TPLinker: Single-stage Joint Extraction of Entities and Relations Through Token Pair Linking

Understand

Extracting entities and relations from unstructured text has attracted increasing attention in recent years but remains challenging, due to the intrinsic difficulty in identifying overlapping relations with shared entities.

• Prior works show that joint learning can result in a noticeable performance gain.
• However, they usually involve sequential interrelated steps and suffer from the problem of exposure bias.
• At training time, they predict with the ground truth conditions while at inference it has to make extraction from scratch.