MSMO-ABSA: Multi-Scale and Multi-Objective Optimization for Cross-Lingual Aspect-Based Sentiment Analysis

Aspect-based sentiment analysis (ABSA) garnered growing research interest in multilingual contexts in the past.However, the majority of the studies lack more robust feature alignment and finer aspect-level alignment.In this paper, we propose a novel framework, MSMO: Multi-Scale and Multi-Objective optimization for cross-lingual ABSA.During multi-scale alignment, we achieve cross-lingual sentencelevel and aspect-level alignment, aligning features of aspect terms in different contextual environments.Specifically, we introduce codeswitched bilingual sentences into the language discriminator and consistency training modules to enhance the model's robustness.During multi-objective optimization, we design two optimization objectives: supervised training and consistency training, aiming to enhance cross-lingual semantic alignment.To further improve model performance, we incorporate distilled knowledge of the target language into the model.Results show that MSMO significantly enhances cross-lingual ABSA by achieving state-of-the-art performance across multiple languages and models. 1