Learning Household Task Knowledge from WikiHow Descriptions

TitleLearning Household Task Knowledge from WikiHow Descriptions
Publication TypeWorkshop Paper
Year of Publication2019
AuthorsZhou, Y., J. Shah, and S. Schockaert
Conference NameInternational Joint Conference on Artificial Intelligence (IJCAI)
Workshop NameWorkshop on Semantic Deep Learning
Date Published08/2019
AbstractCommonsense 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.