Delexicalized and Minimally Supervised Parsing on Universal Dependencies

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F16%3A10335497" target="_blank" >RIV/00216208:11320/16:10335497 - isvavai.cz</a>
Result on the web
<a href="http://dx.doi.org/10.1007/978-3-319-45925-7_3" target="_blank" >http://dx.doi.org/10.1007/978-3-319-45925-7_3</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/978-3-319-45925-7_3" target="_blank" >10.1007/978-3-319-45925-7_3</a>

Result language
angličtina
Original language name
Delexicalized and Minimally Supervised Parsing on Universal Dependencies
Original language description
In this paper, we compare delexicalized transfer and minimally supervised parsing techniques on 32 different languages from Universal Dependencies treebank collection. The minimal supervision is in adding handcrafted universal grammatical rules for POS tags. The rules are incorporated into the unsupervised dependency parser in forms of external prior probabilities. We also experiment with learning this probabilities from other treebanks. The average attachment score of our parser is slightly lower then the delexicalized transfer parser, however, it performs better for languages from less resourced language families (non-Indo-European) and is therefore suitable for those, for which the treebanks often do not exist.
Czech name
—
Czech description
—

Project
<a href="/en/project/GP14-06548P" target="_blank" >GP14-06548P: Sentence structure induction without annotated corpora</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year
2016
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Similar results(10)