@article{Gleim_Eger_Mehler_Uslu_Hemati_Lücking_Henlein_Kahlsdorf_Hoenen_2019, title={A practitioner’s view: a survey and comparison of lemmatization and morphological tagging in German and Latin}, volume={7}, url={https://jlm.ipipan.waw.pl/index.php/JLM/article/view/205}, DOI={10.15398/jlm.v7i1.205}, abstractNote={<p>The challenge of POS tagging and lemmatization in morphologically rich languages is examined by comparing German and Latin. We start by defining an NLP evaluation roadmap to model the combination of tools and resources guiding our experiments. We focus on what a practitioner can expect when using state-of-the-art solutions. These solutions are then compared with old(er) methods and implementations for coarse-grained POS tagging, as well as fine-grained (morphological) POS tagging (e.g. case, number, mood). We examine to what degree recent advances in tagger development have improved accuracy – and at what cost, in terms of training and processing time. We also conduct in-domain vs. out-of-domain evaluation. Out-of-domain evaluation is particularly pertinent because the distribution of data to be tagged will typically differ from the distribution of data used to train the tagger. Pipeline tagging is then compared with a tagging approach that acknowledges dependencies between inflectional categories. Finally, we evaluate three lemmatization techniques.</p>}, number={1}, journal={Journal of Language Modelling}, author={Gleim, Rüdiger and Eger, Steffen and Mehler, Alexander and Uslu, Tolga and Hemati, Wahed and Lücking, Andy and Henlein, Alexander and Kahlsdorf, Sven and Hoenen, Armin}, year={2019}, month={Jul.}, pages={1–52} }