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

2026-04-11

AI Summary

This study addresses the scarcity of high-quality data and effective methods for fine-grained aspect-level sentiment quadruple extraction—comprising target, aspect, opinion, and sentiment—in low-resource languages. To this end, we introduce LASQ, the first annotated dataset for Uzbek and Uyghur, and propose a lattice-based tagging model enhanced with syntactic knowledge. Our model incorporates a Syntactic Knowledge Embedding Module (SKEM) that integrates part-of-speech tags and dependency parsing information into the lattice structure, effectively mitigating lexical sparsity challenges inherent in agglutinative languages. Experimental results demonstrate that the proposed approach significantly outperforms multiple strong baselines on LASQ, confirming both the utility of the dataset and the efficacy of the syntactically informed architecture.

Technology Category

• Natural Language Processing: Sentiment Analysis, Stylistic Analysis, and Argument Mining
• Knowledge Representation and Reasoning: Knowledge Representation Languages
• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Sentiment analysis and opinion mining
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search

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.

Problem

• low-resource languages
• aspect-based sentiment analysis
• sentiment quadruple extraction
• fine-grained sentiment analysis

Innovation

• low-resource languages
• aspect-based sentiment quadruple extraction
• syntax knowledge embedding
• grid-tagging model
• agglutinative languages