LAS: an integrated language analysis tool for multiple languages

Abstract

LAS is a command-line tool for lemmatizing, morphological analysis, inflected form gen-eration, hyphenation and language identification of multiple languages. These functionalities are of use as part of many workflows requiring natural language processing. Indeed, LAS has been used for example as part of a pipeline for entity recog-nition (Mäkelä 2014), in creating a contextual reader for texts in English, Finnish and Latin (Mäkelä, Lindquist, and Hyvönen 2016), and for processing a Finnish historical newspaper collection in preparation for data publication (Pääkkönen et al. 2016).