Visual Elements Mining as Prompts for Instruction Learning for Target-Oriented Multimodal Sentiment Classification

Bin Yang, Jinlong Li


Abstract
Target-oriented Multimodal Sentiment Classification (TMSC) aims to incorporate visual modality with text modality to identify the sentiment polarity towards a specific target within a sentence. To address this task, we propose a Visual Elements Mining as Prompts (VEMP) method, which describes the semantic information of visual elements with Text Symbols Embedded in the Image (TSEI), Target-aware Adjective-Noun Pairs (TANPs) and image scene caption, and then transform them into prompts for instruction learning of the model Tk-Instruct. In our VEMP, the text symbols embedded in the image may contain the textual descriptions of fine-grained visual elements, and are extracted as input TSEI; we extract adjective-noun pairs from the image and align them with the target to obtain TANPs, in which the adjectives provide emotional embellishments for the relevant target; finally, to effectively fuse these visual elements with text modality for sentiment prediction, we integrate them to construct instruction prompts for instruction-tuning Tk-Instruct which possesses powerful learning capabilities under instructions. Extensive experimental results show that our method achieves state-of-the-art performance on two benchmark datasets. And further analysis demonstrates the effectiveness of each component of our method.
Anthology ID:
2023.findings-emnlp.403
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2023
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6062–6075
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.403
DOI:
10.18653/v1/2023.findings-emnlp.403
Bibkey:
Cite (ACL):
Bin Yang and Jinlong Li. 2023. Visual Elements Mining as Prompts for Instruction Learning for Target-Oriented Multimodal Sentiment Classification. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 6062–6075, Singapore. Association for Computational Linguistics.
Cite (Informal):
Visual Elements Mining as Prompts for Instruction Learning for Target-Oriented Multimodal Sentiment Classification (Yang & Li, Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-emnlp.403.pdf