Do the Benefits of Joint Models for Relation Extraction Extend to Document-level Tasks?
This work addresses the challenge of document-level relation extraction for NLP researchers, showing that joint models' benefits do not extend, which is incremental as it benchmarks existing methods on new data.
The paper investigated whether joint models, which outperform pipeline models for sentence-level relation extraction, maintain their advantage in document-level tasks, finding that joint models' performance drops sharply below pipeline models in the document-level setting.
Two distinct approaches have been proposed for relational triple extraction - pipeline and joint. Joint models, which capture interactions across triples, are the more recent development, and have been shown to outperform pipeline models for sentence-level extraction tasks. Document-level extraction is a more challenging setting where interactions across triples can be long-range, and individual triples can also span across sentences. Joint models have not been applied for document-level tasks so far. In this paper, we benchmark state-of-the-art pipeline and joint extraction models on sentence-level as well as document-level datasets. Our experiments show that while joint models outperform pipeline models significantly for sentence-level extraction, their performance drops sharply below that of pipeline models for the document-level dataset.