Transfer Learning for Relation Extraction via Relation-Gated Adversarial Learning
This work addresses the challenge of expensive human annotation and noisy data in relation extraction for NLP applications, but it is incremental as it builds on existing adversarial domain adaptation methods.
The paper tackles the problem of relation extraction across domains with mismatched label spaces by proposing a relation-gated adversarial learning model, which outperforms previous domain adaptation methods in partial domain adaptation and improves accuracy in distantly supervised relation extraction through fine-tuning.
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 relation 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.