 Key challenges:
(1) learning from text or names
(2) datasets towards special interests

Hamilton College

Han, X. (n.d.). More Data, More Relations, More Context and More Openness:
A Review and Outlook for Relation Extraction *, Retrieved June 4, 2022, from https://arxiv.org/pdf/2004.03186.pdf

More Relations, More Context and More Openness:
A Review and Outlook for Relation Extraction

(1) collecting high-quality human annotations is expensive and time-consuming


(2) many long-tail relations cannot provide large amounts
of training examples


(3) most facts are expressed by long context consisting of multiple sentences

(4) using a pre-defined set to cover those relations with open-ended growth is difficult

Learn Before

Related