Three Sentences Are All You Need: Local Path Enhanced Document Relation Extraction
This addresses the challenge of multi-sentence reasoning in document-level relation extraction for NLP researchers, though it is incremental as it builds on existing methods like BiLSTM.
The paper tackles document-level relation extraction by proposing a simple heuristic to select evidence sentences, achieving better performance than graph neural network methods on benchmark datasets.
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.