LASQ: A Low-resource Aspect-based Sentiment Quadruple Extraction Dataset

TL;DR

This paper introduces LASQ, a novel dataset for aspect-based sentiment analysis in low-resource languages Uzbek and Uyghur, along with a syntactic knowledge-integrated model that improves quadruple extraction performance.

Contribution

The paper creates the first low-resource language ABSA dataset LASQ and proposes a grid-tagging model with syntax knowledge embedding to enhance extraction accuracy.

Findings

Experiments show the model outperforms baselines on LASQ.

LASQ enables research in low-resource language sentiment analysis.

The syntax knowledge embedding improves handling of agglutinative languages.

Abstract

In recent years, aspect-based sentiment analysis (ABSA) has made rapid progress and shown strong practical value. However, existing research and benchmarks are largely concentrated on high-resource languages, leaving fine-grained sentiment extraction in low-resource languages under-explored. To address this gap, we constructed the first Low-resource languages Aspect-based Sentiment Quadruple dataset, named LASQ, which includes two low-resource languages: Uzbek and Uyghur. Secondly, it includes a fine-grained target-aspect-opinion-sentiment quadruple extraction task. To facilitate future research, we designed a grid-tagging model that integrates syntactic knowledge. This model incorporates part-of-speech (POS) and dependency knowledge into the model through our designed Syntax Knowledge Embedding Module (SKEM), thereby alleviating the lexical sparsity problem caused by agglutinative languages. Experiments on LASQ demonstrate consistent gains over competitive baselines, validating both the dataset's utility and the effectiveness of the proposed modeling approach.