← Search

Arzoo Katiyar

2 accepted papers

2022

CONTaiNER: Few-Shot Named Entity Recognition via Contrastive Learning

ACL 2022long

Named Entity Recognition (NER) in Few-Shot setting is imperative for entity tagging in low resource domains. Existing approaches only learn class-specific semantic features and intermediate representations from source domains. This affects generalizability to unseen target domains, resulting in subo…

2021

Revisiting Few-sample BERT Fine-tuning

ICLR 2021poster

This paper is a study of fine-tuning of BERT contextual representations, with focus on commonly observed instabilities in few-sample scenarios. We identify several factors that cause this instability: the common use of a non-standard optimization method with biased gradient estimation; the limited a…