@inproceedings{KirkČermakova2017, author = {John Kirk and Anna Čerm{\´a}kov{\´a}}, title = {From ICE to ICC: The new International Comparable Corpus}, 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:mh39-62490}, pages = {7 -- 12}, year = {2017}, abstract = {This paper outlines the broad research context and rationale for a new international comparable corpus (ICC). The ICC is to be largely modelled on the text categories and their quantities the International Corpus of English with only a few changes. The corpus will initially begin with nine European languages but others may join in due course. The paper reports on those and other agreements made at the inaugural planning meeting in Prague on 22-23 June 2017. It also sets out the project’s goals for its first two years.}, language = {en} }