Improving Distantly Supervised Document-Level Relation Extraction Through Natural Language Inference
Abstract
The distant supervision (DS) paradigm has been widely used for relation extraction (RE) to alleviate the need for expensive annotations. However, it suffers from noisy labels, which leads to worse performance than models trained on human-annotated data, even when trained using hundreds of times more data. We present a systematic study on the use of natural language inference (NLI) to improve distantly supervised document-level RE. We apply NLI in three scenarios: (i) as a filter for denoising DS labels, (ii) as a filter for model prediction, and (iii) as a standalone RE model. Our results show that NLI filtering consistently improves performance, reducing the performance gap with a model trained on human-annotated data by 2.3 F1.- Anthology ID:
- 2022.deeplo-1.2
- Volume:
- Proceedings of the Third Workshop on Deep Learning for Low-Resource Natural Language Processing
- Month:
- July
- Year:
- 2022
- Address:
- Hybrid
- Venue:
- DeepLo
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 14–20
- Language:
- URL:
- https://aclanthology.org/2022.deeplo-1.2
- DOI:
- 10.18653/v1/2022.deeplo-1.2
- Cite (ACL):
- Clara Vania, Grace Lee, and Andrea Pierleoni. 2022. Improving Distantly Supervised Document-Level Relation Extraction Through Natural Language Inference. In Proceedings of the Third Workshop on Deep Learning for Low-Resource Natural Language Processing, pages 14–20, Hybrid. Association for Computational Linguistics.
- Cite (Informal):
- Improving Distantly Supervised Document-Level Relation Extraction Through Natural Language Inference (Vania et al., DeepLo 2022)
- PDF:
- https://preview.aclanthology.org/auto-file-uploads/2022.deeplo-1.2.pdf
- Data
- DocRED