@inproceedings{04d4d6736f38445fb97f4f4a7f991a07,
title = "The Hebrew Essay Corpus",
abstract = "We present the Hebrew Essay Corpus: an annotated corpus of Hebrew language argumentative essays authored by prospective higher-education students. The corpus includes both essays by native speakers, written as part of the psychometric exam that is used to assess their future success in academic studies; and essays authored by non-native speakers, with three different native languages, that were written as part of a language aptitude test. The corpus is uniformly encoded and stored. The nonnative essays were annotated with target hypotheses whose main goal is to make the texts amenable to automatic processing (morphological and syntactic analysis). The corpus is available for academic purposes upon request. We describe the corpus and the error correction and annotation schemes used in its analysis. In addition to introducing this new resource, we discuss the challenges of identifying and analyzing non-native language use in general, and propose various ways for dealing with these challenges.",
keywords = "Hebrew, Learner corpora, non-native language",
author = "Chen Gafni and Anat Prior and Shuly Wintner",
note = "Publisher Copyright: {\textcopyright} European Language Resources Association (ELRA), licensed under CC-BY-NC-4.0.; 13th International Conference on Language Resources and Evaluation Conference, LREC 2022 ; Conference date: 20-06-2022 Through 25-06-2022",
year = "2022",
language = "الإنجليزيّة",
series = "2022 Language Resources and Evaluation Conference, LREC 2022",
pages = "5580--5586",
editor = "Nicoletta Calzolari and Frederic Bechet and Philippe Blache and Khalid Choukri and Christopher Cieri and Thierry Declerck and Sara Goggi and Hitoshi Isahara and Bente Maegaard and Joseph Mariani and Helene Mazo and Jan Odijk and Stelios Piperidis",
booktitle = "2022 Language Resources and Evaluation Conference, LREC 2022",
}