DMCA
Noname manuscript No. (will be inserted by the editor) Parsing Hebrew CHILDES Transcripts (2013)
BibTeX
@MISC{Gretz13nonamemanuscript,
author = {Shai Gretz and Alon Itai and Brian Macwhinney Bracha and Nir Shuly Wintner},
title = {Noname manuscript No. (will be inserted by the editor) Parsing Hebrew CHILDES Transcripts},
year = {2013}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Abstract We present a syntactic parser of (transcripts of) spoken Hebrew: a dependency parser of the Hebrew CHILDES database. CHILDES is a corpus of child–adult linguistic interactions. Its Hebrew section has recently been morphologically analyzed and disambiguated, paving the way for syntactic an-notation. This paper describes a novel annotation scheme of dependency relations reflecting constructions of child and child-directed Hebrew utterances. A subset of the corpus was annotated with dependency relations according to this scheme, and was used to train two parsers (MaltParser and MEGRASP) with which the rest of the data were parsed. The adequacy of the annotation scheme to the CHILDES data is established through numerous evaluation scenarios. The paper also discusses different annotation approaches to several linguistic phenomena, as well as the contribution of morphological features to the accuracy of parsing.
Keyphrases
hebrew childes transcript dependency relation novel annotation scheme childes data dependency parser hebrew section syntactic an-notation different annotation approach child adult linguistic interaction syntactic parser numerous evaluation scenario annotation scheme hebrew childes database child-directed hebrew utterance several linguistic phenomenon morphological feature
