Publication
Relation Extraction for the Food Domain without Labeled Training Data - Is Distant Supervision the Best Solution?
Melanie Reiplinger; Michael Wiegand; Dietrich Klakow
In: Adam Przepiórkowski; Maciej Ogrodniczuk (Hrsg.). Advances in Natural Language Processing. Pages 345-357, Lecture Notes in Computer Science (LNCS), Vol. 8686, ISBN 978-3-319-10887-2, Springer International Publishing, Switzerland, 9/2014.
Abstract
We examine the task of relation extraction in the food domain by employing distant supervision. We focus on the extraction of two relations that are not only relevant to product recommendation in the food domain, but that also have significance in other domains, such as the fashion or electronics domain. In order to select suitable training data, we investigate various degrees of freedom. We consider three processing levels being argument level, sentence level and feature level. As external resources, we employ manually created surface patterns and semantic types on all these levels. We also explore in how far rule-based methods employing the same information are competitive.