CrossRE: A Cross-Domain Dataset for Relation Extraction
This addresses the problem of evaluating relation extraction systems in realistic, cross-domain scenarios for researchers, though it is incremental as it primarily provides a new dataset.
The authors tackled the lack of out-of-distribution evaluation in relation extraction by introducing CrossRE, a cross-domain benchmark with six text domains and multi-label annotations, finding that cross-domain RE is difficult based on empirical evaluation with a state-of-the-art model.
Relation Extraction (RE) has attracted increasing attention, but current RE evaluation is limited to in-domain evaluation setups. Little is known on how well a RE system fares in challenging, but realistic out-of-distribution evaluation setups. To address this gap, we propose CrossRE, a new, freely-available cross-domain benchmark for RE, which comprises six distinct text domains and includes multi-label annotations. An additional innovation is that we release meta-data collected during annotation, to include explanations and flags of difficult instances. We provide an empirical evaluation with a state-of-the-art model for relation classification. As the meta-data enables us to shed new light on the state-of-the-art model, we provide a comprehensive analysis on the impact of difficult cases and find correlations between model and human annotations. Overall, our empirical investigation highlights the difficulty of cross-domain RE. We release our dataset, to spur more research in this direction.