Learning In-context Learning for Named Entity Recognition

05/18/2023

∙

by   Jiawei Chen, et al.

∙

0

∙

share

Named entity recognition in real-world applications suffers from the diversity of entity types, the emergence of new entity types, and the lack of high-quality annotations. To address the above problems, this paper proposes an in-context learning-based NER approach, which can effectively inject in-context NER ability into PLMs and recognize entities of novel types on-the-fly using only a few demonstrative instances. Specifically, we model PLMs as a meta-function λ_ 𝒾𝓃𝓈𝓉𝓇𝓊𝒸𝓉𝒾ℴ𝓃, 𝒹ℯ𝓂ℴ𝓃𝓈𝓉𝓇𝒶𝓉𝒾ℴ𝓃𝓈, 𝓉ℯ𝓍𝓉. ℳ, and a new entity extractor can be implicitly constructed by applying new instruction and demonstrations to PLMs, i.e., (λ . ℳ)(instruction, demonstrations) → ℱ where ℱ will be a new entity extractor, i.e., ℱ: text → entities. To inject the above in-context NER ability into PLMs, we propose a meta-function pre-training algorithm, which pre-trains PLMs by comparing the (instruction, demonstration)-initialized extractor with a surrogate golden extractor. Experimental results on 4 few-shot NER datasets show that our method can effectively inject in-context NER ability into PLMs and significantly outperforms the PLMs+fine-tuning counterparts.