TKDP: Threefold Knowledge-enriched Deep Prompt Tuning for Few-shot Named Entity Recognition

TL;DR

This paper introduces TKDP, a knowledge-enriched deep prompt tuning framework that integrates internal context, external label, and sememe knowledge to significantly improve few-shot NER performance across multiple datasets.

Contribution

The paper proposes a novel threefold knowledge integration into deep prompt tuning for few-shot NER, enhancing performance over existing methods.

Findings

Boosts up to 11.53% F1 over raw deep prompt methods

Outperforms 8 strong baselines in various few-shot settings

Demonstrates broad adaptability to other few-shot tasks

Abstract

Few-shot named entity recognition (NER) exploits limited annotated instances to identify named mentions. Effectively transferring the internal or external resources thus becomes the key to few-shot NER. While the existing prompt tuning methods have shown remarkable few-shot performances, they still fail to make full use of knowledge. In this work, we investigate the integration of rich knowledge to prompt tuning for stronger few-shot NER. We propose incorporating the deep prompt tuning framework with threefold knowledge (namely TKDP), including the internal 1) context knowledge and the external 2) label knowledge & 3) sememe knowledge. TKDP encodes the three feature sources and incorporates them into the soft prompt embeddings, which are further injected into an existing pre-trained language model to facilitate predictions. On five benchmark datasets, our knowledge-enriched model boosts by at most 11.53% F1 over the raw deep prompt method, and significantly outperforms 8 strong-performing baseline systems in 5-/10-/20-shot settings, showing great potential in few-shot NER. Our TKDP can be broadly adapted to other few-shot tasks without effort.