EUVIMEDEUVIMED entdecken
Crossref

DEQA: Descriptions Enhanced Question-Answering Framework for Multimodal Aspect-Based Sentiment Analysis

Zhixin Han, Mengting Hu, Yinhao Bai, Xunzhi Wang, Bitong Luo

Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (22) · 23987-23995

DOI: 10.1609/aaai.v39i22.34572 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Zhixin Han und 4 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multimodal aspect-based sentiment analysis (MABSA) integrates text and images to perform fine-grained sentiment analysis on specific aspects, enhancing the understanding of user opinions in various applications. Existing methods use modality alignment for information interaction and fusion between images and text, but an inherent gap between these two modalities necessitates a more direct bridging mechanism to effectively connect image understanding with text content. For this, we propose the Descriptions Enhanced Question-Answering Framework (DEQA), which generates descriptions of images using GPT-4, leveraging the multimodal large language model to provide more direct semantic context of images. In DEQA, to help the model better understand the task's purpose, we frame MABSA as a multi-turn question-answering problem to add semantic guidance and hints. We input text, image, and description into separate experts in various combinations, allowing each expert to focus on different features and thereby improving the comprehensive utilization of input information. By integrating these expert outputs within a multi-turn question-answering format, we employ a multi-expert ensemble decision-making approach to produce the final prediction results. Experimental results on two widely-used datasets demonstrate that our method achieves state-of-the-art performance. Furthermore, our framework substantially outperforms GPT-4o and other multimodal large language models, showcasing its superior effectiveness in multimodal sentiment analysis.

Zitieren

APA

Han, Z., Hu, M., Bai, Y., Wang, X., & Luo, B. (2025). DEQA: Descriptions Enhanced Question-Answering Framework for Multimodal Aspect-Based Sentiment Analysis. Proceedings of the AAAI Conference on Artificial Intelligence, 39(22), 23987-23995. https://doi.org/10.1609/aaai.v39i22.34572

Vancouver

Han Z, Hu M, Bai Y, Wang X, Luo B. DEQA: Descriptions Enhanced Question-Answering Framework for Multimodal Aspect-Based Sentiment Analysis. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(22):23987-23995. doi:10.1609/aaai.v39i22.34572

BibTeX
@article{Han2025,
  author = {Han, Zhixin and Hu, Mengting and Bai, Yinhao and Wang, Xunzhi and Luo, Bitong},
  title = {DEQA: Descriptions Enhanced Question-Answering Framework for Multimodal Aspect-Based Sentiment Analysis},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2025},
  volume = {39},
  number = {22},
  pages = {23987--23995},
  doi = {10.1609/aaai.v39i22.34572}
}
Kostenlos starten →