Understanding Multimodal Procedural Knowledge by Sequencing Multimodal Instructional Manuals

TL;DR

This paper benchmarks machine learning models' ability to sequence unordered multimodal instructions and introduces sequentiality-aware pretraining techniques that improve performance by over 5%.

Contribution

It provides a new dataset and human annotations for multimodal instruction sequencing and proposes pretraining methods that enhance model reasoning over multimodal procedures.

Findings

Models perform worse than humans in multimodal sequencing.

Current models struggle to utilize multimodal information effectively.

Sequentiality-aware pretraining improves performance by over 5%.

Abstract

The ability to sequence unordered events is an essential skill to comprehend and reason about real world task procedures, which often requires thorough understanding of temporal common sense and multimodal information, as these procedures are often communicated through a combination of texts and images. Such capability is essential for applications such as sequential task planning and multi-source instruction summarization. While humans are capable of reasoning about and sequencing unordered multimodal procedural instructions, whether current machine learning models have such essential capability is still an open question. In this work, we benchmark models' capability of reasoning over and sequencing unordered multimodal instructions by curating datasets from popular online instructional manuals and collecting comprehensive human annotations. We find models not only perform significantly worse than humans but also seem incapable of efficiently utilizing the multimodal information. To improve machines' performance on multimodal event sequencing, we propose sequentiality-aware pretraining techniques that exploit the sequential alignment properties of both texts and images, resulting in > 5% significant improvements.