@inproceedings{MellStorjohann2017, author = {Ruth Maria Mell and Petra Storjohann}, title = {A corpus-assisted approach to paronym categorisation}, series = {Electronic lexicography in the 21st century. Proceedings of eLex 2017 conference. Leiden, the Netherlands, 19 – 21 September 2017}, editor = {Iztok Kosem and Carole Tiberius and Miloš Jakub{\´i}ček and Jelena Kallas and Simon Krek and V{\´i}t Baisa}, publisher = {Lexical Computing CZ s.r.o.}, address = {Brno, Czech Republic}, issn = {2533-5626}, url = {https://nbn-resolving.org/urn:nbn:de:bsz:mh39-64256}, pages = {342 -- 354}, year = {2017}, abstract = {In this paper, we will present a first attempt to classify commonly confused words in German by consulting their communicative functions in corpora. Although the use of so-called paronyms causes frequent uncertainties due to similarities in spelling, sound and semantics, up until now the phenomenon has attracted little attention either from the perspective of corpus linguistics or from cognitive linguistics. Existing investigations rely on structuralist models, which do not account for empirical evidence. Still, they have developed an elaborate model based on formal criteria, primarily on word formation (cf. Lăzărescu 1999). Looking from a corpus perspective, such classifications are incompatible with language in use and cognitive elements of misuse. This article sketches first lexicological insights into a classification model as derived from semantic analyses of written communication. Firstly, a brief description of the project will be provided. Secondly, corpus-assisted paronym detection will be focused. Thirdly, in the main section the paper concerns the description of the datasets for paronym classification and the classification procedures. As a work in progress, new insights will continually be extended once spoken and CMC data are added to the investigations.}, language = {en} }