CL-XABSA: Contrastive Learning for Cross-lingual Aspect-based Sentiment Analysis

TL;DR

This paper introduces CL-XABSA, a contrastive learning framework that aligns semantic spaces across languages for improved cross-lingual and multilingual aspect-based sentiment analysis, leveraging contrastive strategies and knowledge distillation.

Contribution

The paper proposes a novel contrastive learning framework with token and sentiment level strategies for cross-lingual ABSA, and incorporates knowledge distillation to enhance performance across multiple languages.

Findings

Improves XABSA, distillation XABSA, and MABSA tasks.

Effective in aligning semantic spaces across languages.

Utilizes knowledge distillation with various data types.

Abstract

As an extensive research in the field of natural language processing (NLP), aspect-based sentiment analysis (ABSA) is the task of predicting the sentiment expressed in a text relative to the corresponding aspect. Unfortunately, most languages lack sufficient annotation resources, thus more and more recent researchers focus on cross-lingual aspect-based sentiment analysis (XABSA). However, most recent researches only concentrate on cross-lingual data alignment instead of model alignment. To this end, we propose a novel framework, CL-XABSA: Contrastive Learning for Cross-lingual Aspect-Based Sentiment Analysis. Based on contrastive learning, we close the distance between samples with the same label in different semantic spaces, thus achieving a convergence of semantic spaces of different languages. Specifically, we design two contrastive strategies, token level contrastive learning of token embeddings (TL-CTE) and sentiment level contrastive learning of token embeddings (SL-CTE), to regularize the semantic space of source and target language to be more uniform. Since our framework can receive datasets in multiple languages during training, our framework can be adapted not only for XABSA task but also for multilingual aspect-based sentiment analysis (MABSA). To further improve the performance of our model, we perform knowledge distillation technology leveraging data from unlabeled target language. In the distillation XABSA task, we further explore the comparative effectiveness of different data (source dataset, translated dataset, and code-switched dataset). The results demonstrate that the proposed method has a certain improvement in the three tasks of XABSA, distillation XABSA and MABSA. For reproducibility, our code for this paper is available at https://github.com/GKLMIP/CL-XABSA.