{"type":"ScholarlyArticle","title":"FCKT: Fine-Grained Cross-Task Knowledge Transfer with Semantic Contrastive Learning for Targeted Sentiment Analysis","authors":[{"name":"Wei Chen","slug":"wei-chen","given":"Wei","family":"Chen","affiliation":""},{"name":"Zhao Zhang","slug":"zhao-zhang","given":"Zhao","family":"Zhang","affiliation":""},{"name":"Meng Yuan","slug":"meng-yuan","given":"Meng","family":"Yuan","affiliation":""},{"name":"Kepeng Xu","slug":"kepeng-xu","given":"Kepeng","family":"Xu","affiliation":""},{"name":"Fuzhen Zhuang","slug":"fuzhen-zhuang","given":"Fuzhen","family":"Zhuang","affiliation":""}],"abstract":"In this paper, we address the task of targeted sentiment analysis , which involves two sub-tasks, i.e., identifying specific aspects from reviews and determining their corresponding senti-ments.  Aspect extraction forms the foundation for sentiment prediction, highlighting the critical dependency between these two tasks for effective cross-task knowledge transfer.\r\n\tWhile 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.\r\n   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, our framework achieves fine-grained knowledge transfer, effectively mitigating negative transfer and enhancing task performance.\r\n   Extensive experiments on three real-world datasets, including comparisons with various baselines and large language models (LLMs), demonstrate the effectiveness of FCKT. The source code\r\nis available on https://github.com/cwei01/FCKT.","doi":"10.24963/ijcai.2025/304","url":"https://ijcai.org/proceedings/2025/304","pdf":"https://ijcai.org/proceedings/2025/0304.pdf","markdown":"https://ijcai.org/proceedings/2025/304.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/304","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"Data Mining","track":"Main Track","number":304,"pages":{"first":2731,"last":2739},"keywords":["Data Mining: DM: Mining text, web, social media","Knowledge Representation and Reasoning: KRR: Knowledge representation languages","Machine Learning: ML: Deep learning architectures"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}