the research on document-level RE, we introduce DocRED, a new dataset constructed from Wikipedia and Wikidata with three features: (1) DocRED annotates both named entities and relations, and is the largest human-annotated dataset for document-level RE from plain text; (2) DocRED requires reading multiple sentences in a document to extract entities and infer their relations by synthesizing all information of the document; (3) along with the human-annotated data, we also offer large-scale distantly supervised data, which enables DocRED to be adopted for both supervised and weakly supervised scenarios. In order to verify the challenges of document-level RE, we implement recent state-of-the-art methods for RE and conduct a thorough evaluation of these methods on DocRED. Empirical results show that DocRED is challenging for existing RE methods, which indicates that document-level RE remains an open problem and requires further efforts. Based on the detailed analysis on the experiments, we discuss multiple promising directions for future research.

PDF Abstract ACL 2019 PDF ACL 2019 Abstract

Datasets


Introduced in the Paper:

DocRED

Used in the Paper:

SemEval-2010 Task 8 BC5CDR FewRel

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Relation Extraction DocRED DocRED-Context-Aware F1 50.64 # 52
Ign F1 43.93 # 49
Relation Extraction DocRED DocRED-CNN F1 42.33 # 54
Ign F1 36.44 # 51
Relation Extraction DocRED BiLSTM F1 50.12 # 53
Ign F1 43.60 # 50
F1 51.06 # 51
Ign F1 44.73 # 48

Methods


No methods listed for this paper. Add relevant methods here