Learning household task knowledge from WikiHow descriptions

Zhou, Yilun, Shah, Julie A. and Schockaert, Steven ORCID: https://orcid.org/0000-0002-9256-2881 2019. Learning household task knowledge from WikiHow descriptions. Presented at: 5th Workshop on Semantic Deep Learning, Macau, China, 10-16 August 2019. 10.48550/arXiv.1909.06414

Preview

PDF - Accepted Post-Print Version Download (850kB) | Preview

Abstract

Commonsense procedural knowledge is important for AI agents and robots that operate in a human environment. While previous attempts at constructing procedural knowledge are mostly rule- and template-based, recent advances in deep learning provide the possibility of acquiring such knowledge directly from natural language sources. As a first step in this direction, we propose a model to learn embeddings for tasks, as well as the individual steps that need to be taken to solve them, based on WikiHow articles. We learn these embeddings such that they are predictive of both step relevance and step ordering. We also experiment with the use of integer programming for inferring consistent global step orderings from noisy pairwise predictions.

Item Type:	Conference or Workshop Item (Paper)
Date Type:	Publication
Status:	Published
Schools:	Schools > Computer Science & Informatics
Date of First Compliant Deposit:	14 August 2019
Last Modified:	11 Aug 2025 11:45
URI:	https://orca.cardiff.ac.uk/id/eprint/124040

Actions (repository staff only)

Edit Item