KECP: Knowledge Enhanced Contrastive Prompting for Few-shot Extractive Question Answering

TL;DR

KECP introduces a novel knowledge-enhanced contrastive prompt-tuning framework that transforms extractive question answering into a masked language modeling task, significantly improving few-shot performance by leveraging external knowledge and contrastive learning.

Contribution

The paper proposes a new paradigm for EQA that replaces pointer heads with MLM-based generation and combines external knowledge with contrastive learning for better few-shot results.

Findings

Outperforms state-of-the-art in few-shot settings

Effectively leverages external knowledge bases

Transforms EQA into a non-autoregressive MLM task

Abstract

Extractive Question Answering (EQA) is one of the most important tasks in Machine Reading Comprehension (MRC), which can be solved by fine-tuning the span selecting heads of Pre-trained Language Models (PLMs). However, most existing approaches for MRC may perform poorly in the few-shot learning scenario. To solve this issue, we propose a novel framework named Knowledge Enhanced Contrastive Prompt-tuning (KECP). Instead of adding pointer heads to PLMs, we introduce a seminal paradigm for EQA that transform the task into a non-autoregressive Masked Language Modeling (MLM) generation problem. Simultaneously, rich semantics from the external knowledge base (KB) and the passage context are support for enhancing the representations of the query. In addition, to boost the performance of PLMs, we jointly train the model by the MLM and contrastive learning objectives. Experiments on multiple benchmarks demonstrate that our method consistently outperforms state-of-the-art approaches in few-shot settings by a large margin.