Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2021
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2110.08486 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929249233928192 |
|---|---|
| author | Wu, Te-Lin Spangher, Alex Alipoormolabashi, Pegah Freedman, Marjorie Weischedel, Ralph Peng, Nanyun |
| author_facet | Wu, Te-Lin Spangher, Alex Alipoormolabashi, Pegah Freedman, Marjorie Weischedel, Ralph Peng, Nanyun |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2110_08486 |
| institution | arXiv |
| publishDate | 2021 |
| record_format | arxiv |
| spellingShingle | Understanding Multimodal Procedural Knowledge by Sequencing Multimodal Instructional Manuals Wu, Te-Lin Spangher, Alex Alipoormolabashi, Pegah Freedman, Marjorie Weischedel, Ralph Peng, Nanyun Computation and Language Computer Vision and Pattern Recognition 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. |
| title | Understanding Multimodal Procedural Knowledge by Sequencing Multimodal Instructional Manuals |
| topic | Computation and Language Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2110.08486 |