A Multi-Task Semantic Decomposition Framework with Task-specific Pre-training for Few-Shot NER

TL;DR

This paper introduces a novel multi-task semantic decomposition framework with task-specific pre-training to improve few-shot NER, leveraging demonstration-based and contrastive learning to enhance entity representations and boundary detection.

Contribution

It proposes two new pre-training tasks and a multi-task joint optimization framework that significantly improves few-shot NER performance over existing methods.

Findings

MSDP outperforms strong baselines on two benchmarks.

The framework effectively incorporates entity boundary information.

Extensive analysis confirms its robustness and generalization.

Abstract

The objective of few-shot named entity recognition is to identify named entities with limited labeled instances. Previous works have primarily focused on optimizing the traditional token-wise classification framework, while neglecting the exploration of information based on NER data characteristics. To address this issue, we propose a Multi-Task Semantic Decomposition Framework via Joint Task-specific Pre-training (MSDP) for few-shot NER. Drawing inspiration from demonstration-based and contrastive learning, we introduce two novel pre-training tasks: Demonstration-based Masked Language Modeling (MLM) and Class Contrastive Discrimination. These tasks effectively incorporate entity boundary information and enhance entity representation in Pre-trained Language Models (PLMs). In the downstream main task, we introduce a multi-task joint optimization framework with the semantic decomposing method, which facilitates the model to integrate two different semantic information for entity classification. Experimental results of two few-shot NER benchmarks demonstrate that MSDP consistently outperforms strong baselines by a large margin. Extensive analyses validate the effectiveness and generalization of MSDP.