Machine Translation within One Language as a Paraphrasing Technique

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F14%3A10289361" target="_blank" >RIV/00216208:11320/14:10289361 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Machine Translation within One Language as a Paraphrasing Technique

Popis výsledku v původním jazyce

We present a method for improving machine translation (MT) evaluation by targeted paraphrasing of reference sentences. For this purpose, we employ MT systems themselves and adapt them for translating within a single language. We describe this attempt ontwo types of MT systems -- phrase-based and rule-based. Initially, we experiment with the freely available SMT system Moses. We create translation models from two available sources of Czech paraphrases -- Czech WordNet and the Meteor Paraphrase tables. We extended Moses by a new feature that makes the translation targeted. However, the results of this method are inconclusive. In the view of errors appearing in the new paraphrased sentences, we propose another solution -- targeted paraphrasing using parts of a rule-based translation system included in the NLP framework Treex.

Název v anglickém jazyce

Machine Translation within One Language as a Paraphrasing Technique

Popis výsledku anglicky

We present a method for improving machine translation (MT) evaluation by targeted paraphrasing of reference sentences. For this purpose, we employ MT systems themselves and adapt them for translating within a single language. We describe this attempt ontwo types of MT systems -- phrase-based and rule-based. Initially, we experiment with the freely available SMT system Moses. We create translation models from two available sources of Czech paraphrases -- Czech WordNet and the Meteor Paraphrase tables. We extended Moses by a new feature that makes the translation targeted. However, the results of this method are inconclusive. In the view of errors appearing in the new paraphrased sentences, we propose another solution -- targeted paraphrasing using parts of a rule-based translation system included in the NLP framework Treex.

Druh

D - Stať ve sborníku

CEP obor

IN - Informatika

OECD FORD obor

—

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2014

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of the 14th conference ITAT 2014

ISBN

978-80-87136-18-8

ISSN

1613-0073

e-ISSN

—

Počet stran výsledku

6

Strana od-do

1-6

Název nakladatele

Institute of Computer Science AS CR

Místo vydání

Praha, Czechia

Místo konání akce

Demänovská Dolina, Slovakia

Datum konání akce

25. 9. 2014

Typ akce podle státní příslušnosti

CST - Celostátní akce

Kód UT WoS článku

—