FCKT: Fine-Grained Cross-Task Knowledge Transfer with Semantic Contrastive Learning for Targeted Sentiment Analysis

2025-05-27

AI Summary

Existing target-oriented sentiment analysis (TSA) approaches employ overly coarse-grained cross-task knowledge transfer, often erroneously assuming uniform sentiment polarity across all aspects of a given target and neglecting context dependency—leading to negative transfer. To address this, we propose a fine-grained cross-task knowledge transfer framework that jointly models aspect extraction and sentiment classification. First, we design an aspect-aware feature disentanglement and semantic-sentiment alignment mechanism to explicitly capture aspect-level fine-grained relationships. Second, we introduce semantic contrastive learning to suppress task interference. Third, we develop a fine-grained knowledge distillation strategy to enhance transfer quality. Extensive experiments on three standard benchmarks demonstrate significant improvements in both aspect extraction and sentiment classification F1 scores over state-of-the-art multi-task baselines and large language model–based methods. The source code is publicly available.

Technology Category

• Natural Language Processing: Sentence-level Semantics, Textual Inference, etc.
• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Data Mining & Knowledge Management: Semantic Web

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Web Mining and Content Analysis: Sentiment analysis and opinion mining

Abstract

In this paper, we address the task of targeted sentiment analysis (TSA), which involves two sub-tasks, i.e., identifying specific aspects from reviews and determining their corresponding sentiments. Aspect extraction forms the foundation for sentiment prediction, highlighting the critical dependency between these two tasks for effective cross-task knowledge transfer. While most existing studies adopt a multi-task learning paradigm to align task-specific features in the latent space, they predominantly rely on coarse-grained knowledge transfer. Such approaches lack fine-grained control over aspect-sentiment relationships, often assuming uniform sentiment polarity within related aspects. This oversimplification neglects contextual cues that differentiate sentiments, leading to negative transfer. To overcome these limitations, we propose FCKT, a fine-grained cross-task knowledge transfer framework tailored for TSA. By explicitly incorporating aspect-level information into sentiment prediction, FCKT achieves fine-grained knowledge transfer, effectively mitigating negative transfer and enhancing task performance. Experiments on three datasets, including comparisons with various baselines and large language models (LLMs), demonstrate the effectiveness of FCKT. The source code is available on https://github.com/cwei01/FCKT.

Problem

• Enhancing targeted sentiment analysis via fine-grained knowledge transfer
• Addressing negative transfer in aspect-sentiment relationship modeling
• Improving cross-task dependency in aspect extraction and sentiment prediction

Innovation

• Fine-grained cross-task knowledge transfer
• Semantic contrastive learning for TSA
• Aspect-level information integration