@inproceedings{f15df12461504fc8945178f1c250f934,
title = "A Morphologically Annotated Hebrew CHILDES Corpus",
abstract = "We present a corpus of transcribed spoken Hebrew that reflects spoken interactions between children and adults. The corpus is an integral part of the CHILDES database, which distributes similar corpora for over 25 languages. We introduce a dedicated transcription scheme for the spoken Hebrew data that is sensitive to both the phonology and the standard orthography of the language. We also introduce a morphological analyzer that was specifically developed for this corpus. The analyzer adequately covers the entire corpus, producing detailed correct analyses for all tokens. Evaluation on a new corpus reveals high coverage as well. Finally, we describe a morphological disambiguation module that selects the correct analysis of each token in context. The result is a high-quality morphologically-annotated CHILDES corpus of Hebrew, along with a set of tools that can be applied to new corpora.",
author = "Aviad Albert and Brian MacWhinney and Bracha Nir and Shuly Wintner",
year = "2012",
language = "אנגלית",
series = "EACL '12",
publisher = "Association for Computational Linguistics",
pages = "20–22",
booktitle = "Proceedings of the Workshop on Computational Models of Language Acquisition and Loss",
address = "ארצות הברית",
}