Towards End-User Development for IoT: A Case Study on Semantic Parsing of Cooking Recipes for Programming Kitchen Devices

TL;DR

This paper presents a new annotated corpus and machine learning methods for semantic parsing of cooking recipes to enable end-user programming of IoT kitchen devices, highlighting challenges due to instruction incompleteness.

Contribution

It introduces a novel corpus and models for translating recipe instructions into machine-understandable commands for IoT devices.

Findings

Semantic parsers can be trained on the corpus

Instructions are often incomplete, complicating parsing

Neural network models outperform traditional methods

Abstract

Semantic parsing of user-generated instructional text, in the way of enabling end-users to program the Internet of Things (IoT), is an underexplored area. In this study, we provide a unique annotated corpus which aims to support the transformation of cooking recipe instructions to machine-understandable commands for IoT devices in the kitchen. Each of these commands is a tuple capturing the semantics of an instruction involving a kitchen device in terms of "What", "Where", "Why" and "How". Based on this corpus, we developed machine learning-based sequence labelling methods, namely conditional random fields (CRF) and a neural network model, in order to parse recipe instructions and extract our tuples of interest from them. Our results show that while it is feasible to train semantic parsers based on our annotations, most natural-language instructions are incomplete, and thus transforming them into formal meaning representation, is not straightforward.