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

Kód výsledku v 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>

Výsledek na webu

<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

—

Jazyk výsledku

angličtina

Název v původním jazyce

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

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

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

Popis výsledku anglicky

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.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

60203 - Linguistics

Projekt

<a href="/cs/project/GA13-27184S" target="_blank" >GA13-27184S: Treebank češtiny na základě gramatiky</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2016

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings of the 16th ITAT: Slovenskočeský NLP workshop (SloNLP 2016)

ISBN

978-1-5370-1674-0

ISSN

1613-0073

e-ISSN

—

Počet stran výsledku

6

Strana od-do

42-47

Název nakladatele

CreateSpace Independent Publishing Platform

Místo vydání

Bratislava

Místo konání akce

Tatranské Matliare, Slovensko

Datum konání akce

17. 9. 2016

Typ akce podle státní příslušnosti

EUR - Evropská akce

Kód UT WoS článku

—