Semi-automatic Detection of Cross-lingual Marketing Blunders based on Pragmatic Label Propagation in Wiktionary

Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 2071–2081, Osaka, Japan, December 11-17 2016. Semi-automatic Detection of Cross-lingual Marketing Blunders based on Pragmatic Label Propagation in Wiktionary Christian M. Meyer and Judith Eckle-Kohler and Iryna Gurevych Ubiquitous Knowledge Processing (UKP) Lab and Research Training Group AIPHES Technische Universit¨at Darmstadt, Germany https://www.ukp.tu-darmstadt.de 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/. 1 Introduction Large companies increasingly advertise and sell their products in international markets. Developing a marketing campaign for a new country requires tremendous translation efforts in order to bridge language and cultural boundaries. A particular problem often occurs if an established product, brand, or company name is introduced to a new, foreign market without being adapted to local habits and language use. This may yield offensive, embarrassing, or (at best) funny results causing excessive remedial cost and maybe even the withdrawal of a product from the new market. Such a marketing blunder can have multiple different reasons. A commercial for a men’s fragrance showing a man with his dog failed, for instance, in Islamic countries where dogs are considered unclean. Dalgic and Heijblom (1996) distinguish possible reasons, including political, ethical, and legal issues, different traditions, inappropriate language, etc. In this work, we focus on cross-lingual marketing blunders, which are a result of using inappropriate or negatively connotated expressions or translations for naming a company, brand, or product. One example for this is using the word mist, which usually describes fabulous, enigmatic, lightweight, or mystic things in English. A British car manufacturer, for example, chose the word to advertise their Silver Mist model. In German, the false friend Mist means, however, dung or manure, and it is a frequently used slang expression to describe a futile, cheap, or broken thing, nonsense, or an annoying, tedious situation. This pejorative meaning has caused the car manufacturer to rename its product (Room, 1982; Felser, 2010). A more recent example is the announcement of the 7th edition of a smartphone in Asia. The company’s original English slogan “This is 7” has been changed for the Hong Kong market, as the pronunciation of the numeral seven (jyutping: cat1) is very similar to a vulgar expression for the male genitals (cat6), which would cause funny reactions when combined with “This is” on a product’s advertisement poster.1 Spotting a marketing blunder can be very time-consuming …

Content truncated to 500 words