ParsPer: A Dependency Parser for Persian
2015 (English)In: Depling 2015: Third International Conference on Dependency Linguistics, Uppsala: Uppsala universitet, 2015, 300-309 p.Conference paper (Refereed)
We present a dependency parser for Persian, called ParsPer, developed using the graph-based parser in the Mate Tools. The parser is trained on the entire Uppsala Persian Dependency Treebank with a specific configuration that was selected by MaltParser as the best performing parsing representation. The treebank’s syntactic annotation scheme is based on Stanford Typed Dependencies with extensions for Persian. The results of the ParsPer evaluation revealed a best labeled accuracy over 82% with an unlabeled accuracy close to 87%. The parser is freely available and released as an open source tool for parsing Persian.
Place, publisher, year, edition, pages
Uppsala: Uppsala universitet, 2015. 300-309 p.
Language Technology (Computational Linguistics)
IdentifiersURN: urn:nbn:se:uu:diva-268907ISBN: 978-91-637-8965-6OAI: oai:DiVA.org:uu-268907DiVA: diva2:881563
International Conference on Dependency Linguistics (DepLing 2015), August 24-26, 2015, Uppsala, Sweden