Preprocessing Tools for the Albanian Language: A State-of-the-Art Survey and an Annotation Schema Proposal
Nelda Kote, Marenglen Biba · Albanian Journal of Natural and Technical Sciences · 2022
Language preprocessing tools as parser, morphological analyzer, and lemmatizer have become very popular Natural Language Processing (NLP) approaches. Firstly, in this paper, we have presented a literature review of recent researches on preprocessing tools for the Albanian language. There is a lack of works done to implement these tools for the Albanian language. To our knowledge, there is not an official published preprocessing tool for the Albanian language. Secondly, in this paper, we have proposed a part-of-speech annotation schema for the Albanian language. We mapped the annotation schema proposed by Salavaçi and Biba (2012) into a new annotation schema containing the part-of-speech tags and morphological characteristics tags. Improving the proposed annotation schema and developing a morphological tagger for the Albanian language will foster.