# Semi-Supervised Few-Shot Learning for Dual Question-Answer Extraction

## TL;DR

This paper introduces SAMIE, a semi-supervised model for key phrase extraction that learns to ask and answer questions, enabling effective few-shot learning and outperforming supervised methods with limited labeled data.

## Contribution

The paper proposes SAMIE, a novel semi-supervised dual-question-answering model that improves key phrase extraction with minimal supervision and supports clustering analysis.

## Key findings

- Outperforms supervised methods with limited labeled data
- Supports few-shot learning effectively
- Enables clustering analysis without supervision

## Abstract

This paper addresses the problem of key phrase extraction from sentences. Existing state-of-the-art supervised methods require large amounts of annotated data to achieve good performance and generalization. Collecting labeled data is, however, often expensive. In this paper, we redefine the problem as question-answer extraction, and present SAMIE: Self-Asking Model for Information Ixtraction, a semi-supervised model which dually learns to ask and to answer questions by itself. Briefly, given a sentence $s$ and an answer $a$, the model needs to choose the most appropriate question $\hat q$; meanwhile, for the given sentence $s$ and same question $\hat q$ selected in the previous step, the model will predict an answer $\hat a$. The model can support few-shot learning with very limited supervision. It can also be used to perform clustering analysis when no supervision is provided. Experimental results show that the proposed method outperforms typical supervised methods especially when given little labeled data.