An Improved Baseline for Sentence-level Relation Extraction.

Sentence-level relation extraction (RE) aims at identifying the relationship between two entities in a sentence. Many efforts have been devoted to this problem, while the best performing methods are still far behind human performance. In this paper, we revisit two aspects of RE models that are not thoroughly studied, namely entity representation and NA instance prediction. Our improved baseline model, incorporated with entity representations with type markers and confidence-based classification for enhanced NA instance detection, achieves an F1 of 75.0% on TACRED, significantly outperforms previous SOTA methods.