Calibrated Seq2seq Models for Efficient and Generalizable Ultra-fine Entity Typing. (arXiv:2311.00835v1 [cs.CL])

Ultra-fine entity typing plays a crucial role in information extraction by
predicting fine-grained semantic types for entity mentions in text. However,
this task poses significant challenges due to the massive number of entity
types in the output space. The current state-of-the-art approaches, based on
standard multi-label classifiers or cross-encoder models, suffer from poor
generalization performance or inefficient inference. In this paper, we present
CASENT, a seq2seq model designed for ultra-fine entity typing that predicts
ultra-fine types with calibrated confidence scores. …

art arxiv challenges classifiers current extraction fine-grained information information extraction massive role semantic seq2seq space standard state text types typing