Volltext-Downloads (blau) und Frontdoor-Views (grau)

Relation Extraction for the Food Domain without Labeled Training Data – Is Distant Supervision the Best Solution?

  • 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.

Download full text files

  • Reiplinger_Wiegand_Klakow_RE_for_the_Food_Domain_w_o_Labeled_Training_Data_2014.pdf


Export metadata

Additional Services

Search Google Scholar


Author:Melanie Reiplinger, Michael WiegandGND, Dietrich Klakow
Parent Title (English):Advances in Natural Language Processing. Proceedings of the 9th International Conference on NLP, PolTAL 2014, Warsaw, Poland, September 17-19, 2014
Series (Serial Number):Lecture Notes in Artificial Intelligence (8686)
Place of publication:Cham
Editor:Adam Przepiórkowski, Maciej Ogrodniczuk
Document Type:Conference Proceeding
Year of first Publication:2014
Date of Publication (online):2019/04/02
Tag:Food item; Relation extraction; Sentence level; Surface pattern; Target relation
GND Keyword:Computerlinguistik; Information Extraction; Lebensmittel; Maschinelles Lernen; Natürliche Sprache
First Page:345
Last Page:357
Dieser Beitrag ist aus urheberrechtlichen Gründen online nicht frei zugänglich.
DDC classes:400 Sprache / 400 Sprache, Linguistik
Open Access?:nein
Licence (German):License LogoUrheberrechtlich geschützt