Personalized Multimodal Feedback Generation in Education
Liu, Haochen, Liu, Zitao, Wu, Zhongqin, Tang, Jiliang
–arXiv.org Artificial Intelligence
The automatic evaluation for school assignments is an important application of AI in the education field. In this work, we focus on the task of personalized multimodal feedback generation, which aims to generate personalized feedback for various teachers to evaluate students' assignments involving multimodal inputs such as images, audios, and texts. This task involves the representation and fusion of multimodal information and natural language generation, which presents the challenges from three aspects: 1) how to encode and integrate multimodal inputs; 2) how to generate feedback specific to each modality; and 3) how to realize personalized feedback generation. In this paper, we propose a novel Personalized Multimodal Feedback Generation Network (PMFGN) armed with a modality gate mechanism and a personalized bias mechanism to address these challenges. The extensive experiments on real-world K-12 education data show that our model significantly outperforms several baselines by generating more accurate and diverse feedback. In addition, detailed ablation experiments are conducted to deepen our understanding of the proposed framework.
arXiv.org Artificial Intelligence
Oct-31-2020
- Country:
- North America > United States
- Michigan > Ingham County
- Lansing (0.04)
- East Lansing (0.04)
- Massachusetts
- Hampshire County > Amherst (0.14)
- Suffolk County > Boston (0.04)
- Louisiana > Orleans Parish
- New Orleans (0.04)
- California
- San Francisco County > San Francisco (0.14)
- San Diego County > San Diego (0.04)
- Michigan > Ingham County
- Europe
- Germany > Berlin (0.04)
- Spain > Valencian Community
- Valencia Province > Valencia (0.04)
- Italy > Veneto
- Venice (0.04)
- France > Hauts-de-France
- Asia > China
- North America > United States
- Genre:
- Research Report (0.82)
- Industry:
- Education > Educational Setting > K-12 Education (0.87)
- Technology: