All Entities are Not Created Equal: Examining the Long Tail for Ultra-Fine Entity Typing
This work proposes a novel heuristic to approximate the pre-training distribution of entities when the pre-training data is unknown, and demonstrates that entity-typing approaches that rely solely on the parametric knowledge of PLMs struggle significantly with entities at the long tail of the pre-training distribution.
Advait Deshmukh, Ashwin Umadi, Dananjay Srinivas et al.
· Joint Conference on Lexical... · 4 citations