ACL Findings2023
Few-shot Joint Multimodal Aspect-Sentiment Analysis Based on Generative Multimodal Prompt
Xiaocui Yang, Shi Feng, Daling Wang, Qi Sun, Wenfang Wu, Yifei Zhang, Pengfei Hong, Soujanya Poria
摘要
We have witnessed the rapid proliferation of multimodal data on numerous social media platforms. Conventional studies typically require massive labeled data to train models for Multimodal Aspect-Based Sentiment Analysis (MABSA). However, collecting and annotating fine-grained multimodal data for MABSA is tough. To alleviate the above issue, we perform three MABSA-related tasks with quite a small number of labeled multimodal samples. We first build diverse and comprehensive multimodal few-shot datasets according to the data distribution. To capture the specific prompt for each aspect term in a few-shot scenario, we propose a novel Generative Multimodal Prompt (GMP) 1 model for MABSA, which includes the Multimodal Encoder module and the N-Stream Decoders module. We further introduce a subtask to predict the number of aspect terms in each instance to construct the multimodal prompt. Extensive experiments on two datasets demonstrate that our approach outperforms strong baselines on two MABSA-related tasks in the few-shot setting.
问 Lune
几分钟读透这篇 Paper,不用再花一下午。
Lune 能读完全文,也能读引用它的顶会 Paper,讲清它的结论、证据和局限,每一点都注明出自哪篇 Paper。不用硬啃,也不靠猜。
已有 2 篇顶会 Paper 引用了它。别等审稿人问起,先弄清它们发现了什么。
脉络
- VERO: Verification and Zero-Shot Feedback Acquisition for Few-Shot Multimodal Aspect-Level Sentiment Classification 引用了 BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
- Few-Shot Joint Multimodal Entity-Relation Extraction via Knowledge-Enhanced Cross-modal Prompt Model 引用了 Improving Multimodal Named Entity Recognition via Entity Span Detection with Unified Multimodal Transformer
- Few-Shot Joint Multimodal Entity-Relation Extraction via Knowledge-Enhanced Cross-modal Prompt Model 引用了 Multi-modal Graph Fusion for Named Entity Recognition with Targeted Visual Guidance
- Multi-modal Graph Fusion for Named Entity Recognition with Targeted Visual Guidance 引用了 Improving Multimodal Named Entity Recognition via Entity Span Detection with Unified Multimodal Transformer
引用它的顶会 Paper2
- Few-Shot Joint Multimodal Entity-Relation Extraction via Knowledge-Enhanced Cross-modal Prompt ModelLi Yuan, Yi Cai, Junsheng HuangACM MM 2024 · 9 次引用
- VERO: Verification and Zero-Shot Feedback Acquisition for Few-Shot Multimodal Aspect-Level Sentiment ClassificationKai Sun, Hao Wu, Bin Shi, Samuel Mensah 等AAAI 2025 · 1 次引用
它引用的 Paper15
- BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and ComprehensionMike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad 等ACL 2020 · 1,224 次引用
- AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated PromptsTaylor Shin, Yasaman Razeghi, Robert L. Logan IV, Eric Wallace 等EMNLP 2020 · 1,162 次引用
- Multimodal Few-Shot Learning with Frozen Language ModelsMaria Tsimpoukelli, Jacob Menick, Serkan Cabi, S. M. Ali Eslami 等NeurIPS 2021 · 1,020 次引用
- Improving Multimodal Named Entity Recognition via Entity Span Detection with Unified Multimodal TransformerJianfei Yu, Jing Jiang, Li Yang, Rui XiaACL 2020 · 260 次引用
- Multi-modal Graph Fusion for Named Entity Recognition with Targeted Visual GuidanceDong Zhang, Suzhong Wei, Shoushan Li, Hanqian Wu 等AAAI 2021 · 240 次引用
相关 Paper
- Few-shot Multimodal Sentiment Analysis Based on Multimodal Probabilistic Fusion PromptsXiaocui Yang, Shi Feng, Daling Wang, Yifei Zhang 等ACM MM 2023 · 34 次引用
- DS²-ABSA: Dual-Stream Data Synthesis with Label Refinement for Few-Shot Aspect-Based Sentiment AnalysisHongling Xu, Yice Zhang, Qianlong Wang, Ruifeng XuACL 2025 · 3 次引用
- Unified Multi-modal Pre-training for Few-shot Sentiment Analysis with Prompt-based LearningYang Yu, Dong Zhang, Shoushan LiACM MM 2022 · 44 次引用
- Vision-Language Pre-Training for Multimodal Aspect-Based Sentiment AnalysisYan Ling, Jianfei Yu, Rui XiaACL 2022 · 116 次引用
- UniSA: Unified Generative Framework for Sentiment AnalysisZaijing Li, Ting-En Lin, Yuchuan Wu, Meng Liu 等ACM MM 2023 · 22 次引用
