Latent Alignment of Procedural Concepts in Multimodal Recipes
Faghihi, Hossein Rajaby, Mirzaee, Roshanak, Paliwal, Sudarshan, Kordjamshidi, Parisa
–arXiv.org Artificial Intelligence
We propose a novel alignment mechanism to deal with procedural reasoning on a newly released multimodal QA dataset, named RecipeQA. Our model is solving the textual cloze task which is a reading comprehension on a recipe containing images and instructions. We exploit the power of attention networks, cross-modal representations, and a latent alignment space between instructions and candidate answers to solve the problem. We introduce constrained max-pooling which refines the max-pooling operation on the alignment matrix to impose disjoint constraints among the outputs of the model. Our evaluation result indicates a 19\% improvement over the baselines.
arXiv.org Artificial Intelligence
Jan-12-2021
- Country:
- North America > United States > Minnesota > Hennepin County > Minneapolis (0.14)
- Genre:
- Research Report (0.64)
- Industry:
- Education (0.34)
- Technology: