Partial Accuracy Rates and Agreements of Parsers: Two Experiments With Ensemble Parsing of Czech

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11210%2F16%3A10330274" target="_blank" >RIV/00216208:11210/16:10330274 - isvavai.cz</a>
Result on the web
<a href="http://ceur-ws.org/Vol-1649/42.pdf" target="_blank" >http://ceur-ws.org/Vol-1649/42.pdf</a>
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
Partial Accuracy Rates and Agreements of Parsers: Two Experiments With Ensemble Parsing of Czech
Original language description
The paper presents two experiments with ensemble parsing, in which we obtain a 1.4% improvement of UAS compared to the best parser. We use five parsers: MateParser, TurboParser, Parsito, MaltParser a MSTParser, and the data of the analytical layer of Prague Dependency Treebank (1.5 million tokens). We split training data into 10 data-splits and run a 10-fold cross-validation scheme with each of the five parsers. In this way, we obtain large parsed data to experiment with. In one experiment, we calculate partial accuracy rates of each parser according to a list of parameters, which we then use as weights in a combination of parsers using an algorithm for finding the maximum spanning tree. In the other experiment, we calculate success rates for agreements of parsers (e.g. Mate+MST vs. Turbo+Malt), and use these rates in another combination of parsers. Both experiments achieve an UAS above 90.0% (1.4% higher than TurboParser), the experiment with accuracy rates achieves better LAS.
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)<br>I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

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

Article name in the collection
Proceedings of the 16th ITAT: Slovenskočeský NLP workshop (SloNLP 2016)
ISBN
978-1-5370-1674-0
ISSN
1613-0073
e-ISSN
—
Number of pages
6
Pages from-to
42-47
Publisher name
CreateSpace Independent Publishing Platform
Place of publication
Bratislava
Event location
Tatranské Matliare, Slovensko
Event date
Sep 17, 2016
Type of event by nationality
EUR - Evropská akce
UT code for WoS article
—

Similar results(10)