Neural Snowball for Few-Shot Relation Learning

Understand

Knowledge graphs typically undergo open-ended growth of new relations.

• This cannot be well handled by relation extraction that focuses on pre-defined relations with sufficient training data.
• To address new relations with few-shot instances, we propose a novel bootstrapping approach, Neural Snowball, to learn new relations by transferring semantic knowledge about existing relations.
• More specifically, we use Relational Siamese Networks (RSN) to learn the metric of relational similarities between instances based on existing relations and their labeled data.