@inproceedings{JurkiewiczRohrbacherKolakovićHansen2017, author = {Edyta Jurkiewicz-Rohrbacher and Zrinka Kolaković and Bj{\"o}rn Hansen}, title = {Web corpora - the best possible solution for tracking rare phenomena in underresourced languages: clitics in Bosnian, Croatian and Serbian}, series = {Proceedings of the Workshop on Challenges in the Management of Large Corpora and Big Data and Natural Language Processing (CMLC-5+BigNLP) 2017 including the papers from the Web-as-Corpus (WAC-XI) guest section. Birmingham, 24 July 2017}, editor = {Piotr Bański and Marc Kupietz and Harald L{\"u}ngen and Paul Rayson and Hanno Biber and Evelyn Breiteneder and Simon Clematide and John Mariani and Mark Stevenson and Theresa Sick}, publisher = {Institut f{\"u}r Deutsche Sprache}, address = {Mannheim}, url = {https://nbn-resolving.org/urn:nbn:de:bsz:mh39-62667}, pages = {49 -- 55}, year = {2017}, abstract = {Complex linguistic phenomena, such as Clitic Climbing in Bosnian, Croatian and Serbian, are often described intuitively, only from the perspective of the main tendency. In this paper, we argue that web corpora currently offer the best source of empirical material for studying Clitic Climbing in BCS. They thus allow the most accurate description of this phenomenon, as less frequent constructions can be tracked only in big, well-annotated data sources. We compare the properties of web corpora for BCS with traditional sources and give examples of studies on CC based on web corpora. Furthermore, we discuss problems related to web corpora and suggest some improvements for the future.}, language = {en} }