Litcius/Paper detail

TKDP: Threefold Knowledge-Enriched Deep Prompt Tuning for Few-Shot Named Entity Recognition

Jiang Liu, Hao Fei, Fei Li, Jingye Li, Bobo Li, Liang Zhao, Chong Teng, Donghong Ji

2024IEEE Transactions on Knowledge and Data Engineering16 citationsDOIOpen Access PDF

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 <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">TKDP</i> ), including the internal 1) <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">context knowledge</i> and the external 2) <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">label knowledge</i> & 3) <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">sememe knowledge</i> . TKDP encodes the three feature sources and incorporates them into soft prompt embeddings, which are further injected into an existing pre-trained language model to facilitate predictions. On five benchmark datasets, the performance of our knowledge-enriched model was boosted by at most 11.53% F1 over the raw deep prompt method, and it significantly outperforms 9 strong-performing baseline systems in 5-/10-/20-shot settings, showing great potential in few-shot NER. Our TKDP framework can be broadly adapted to other few-shot tasks without much effort.

Topics & Concepts

Computer sciencePhysicsNatural Language Processing TechniquesNetwork Packet Processing and OptimizationTopic Modeling
TKDP: Threefold Knowledge-Enriched Deep Prompt Tuning for Few-Shot Named Entity Recognition | Litcius