MSMO-ABSA: Multi-Scale and Multi-Objective Optimization for Cross-Lingual Aspect-Based Sentiment Analysis
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918438607257600 |
|---|---|
| author | Wu, Chengyan Ma, Bolei Deng, Ningyuan He, Yanqing Xue, Yun Liu, Xiaoyong |
| author_facet | Wu, Chengyan Ma, Bolei Deng, Ningyuan He, Yanqing Xue, Yun Liu, Xiaoyong |
| contents | 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 sentence-level and aspect-level alignment, aligning features of aspect terms in different contextual environments. Specifically, we introduce code-switched 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_13718 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MSMO-ABSA: Multi-Scale and Multi-Objective Optimization for Cross-Lingual Aspect-Based Sentiment Analysis Wu, Chengyan Ma, Bolei Deng, Ningyuan He, Yanqing Xue, Yun Liu, Xiaoyong Computation and Language 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 sentence-level and aspect-level alignment, aligning features of aspect terms in different contextual environments. Specifically, we introduce code-switched 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. |
| title | MSMO-ABSA: Multi-Scale and Multi-Objective Optimization for Cross-Lingual Aspect-Based Sentiment Analysis |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2502.13718 |