跨语言情感分析新框架，提升多语言细粒度情感对齐效果
MSMO-ABSA: Multi-Scale and Multi-Objective Optimization for Cross-Lingual Aspect-Based Sentiment Analysis
- 采用多尺度对齐，同时优化句级与词级跨语言特征
- 设计双目标优化，结合监督与一致性训练提升对齐精度
- 适合多语言情感分析研究者，尤其关注细粒度对齐场景
基于方面的情感分析（ABSA）在多语言环境下受到越来越多关注。然而，现有研究普遍缺乏更强的特征对齐能力与更精细的方面级对齐机制。本文提出一种新框架MSMO：多尺度多目标优化用于跨语言ABSA。在多尺度对齐中，实现跨语言句级与方面级对齐，对不同上下文环境下的方面词特征进行对齐。具体地，引入代码混杂的双语句子至语言判别器和一致性训练模块，增强模型鲁棒性。在多目标优化中，设计监督训练与一致性训练两个目标，旨在提升跨语言语义对齐。为进一步提升性能，将目标语言的蒸馏知识融入模型。实验结果表明，MSMO显著提升了跨语言ABSA性能，在多个语言与模型上达到当前最优水平。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。