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

Aspect-based sentiment analysis (ABSA), an extensively researched area in the field of natural language processing (NLP), predicts the sentiment expressed in a text relative to the corresponding aspect. Unfortunately, most languages lack sufficient annotation resources; thus, an increasing number of...

Full description

Saved in:
Bibliographic Details
Published in:IEEE/ACM transactions on audio, speech, and language processing speech, and language processing, 2023-01, Vol.31, p.1-12
Main Authors: Lin, Nankai, Fu, Yingwen, Lin, Xiaotian, Zhou, Dong, Yang, Aimin, Jiang, Shengyi
Format: Article
Language:English
Subjects:
Alignment
Annotations
Contrastive Learning
Cross-lingual Aspect-based Sentiment Analysis
Data mining
Data models
Datasets
Distillation
Information science
Knowledge Distillation
Learning
Multilingual Aspect-based Sentiment Analysis
Natural language processing
Semantics
Sentiment analysis
Speech processing
Task analysis
Training
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Aspect-based sentiment analysis (ABSA), an extensively researched area in the field of natural language processing (NLP), predicts the sentiment expressed in a text relative to the corresponding aspect. Unfortunately, most languages lack sufficient annotation resources; thus, an increasing number of recent researchers have focused on cross-lingual aspect-based sentiment analysis (XABSA). However, most recent studies focus only on cross-lingual data alignment instead of model alignment. Therefore, 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, achieving convergence of semantic spaces of different languages. Specifically, we design two contrastive objectives, token-level contrastive learning of token embeddings (TL-CTE) and sentiment-level contrastive learning of token embeddings (SL-CTE), to unify the semantic space of source and target languages. Since CL-XABSA can receive datasets in multiple languages during training, it can be further extended to multilingual aspect-based sentiment analysis (MABSA). To further improve the model performance, we perform knowledge distillation with target-language unlabeled data. In the distillation XABSA task, we further explore the 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 XABSA tasks, distillation XABSA and MABSA. The source code of this paper is publicly available at https://github.com/GKLMIP/CL-XABSA .
ISSN:2329-9290
2329-9304
DOI:10.1109/TASLP.2023.3297964