@misc{10498/17823, year = {2015}, month = {1}, url = {http://hdl.handle.net/10498/17823}, abstract = {In this paper we describe the CLEC corpus, an ongoing project set up at the University of Cádiz with the purpose of building up a large corpus of English as a 2L classified according to CEFR proficiency levels and formed to train statistical models for automatic proficiency assessment. The goal of this corpus is twofold: on the one hand it will be used as a data resource for the development of automatic text classification systems and, on the other, it has been used as a means of teaching innovation techniques.}, publisher = {Elsevier}, keywords = {automatic assessment}, keywords = {CEFR proficiency labels}, keywords = {teaching innovation techniques}, keywords = {corpus linguistics}, keywords = {automatic linguistic profile}, title = {Building a Corpus of 2L English for Automatic Assessment: the CLEC Corpus}, doi = {10.1016/j.sbspro.2015.07.474}, author = {Zarco Tejada, María Ángeles and Noya Gallardo, María Del Carmen and Merino Ferradá, María del Carmen and Calderón López, María Isabel}, }