Latent Alignment of Procedural Concepts in Multimodal Recipes
About
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.
Hossein Rajaby Faghihi, Roshanak Mirzaee, Sudarshan Paliwal, Parisa Kordjamshidi• 2021
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Textual Cloze | RecipeQA (test) | Accuracy47.5 | 9 |
Showing 1 of 1 rows