Improving Dependency Parsing by Filtering Linguistic Noise

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11210%2F13%3A10188878" target="_blank" >RIV/00216208:11210/13:10188878 - isvavai.cz</a>
Result on the web
<a href="http://link.springer.com/chapter/10.1007%2F978-3-642-40585-3_37" target="_blank" >http://link.springer.com/chapter/10.1007%2F978-3-642-40585-3_37</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/978-3-642-40585-3_37" target="_blank" >10.1007/978-3-642-40585-3_37</a>

Result language
angličtina
Original language name
Improving Dependency Parsing by Filtering Linguistic Noise
Original language description
In this paper, we describe a way to improve stochastic dependency parsing by simplifying both the training data and new text to be parsed. Many parsing errors are due to limited size of the training data, where most of the words of a given language occurseldom or not at all, thus the parser cannot learn their syntactic properties. By defining narrow classes of words with identical syntactic properties and replacing members of these classes by one representative, we facilitate language modeling done bythe parser and improve its accuracy. In our experiment, a 17.8%decrease in forms variability in the training data of the Czech dependency treebank PDT led to a 8.1% relative error reduction.
Czech name
—
Czech description
—

Project
<a href="/en/project/GA13-27184S" target="_blank" >GA13-27184S: Grammar-based treebank of Czech</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year
2013
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Similar results(10)