Predicting Implicit Arguments in Procedural Video Instructions
This addresses the challenge of inferring implicit arguments in multimodal procedural data for AI systems, though it is incremental as it builds on existing SRL methods with a new dataset and model.
The paper tackles the problem of incomplete understanding in procedural video instructions due to missing implicit arguments in Semantic Role Labeling (SRL), by introducing the Implicit-VidSRL dataset and achieving a 17% relative F1-score improvement for what-implicit and 14.7% for where/with-implicit roles over GPT-4o.
Procedural texts help AI enhance reasoning about context and action sequences. Transforming these into Semantic Role Labeling (SRL) improves understanding of individual steps by identifying predicate-argument structure like {verb,what,where/with}. Procedural instructions are highly elliptic, for instance, (i) add cucumber to the bowl and (ii) add sliced tomatoes, the second step's where argument is inferred from the context, referring to where the cucumber was placed. Prior SRL benchmarks often miss implicit arguments, leading to incomplete understanding. To address this, we introduce Implicit-VidSRL, a dataset that necessitates inferring implicit and explicit arguments from contextual information in multimodal cooking procedures. Our proposed dataset benchmarks multimodal models' contextual reasoning, requiring entity tracking through visual changes in recipes. We study recent multimodal LLMs and reveal that they struggle to predict implicit arguments of what and where/with from multi-modal procedural data given the verb. Lastly, we propose iSRL-Qwen2-VL, which achieves a 17% relative improvement in F1-score for what-implicit and a 14.7% for where/with-implicit semantic roles over GPT-4o.