Home

/hkunlp/ Selective Annotation Makes Language Models Better Few-Shot Learners

Code Link
https://github.com/hkunlp/icl-selective-annotation
Description
Departing from recent in-context learning methods, we formulate an annotation-efficient, two-step framework: selective annotation that chooses a pool of examples to annotate from unlabeled data in advance, followed by prompt retrieval that retrieves task examples from the annotated pool at test time. Code: https://github.com/hkunlp/icl-selective-annotation
Retrieved
2022/09/09
Stars
23
TOP