Inverse is Better! Fast and Accurate Prompt for Few-shot Slot Tagging

TL;DR

This paper introduces an inverse prompting paradigm for few-shot slot tagging that predicts slot values given slot types, significantly improving speed and accuracy over traditional methods by reducing the need for enumerating token spans.

Contribution

The paper proposes a novel inverse prompting approach and an iterative prediction strategy, achieving faster and more accurate few-shot slot tagging results.

Findings

Speeds up prediction by avoiding enumeration of token spans.

Improves F1-score by over 6.1 points in 10-shot setting.

Achieves new state-of-the-art performance in few-shot slot tagging.

Abstract

Prompting methods recently achieve impressive success in few-shot learning. These methods modify input samples with prompt sentence pieces, and decode label tokens to map samples to corresponding labels. However, such a paradigm is very inefficient for the task of slot tagging. Since slot tagging samples are multiple consecutive words in a sentence, the prompting methods have to enumerate all n-grams token spans to find all the possible slots, which greatly slows down the prediction. To tackle this, we introduce an inverse paradigm for prompting. Different from the classic prompts mapping tokens to labels, we reversely predict slot values given slot types. Such inverse prompting only requires a one-turn prediction for each slot type and greatly speeds up the prediction. Besides, we propose a novel Iterative Prediction Strategy, from which the model learns to refine predictions by considering the relations between different slot types. We find, somewhat surprisingly, the proposed method not only predicts faster but also significantly improves the effect (improve over 6.1 F1-scores on 10-shot setting) and achieves new state-of-the-art performance.