Discriminating Between Similar Languages Using Large Web Corpora

descriptionPublicationkeyboard_double_arrow_right Article , Conference object 01 Jan 2019Publisher:ZenodoJournal:Proceedings of Recent Advances in Slavonic Natural Language Processing, RASLAN 2019Funded by:EC | ELEXIS

Authors: Vít Suchomel;

doi: 10.5281/zenodo.6935082 , 10.5281/zenodo.6935083

Discriminating Between Similar Languages Using Large Web Corpora

- Summary
- Subjects
- Metrics

Abstract

This paper presents a method for discriminating similar lan-guages based on wordlists from large web corpora. The main benefits ofthe approach are language independency, a measure of confidence of theclassification and an easy-to-maintain implementation.The method is evaluated on VarDial 2014 workshop data set. The resultaccuracy is comparable to other methods successfully performing at theworkshop.A tool implementing the method in Python can be obtained from web sitehttp://corpus.tools/.

Keywords

strategies, tools, standards for lexicographic resources (objective 3), WP4

Impact byBIP!

	selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	0
	popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.	Average
	influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	Average
	impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.	Average