Linking Data, Services and Human Know-How

Abstract

Abstract. An increasing number of everyday tasks involve a mixture of human actions and machine computation. This paper presents the first framework that allows non-programmer users to create and execute workflows where each task can be completed by a human or a machine. In this framework, humans and machines interact through a shared knowledge base which is both human and machine understandable. This knowledge base is based on the prohow Linked Data vocabulary that can represent human instructions and link them to machine functionalities. Our hypothesis is that non-programmer users can describe how to achieve certain tasks at a level of abstraction which is both human and machine understandable. This paper presents the prohow vocabulary and describes its usage within the proposed framework. We substantiate our claim with a concrete implementation of our framework and by experimental evidence.

Recommending tasks based on search queries and missions

“…Procedural knowledge (Georgeff and Lansky, 1986) is the knowledge involved in accomplishing a task. A few procedural KBs are specialized in semi-structured knowledge (Pareti, Klein, and Barker, 2014; Chu, Tandon, and Weikum, 2017), that has been extracted from corpora of how-to guides collaboratively created in projects like WikiHow or eHow b . Jung et al (2010) automatically create a situation ontology from how-to instructions through a model of daily situational knowledge with goals, action sequences, and contextual items.…”

“…As mentioned above, for pragmatic reasons, we choose to work with a collection of procedural articles from WikiHow as our repository to recommend tasks from. Pareti et al (2014) identify properties that define community-centric tasks. They then design a framework to represent the semantic structure of procedural knowledge in web communities.…”

Engineering Background Knowledge for Social Robots

“…Ongoing work is about integrating and linking Framester's linguistic information with other kinds of knowledge, so to provide robots with a richer human-like knowledge base. The following types of knowledge could be valuable for the robot activities: procedural knowledge (e.g [160]), physical knowledge (e.g. [78]), and open-domain common sense knowledge (such that produced in projects like ConceptNet [196] and NELL [148]).…”