NLP resources for a rare language morphological analyzer: danish case

Abstract

The paper discusses the characteristics and practical aspects of application of the natural language processing resources available for developing a rare language morphological analysis solution. The case under consideration reveals the pipeline design needed to prepare the grammatical resources for Danish. Being rare not only in terms of distribution, but also in the amount of natural language resources available, the Danish language represents a significant problem in terms of application of third-party tools to help solve various NLP-related issues. The paper focuses on part-of-speech tagging and lemmatization, typical but indispensable tasks at the pre-processing stage within the framework of developing a morphological analyzer as a custom NLP solution.