The code is poetry labs are working on a broad range of assets, tools and databases for Natural Language Processing for German language. Here you can find our outcomes, articles and downloads regarding this topic.
The SemMap can be used to calculate semantics in German language. Based on a few existing projects, the SemMap unites all advantages of these projects. Furthermore the map has calculated correlations to create semantic vector spaces and apply arithmetical operations on it.
Answer Type Detection
Answer Type Detection is an important part of a question answering system. For the German language no data set to train such a classifier exist for the general public. Code is poetry labs is the first provider of such a data set.
Levenshtein distance is utilized to find phonetic similarities in two or more phrases. We did the example using German language.