Improvements to Syntax-based Machine Translation using Ensemble Dependency Parsers

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F13%3A10194639" target="_blank" >RIV/00216208:11320/13:10194639 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Improvements to Syntax-based Machine Translation using Ensemble Dependency Parsers

Popis výsledku v původním jazyce

Dependency parsers are almost ubiqui- tously evaluated on their accuracy scores, these scores say nothing of the complex- ity and usefulness of the resulting struc- tures. The structures may have more com- plexity due to their coordination structure or attachment rules. As dependency parses are basic structures in which other systems are built upon, it would seem more reason- able to judge these parsers down the NLP pipeline. We show results from 7 individual parsers, including dependency and constituent parsers, and 3 ensemble parsing tech- niques with their overall effect on a Ma- chine Translation system, Treex, for En- glish to Czech translation. We show that parsers' UAS scores are more correlated to the NIST evaluation metric than to the BLEU Metric, however we see increases in both metrics.

Název v anglickém jazyce

Improvements to Syntax-based Machine Translation using Ensemble Dependency Parsers

Popis výsledku anglicky

Dependency parsers are almost ubiqui- tously evaluated on their accuracy scores, these scores say nothing of the complex- ity and usefulness of the resulting struc- tures. The structures may have more com- plexity due to their coordination structure or attachment rules. As dependency parses are basic structures in which other systems are built upon, it would seem more reason- able to judge these parsers down the NLP pipeline. We show results from 7 individual parsers, including dependency and constituent parsers, and 3 ensemble parsing tech- niques with their overall effect on a Ma- chine Translation system, Treex, for En- glish to Czech translation. We show that parsers' UAS scores are more correlated to the NIST evaluation metric than to the BLEU Metric, however we see increases in both metrics.

Druh

D - Stať ve sborníku

CEP obor

IN - Informatika

OECD FORD obor

—

Projekt

<a href="/cs/project/LM2010013" target="_blank" >LM2010013: LINDAT-CLARIN: Institut pro analýzu, zpracování a distribuci lingvistických dat</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2013

Kód důvěrnosti údajů

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

Název statě ve sborníku

51st Annual Meeting of the Association for Computational Linguistics, Proceedings of the Second Workshop on Hybrid Approaches to Translation

ISBN

978-1-937284-63-3

ISSN

—

e-ISSN

—

Počet stran výsledku

6

Strana od-do

19-24

Název nakladatele

Omnipress, Inc.

Místo vydání

Sofija, Bulgaria

Místo konání akce

Sofija, Bulgaria

Datum konání akce

8. 8. 2013

Typ akce podle státní příslušnosti

CST - Celostátní akce

Kód UT WoS článku

—