Skip to content


Switch branches/tags

Name already in use

A tag already exists with the provided branch name. Many Git commands accept both tag and branch names, so creating this branch may cause unexpected behavior. Are you sure you want to create this branch?

Latest commit


Git stats


Failed to load latest commit information.
Latest commit message
Commit time

Semi-automatic Detection of Cross-lingual Marketing Blunders

Method, software, and data for getting started with a new NLP task: detecting marketing blunders. Check out our online demo:

Please use the following citation:

  author    = {Meyer, Christian M. and Eckle-Kohler, Judith and Gurevych, Iryna},
  title     = {Semi-automatic Detection of Cross-lingual Marketing Blunders based on Pragmatic Label Propagation in Wiktionary},
  booktitle = {Proceedings of the 26th International Conference on Computational Linguistics (COLING)},
  month     = {December},
  year      = {2016},
  address   = {Osaka, Japan},
  publisher = {Association for Computational Linguistics},
  pages     = {2071--2081},
  url       = {}

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

Contact person: Christian M. Meyer,

Don't hesitate to send us an e-mail or report an issue, if something is broken (and it shouldn't be) or if you have further questions.

For license information, see LICENSE.txt file.

Online demo

Available data and software

  • marketing-blunder
    • Source code for creating the homograph index, detecting blunders using our four methods, and reproducing our experiments
    • Please contact the authors if you want to use the BrandPitt corpus (Özbal et al., 2012) and our annotations for this corpus
  • marketing-blunder-online
    • Wicket-based web application for our online demo
  • marketing-blunder-data
    • marketing-blunders-dataset.tsv: our newly created dataset
    • marketing-blunders-dataset.pdf: detailed result table of experiment 1
    • homograph-index.7z: SQL export of our homograph index

System requirements

  • Java 7 and higher
  • J2EE platform (e.g., Apache Tomcat 6 and higher)
  • Maven
  • MySQL database (or other SQL database)

System installation

  • Install Java, Maven, Tomcat, and MySQL.
  • Download the source code from GitHub.
  • Import the homograph index to a database.
  • Update according to template file.
  • Update with your database settings.
  • Add the BrandPitt dataset by Özbal et al. (2012), if needed
  • Build the software using mvn package
  • Deploy the war file from target/ to your application server.
  • Open http://localhost:8080/blunder (or accordingly)
  • Run the evaluation based on the test cases.


Method, software, and data for getting started with a new NLP task: detecting marketing blunders







No releases published


No packages published