[ Skip to the content ]

Institute of Formal and Applied Linguistics

at Faculty of Mathematics and Physics, Charles University, Prague, Czech Republic


[ Back to the navigation ]

Publication


Year 2017
Type in proceedings
Status submitted
Language English
Author(s) Dwivedi, Puneet Zeman, Daniel
Title Universal Dependencies for Sanskrit: A Pilot Study
Czech title Universal Dependencies pro sanskrt: pilotní studie
Note Submitted to EACL and to LAW.
How published online
Supported by 2015-2017 GA15-10472S (Morfologicky a syntakticky anotované korpusy mnoha jazyků) 2012-2016 PRVOUK P46 (Informatika)
Czech abstract Popisujeme první kroky k syntakticky anotovanému korpusu pro sanskrt v rámci formalismu Universal Dependencies. Naše data jsou zatím velmi malá, obsahují pouze necelých 200 vět — jde o výsledek projektu během letní stáže. Nicméně, pokud víme, toto je první veřejně dostupný syntakticky anotovaný text v sanskrtu. Popisujeme také experiment s automatickou syntaktickou analýzou (parsingem), s výsledky lepšími než u delexikalizovaného parsingu.
English abstract We present the first steps towards a treebank of Sanskrit within the Universal Dependencies framework. Our dataset is tiny at the moment, consisting of less than 200 sentences—a result of a summer internship project. Nevertheless, this seems to be, to the best of our knowledge, the first publicly available piece of syntactically annotated Sanskrit text. We also present a parsing experiment, with results surpassing delexicalized parsing.
Specialization linguistics ("jazykověda")
Confidentiality default – not confidential
Open access no
Article no. 35
Creator: Common Account
Created: 9/26/16 8:32 AM
Modifier: Common Account
Modified: 1/13/17 2:45 PM
***

Content, Design & Functionality: ÚFAL, 2006–2016. Page generated: Sat Sep 23 21:54:10 CEST 2017

[ Back to the navigation ] [ Back to the content ]

100% OpenAIRE compliant