Three Sentences Are All You Need: Local Path Enhanced Document Relation Extraction
Document-level Relation Extraction (RE) is a more challenging task than sentence RE as it often requires reasoning over multiple sentences. Yet, human annotators usually use a small number of sentences to identify the relationship between a given entity pair. In this paper, we present an embarrassingly simple but effective method to heuristically select evidence sentences for document-level RE, which can be easily combined with BiLSTM to achieve good performance on benchmark datasets, even better than fancy graph neural network based methods. We have released our code at https://github.com/AndrewZhe/Three-Sentences-Are-All-You-Need.
PDF Abstract ACL 2021 PDF ACL 2021 Abstract
Datasets
DocRED
| Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
|---|---|---|---|---|---|---|
| Relation Extraction | DocRED | Paths+BiLSTM-GloVe | F1 | 56.23 | # 48 |
