Prompt-based Text Entailment for Low-Resource Named Entity Recognition

TL;DR

This paper introduces Prompt-based Text Entailment (PTE), a novel approach that reformulates low-resource named entity recognition as a text entailment task, leveraging PLMs more effectively with minimal labeled data.

Contribution

The paper proposes a new prompt-based reformulation of NER as text entailment, reducing reliance on extensive labeled data and improving performance in low-resource scenarios.

Findings

PTE achieves competitive results on CoNLL03 dataset.

PTE outperforms fine-tuned models on MIT Movie and Few-NERD datasets.

The method reduces time complexity by treating words as basic units.

Abstract

Pre-trained Language Models (PLMs) have been applied in NLP tasks and achieve promising results. Nevertheless, the fine-tuning procedure needs labeled data of the target domain, making it difficult to learn in low-resource and non-trivial labeled scenarios. To address these challenges, we propose Prompt-based Text Entailment (PTE) for low-resource named entity recognition, which better leverages knowledge in the PLMs. We first reformulate named entity recognition as the text entailment task. The original sentence with entity type-specific prompts is fed into PLMs to get entailment scores for each candidate. The entity type with the top score is then selected as final label. Then, we inject tagging labels into prompts and treat words as basic units instead of n-gram spans to reduce time complexity in generating candidates by n-grams enumeration. Experimental results demonstrate that the proposed method PTE achieves competitive performance on the CoNLL03 dataset, and better than fine-tuned counterparts on the MIT Movie and Few-NERD dataset in low-resource settings.