In-Context Learning for Few-Shot Nested Named Entity Recognition
Authors:
- 14 April 2024
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 10026-10030
Abstract
In nested Named entity recognition (NER), entities are nested with each other, and thus requiring more data annotations to address. This leads to the development of few-shot nested NER, where the prevalence of pretrained language models with in-context learning (ICL) offers promising solutions. In this work, we introduce an effective and innovative ICL framework for the setting of few-shot nested NER. We improve the ICL prompt by devising a novel example demonstration selection mechanism, EnDe retriever. In EnDe retriever, we employ contrastive learning to perform three types of representation learning, in terms of semantic similarity, boundary similarity, and label similarity, to generate high-quality demonstration examples. Extensive experiments over three nested NER and four flat NER datasets demonstrate the efficacy of our system.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China
- Baidu
This publication has 15 references indexed in Scilit:
- Focusing, Bridging and Prompting for Few-shot Nested Named Entity Recognition2023
- Unified Named Entity Recognition as Word-Word Relation ClassificationProceedings of the AAAI Conference on Artificial Intelligence, 2022
- Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?2022
- An Enhanced Span-based Decomposition Method for Few-Shot Sequence Labeling2022
- Few-shot Named Entity Recognition with Self-describing Networks2022
- Rethinking Boundaries: End-To-End Recognition of Discontinuous Mentions with Pointer NetworksProceedings of the AAAI Conference on Artificial Intelligence, 2021
- Better Combine Them Together! Integrating Syntactic Constituency and Dependency Representations for Semantic Role Labeling2021
- Locate and Label: A Two-stage Identifier for Nested Named Entity Recognition2021
- Boundaries and edges rethinking: An end-to-end neural model for overlapping entity relation extractionInformation Processing & Management, 2020
- Learning a Similarity Metric Discriminatively, with Application to Face Verification2005