Few-shot Cross-lingual Aspect-Based Sentiment Analysis with Sequence-to-Sequence Models

TL;DR

This paper demonstrates that incorporating a small number of target language examples in cross-lingual aspect-based sentiment analysis significantly enhances performance, often surpassing monolingual baselines, especially in low-resource settings.

Contribution

It evaluates the impact of few-shot target language examples in cross-lingual ABSA using sequence-to-sequence models, highlighting practical improvements over zero-shot methods.

Findings

Adding ten target language examples improves performance markedly.

Combining 1,000 target examples with English data can outperform monolingual baselines.

Few-shot examples are practical and highly effective for low-resource ABSA.

Abstract

Aspect-based sentiment analysis (ABSA) has received substantial attention in English, yet challenges remain for low-resource languages due to the scarcity of labelled data. Current cross-lingual ABSA approaches often rely on external translation tools and overlook the potential benefits of incorporating a small number of target language examples into training. In this paper, we evaluate the effect of adding few-shot target language examples to the training set across four ABSA tasks, six target languages, and two sequence-to-sequence models. We show that adding as few as ten target language examples significantly improves performance over zero-shot settings and achieves a similar effect to constrained decoding in reducing prediction errors. Furthermore, we demonstrate that combining 1,000 target language examples with English data can even surpass monolingual baselines. These findings offer practical insights for improving cross-lingual ABSA in low-resource and domain-specific settings, as obtaining ten high-quality annotated examples is both feasible and highly effective.