Transfer Learning for Relation Extraction via Relation-Gated Adversarial Learning [article]

Ningyu Zhang, Shumin Deng, Zhanlin Sun, Jiaoyan Chen, Wei Zhang, Huajun Chen
2019 arXiv   pre-print
Relation extraction aims to extract relational facts from sentences. Previous models mainly rely on manually labeled datasets, seed instances or human-crafted patterns, and distant supervision. However, the human annotation is expensive, while human-crafted patterns suffer from semantic drift and distant supervision samples are usually noisy. Domain adaptation methods enable leveraging labeled data from a different but related domain. However, different domains usually have various textual
more » ... ion descriptions and different label space (the source label space is usually a superset of the target label space). To solve these problems, we propose a novel model of relation-gated adversarial learning for relation extraction, which extends the adversarial based domain adaptation. Experimental results have shown that the proposed approach outperforms previous domain adaptation methods regarding partial domain adaptation and can improve the accuracy of distance supervised relation extraction through fine-tuning.
arXiv:1908.08507v1 fatcat:3dicu6q6kvfxrex3pfr5rezvkm