Procedural Reasoning Networks for Understanding Multimodal Procedures
This addresses the challenge of understanding multimodal procedures for AI systems, though it is incremental as it builds on existing neural approaches.
The paper tackles the problem of comprehending procedural commonsense knowledge by introducing an entity-aware neural model with external relational memory units, which improves accuracy on the RecipeQA dataset by a large margin.
This paper addresses the problem of comprehending procedural commonsense knowledge. This is a challenging task as it requires identifying key entities, keeping track of their state changes, and understanding temporal and causal relations. Contrary to most of the previous work, in this study, we do not rely on strong inductive bias and explore the question of how multimodality can be exploited to provide a complementary semantic signal. Towards this end, we introduce a new entity-aware neural comprehension model augmented with external relational memory units. Our model learns to dynamically update entity states in relation to each other while reading the text instructions. Our experimental analysis on the visual reasoning tasks in the recently proposed RecipeQA dataset reveals that our approach improves the accuracy of the previously reported models by a large margin. Moreover, we find that our model learns effective dynamic representations of entities even though we do not use any supervision at the level of entity states.