Show Me More Details: Discovering Hierarchies of Procedures from Semi-structured Web Data
Shuyan Zhou, Li Zhang, Yue Yang, Qing Lyu, Pengcheng Yin, Chris Callison-Burch, Graham Neubig
Abstract
Procedures are inherently hierarchical. To make videos, one may need to purchase a camera, which in turn may require one to set a budget. While such hierarchical knowledge is critical for reasoning about complex procedures, most existing work has treated procedures as shallow structures without modeling the parent-child relation. In this work, we attempt to construct an open-domain hierarchical knowledge-base (KB) of procedures based on wikiHow, a website containing more than 110k instructional articles, each documenting the steps to carry out a complex procedure. To this end, we develop a simple and efficient method that links steps (e.g., purchase a camera) in an article to other articles with similar goals (e.g., how to choose a camera), recursively constructing the KB. Our method significantly outperforms several strong baselines according to automatic evaluation, human judgment, and application to downstream tasks such as instructional video retrieval. 1 * Equal contribution.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Cited by top-tier papers12
- WebArena: A Realistic Web Environment for Building Autonomous AgentsShuyan Zhou, Frank F. Xu, Hao Zhu, Xuhui Zhou et al.ICLR 2024 · 1,197 citations
- Synatra: Turning Indirect Knowledge into Direct Demonstrations for Digital Agents at ScaleTianyue Ou, Frank F. Xu, Aman Madaan, Jiarui Liu et al.NeurIPS 2024 · 45 citations
- TaskLAMA: Probing the Complex Task Understanding of Language ModelsQuan Yuan, Mehran Kazemi, Xin Xu, Isaac Noble et al.AAAI 2024 · 22 citations
- PrISM-Q&A: Step-Aware Voice Assistant on a Smartwatch Enabled by Multimodal Procedure Tracking and Large Language ModelsRiku Arakawa, Jill Fain Lehman, Mayank GoelUbiComp 2025 · 20 citations
- PrISM-Observer: Intervention Agent to Help Users Perform Everyday Procedures Sensed using a SmartwatchRiku Arakawa, Hiromu Yakura, Mayank GoelUIST 2024 · 20 citations
Builds on5
- BERTScore: Evaluating Text Generation with BERTTianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q. Weinberger et al.ICLR 2020 · 8,443 citations
- Deberta: decoding-Enhanced Bert with Disentangled AttentionPengcheng He, Xiaodong Liu, Jianfeng Gao, Weizhu ChenICLR 2021 · 3,729 citations
- HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video ClipsAntoine Miech, Dimitri Zhukov, Jean-Baptiste Alayrac, Makarand Tapaswi et al.ICCV 2019 · 1,437 citations
- Dense Passage Retrieval for Open-Domain Question AnsweringVladimir Karpukhin, Barlas Oguz, Sewon Min, Patrick Lewis et al.EMNLP 2020 · 142 citations
- Analogous Process Structure Induction for Sub-event Sequence PredictionHongming Zhang, Muhao Chen, Haoyu Wang, Yangqiu Song et al.EMNLP 2020 · 31 citations
Related papers
- Learning To Recognize Procedural Activities with Distant SupervisionXudong Lin, Fabio Petroni, Gedas Bertasius, Marcus Rohrbach et al.CVPR 2022 · 55 citations
- Learning to Ground Instructional Articles in Videos through NarrationsEffrosyni Mavroudi, Triantafyllos Afouras, Lorenzo TorresaniICCV 2023 · 28 citations
- Non-Sequential Graph Script Induction via Multimedia GroundingYu Zhou, Sha Li, Manling Li, Xudong Lin et al.ACL 2023 · 5 citations
- Neuro-Symbolic Procedural Planning with Commonsense PromptingYujie Lu, Weixi Feng, Wanrong Zhu, Wenda Xu et al.ICLR 2023 · 3 citations
- Learning Procedure-aware Video Representation from Instructional Videos and Their NarrationsYiwu Zhong, Licheng Yu, Yang Bai, Shangwen Li et al.CVPR 2023
