Empirical Study of Mutual Reinforcement Effect and Application in Few-shot Text Classification Tasks via Prompt

TL;DR

This paper empirically investigates the Mutual Reinforcement Effect (MRE) in text classification, demonstrating its existence and leveraging it in prompt learning to improve classification performance across multiple datasets.

Contribution

It provides the first empirical validation of MRE and applies it to enhance few-shot text classification via prompt-based methods.

Findings

MRE exists and impacts model performance

Prompt learning with word-level info improves F1-score

Significant gains in 18 out of 21 datasets

Abstract

The Mutual Reinforcement Effect (MRE) investigates the synergistic relationship between word-level and text-level classifications in text classification tasks. It posits that the performance of both classification levels can be mutually enhanced. However, this mechanism has not been adequately demonstrated or explained in prior research. To address this gap, we employ empirical experiment to observe and substantiate the MRE theory. Our experiments on 21 MRE mix datasets revealed the presence of MRE in the model and its impact. Specifically, we conducted compare experiments use fine-tune. The results of findings from comparison experiments corroborates the existence of MRE. Furthermore, we extended the application of MRE to prompt learning, utilizing word-level information as a verbalizer to bolster the model's prediction of text-level classification labels. In our final experiment, the F1-score significantly surpassed the baseline in 18 out of 21 MRE Mix datasets, further validating the notion that word-level information enhances the language model's comprehension of the text as a whole.