Dr. Christian M. Meyer

Semi-automatic Detection of Cross-lingual Marketing Blunders based on

Pragmatic Label Propagation in Wiktionary

Abstract. We introduce the task of detecting cross-lingual marketing blunders, which occur if a trade name resembles an inappropriate or negatively con­no­ta­ted word in a target language. To this end, we suggest a formal task definition and a semi-automatic method based the propagation of pragmatic labels from Wiktionary across sense-disambiguated trans­lations. Our final tool assists users by providing clues for problematic names in any language, which we simulate in two experiments on detecting previously occurred marketing blunders and identifying relevant clues for established international brands. We con­clude the paper with a suggested research roadmap for this new task. To initiate further research, we publish our online demo along with the source code and data at http://uby.ukp.informatik.tu-darmstadt.de/blunder/.

Submitted: 15.07.2016 | Published: 13.12.2016
Outline of the proposed method.
Outline of the proposed method.