Semi-supervised Relation Extraction via Incremental Meta Self-Training
Xuming Hu, Chenwei Zhang, Fukun Ma, Chenyao Liu, Lijie Wen, Philip S. Yu
Abstract
To alleviate human efforts from obtaining large-scale annotations, Semi-Supervised Relation Extraction methods aim to leverage unlabeled data in addition to learning from limited samples. Existing self-training methods suffer from the gradual drift problem, where noisy pseudo labels on unlabeled data are incorporated during training. To alleviate the noise in pseudo labels, we propose a method called MetaSRE, where a Relation Label Generation Network generates accurate quality assessment on pseudo labels by (meta) learning from the successful and failed attempts on Relation Classification Network as an additional meta-objective. To reduce the influence of noisy pseudo labels, MetaSRE adopts a pseudo label selection and exploitation scheme which assesses pseudo label quality on unlabeled samples and only exploits high-quality pseudo labels in a self-training fashion to incrementally augment labeled samples for both robustness and accuracy. Experimental results on two public datasets demonstrate the effectiveness of the proposed approach.- Anthology ID:
- 2021.findings-emnlp.44
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2021
- Month:
- November
- Year:
- 2021
- Address:
- Punta Cana, Dominican Republic
- Venue:
- Findings
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 487–496
- Language:
- URL:
- https://aclanthology.org/2021.findings-emnlp.44
- DOI:
- 10.18653/v1/2021.findings-emnlp.44
- Cite (ACL):
- Xuming Hu, Chenwei Zhang, Fukun Ma, Chenyao Liu, Lijie Wen, and Philip S. Yu. 2021. Semi-supervised Relation Extraction via Incremental Meta Self-Training. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 487–496, Punta Cana, Dominican Republic. Association for Computational Linguistics.
- Cite (Informal):
- Semi-supervised Relation Extraction via Incremental Meta Self-Training (Hu et al., Findings 2021)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2021.findings-emnlp.44.pdf
- Code
- THU-BPM/MetaSRE