BvSP: Broad-view Soft Prompting for Few-Shot Aspect Sentiment Quad Prediction

TL;DR

This paper introduces BvSP, a novel soft prompting approach that leverages multiple templates and their correlations to improve few-shot aspect sentiment quad prediction, significantly outperforming existing methods.

Contribution

The paper proposes a broad-view soft prompting method that aggregates multiple templates considering their correlations, enhancing few-shot ASQP performance.

Findings

BvSP outperforms state-of-the-art methods in four few-shot settings.

Constructed a new balanced few-shot ASQP dataset (FSQP).

Demonstrated the effectiveness of template correlation modeling.

Abstract

Aspect sentiment quad prediction (ASQP) aims to predict four aspect-based elements, including aspect term, opinion term, aspect category, and sentiment polarity. In practice, unseen aspects, due to distinct data distribution, impose many challenges for a trained neural model. Motivated by this, this work formulates ASQP into the few-shot scenario, which aims for fast adaptation in real applications. Therefore, we first construct a few-shot ASQP dataset (FSQP) that contains richer categories and is more balanced for the few-shot study. Moreover, recent methods extract quads through a generation paradigm, which involves converting the input sentence into a templated target sequence. However, they primarily focus on the utilization of a single template or the consideration of different template orders, thereby overlooking the correlations among various templates. To tackle this issue, we further propose a Broadview Soft Prompting (BvSP) method that aggregates multiple templates with a broader view by taking into account the correlation between the different templates. Specifically, BvSP uses the pre-trained language model to select the most relevant k templates with Jensen-Shannon divergence. BvSP further introduces soft prompts to guide the pre-trained language model using the selected templates. Then, we aggregate the results of multi-templates by voting mechanism. Empirical results demonstrate that BvSP significantly outperforms the stateof-the-art methods under four few-shot settings and other public datasets. Our code and dataset are available at https://github.com/byinhao/BvSP.