Error-tolerant finite-state lookup for trademark search

Andreas Eisele; Tim vor der Brück

In: 27th Annual German Conference on AI, KI 2004, Ulm, Germany, September 20--24, 2004, Proceedings. German Conference on Artificial Intelligence (KI), 2004.


Error-tolerant lookup of words in large vocabularies has many potential uses, both within and beyond natural language processing (NLP). This work describes a generic library for finite-state-based lexical lookup, originally designed for NLP-related applications, that can be adapted to application-specific error metrics. We show how this tool can be used for searching existing trademarks in a database, using orthographic and phonetic similarity. We sketch a prototypical implementation of a trademark search engine and show results of a preliminary evaluation of this system.

dema.pdf (pdf, 287 KB )

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence