End-to-End Lexically Constrained Machine Translation for Morphologically Rich Languages

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F21%3A10440543" target="_blank" >RIV/00216208:11320/21:10440543 - isvavai.cz</a>

Výsledek na webu

<a href="https://aclanthology.org/2021.acl-long.311" target="_blank" >https://aclanthology.org/2021.acl-long.311</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.18653/v1/2021.acl-long.311" target="_blank" >10.18653/v1/2021.acl-long.311</a>

Jazyk výsledku

angličtina

Název v původním jazyce

End-to-End Lexically Constrained Machine Translation for Morphologically Rich Languages

Popis výsledku v původním jazyce

Lexically constrained machine translation allows the user to manipulate the output sentence by enforcing the presence or absence of certain words and phrases. Although current approaches can enforce terms to appear in the translation, they often struggle to make the constraint word form agree with the rest of the generated output. Our manual analysis shows that 46% of the errors in the output of a baseline constrained model for English to Czech translation are related to agreement. We investigate mechanisms to allow neural machine translation to infer the correct word inflection given lemmatized constraints. In particular, we focus on methods based on training the model with constraints provided as part of the input sequence. Our experiments on the English-Czech language pair show that this approach improves the translation of constrained terms in both automatic and manual evaluation by reducing errors in agreement. Our approach thus eliminates inflection errors, without introducing new errors or decr

Název v anglickém jazyce

End-to-End Lexically Constrained Machine Translation for Morphologically Rich Languages

Popis výsledku anglicky

Lexically constrained machine translation allows the user to manipulate the output sentence by enforcing the presence or absence of certain words and phrases. Although current approaches can enforce terms to appear in the translation, they often struggle to make the constraint word form agree with the rest of the generated output. Our manual analysis shows that 46% of the errors in the output of a baseline constrained model for English to Czech translation are related to agreement. We investigate mechanisms to allow neural machine translation to infer the correct word inflection given lemmatized constraints. In particular, we focus on methods based on training the model with constraints provided as part of the input sequence. Our experiments on the English-Czech language pair show that this approach improves the translation of constrained terms in both automatic and manual evaluation by reducing errors in agreement. Our approach thus eliminates inflection errors, without introducing new errors or decr

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/GX19-26934X" target="_blank" >GX19-26934X: Neuronové reprezentace v multimodálním a mnohojazyčném modelování</a><br>

Návaznosti

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

Rok uplatnění

2021

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of the Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing

ISBN

978-1-954085-52-7

ISSN

—

e-ISSN

—

Počet stran výsledku

15

Strana od-do

4019-4033

Název nakladatele

Association for Computational Linguistics

Místo vydání

Stroudsburg, PA, USA

Místo konání akce

Online

Datum konání akce

2. 8. 2021

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—