Generative Models Enhanced by Sequence Labelling and Aspect-Code Switching Improve Cross-lingual Aspect-Based Sentiment Analysis
2026-08-31 • Computation and Language
Computation and Language
AI summaryⓘ
The authors study how to teach computers to understand detailed feelings about specific parts of a sentence in many languages, even when there is no labeled data for those languages. They create a new method called SeqLab that helps the model better find important words and their feelings by combining two tasks. They also use a technique called aspect-code switching, which mixes words from different languages to make training data more diverse. Their method works well across multiple languages and tasks, including some harder ones, and they carefully analyze where the method still struggles.
Cross-lingualAspect-based sentiment analysisSequence-to-sequence modelSequence labelingAspect term recognitionAspect-code switchingTarget-aspect-sentiment detectionE2E-ABSAMultilingual NLPError analysis
Authors
Jakub Šmíd, Pavel Přibáň, Pavel Král
Abstract
Cross-lingual aspect-based sentiment analysis (ABSA) transfers knowledge from a source language with annotated data to a target language, enabling fine-grained sentiment analysis without annotated target-language data. While monolingual ABSA has seen significant progress, cross-lingual ABSA remains underexplored, especially for complex tasks involving multiple sentiment elements like target-aspect-sentiment detection (TASD). In this paper, we propose a novel SeqLab framework that enhances cross-lingual ABSA using a sequence-to-sequence model with an auxiliary sequence-labelling task performed by the encoder, enhancing aspect term recognition and sentiment predictions. Additionally, we incorporate aspect-code switching (ACS), a translation-based technique that swaps aspect terms between source and translated sentences, generating additional training data to enhance the model's cross-lingual understanding. We evaluate our approach across eleven languages, three domains, and two backbone models, surpassing previous state-of-the-art results for the commonly studied E2E-ABSA task. Unlike most prior work that relies solely on English as the source language, we systematically assess different source-target language pairs and extend our evaluation to the more challenging, yet underexplored TASD task in cross-lingual settings. Finally, we provide a detailed error analysis highlighting key challenges and limitations.