MUNI-NLP Systems for Low-resource Indic Machine Translation

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216224%3A14330%2F23%3A00138713" target="_blank" >RIV/00216224:14330/23:00138713 - isvavai.cz</a>

Výsledek na webu

<a href="https://aclanthology.org/2023.wmt-1.91.pdf" target="_blank" >https://aclanthology.org/2023.wmt-1.91.pdf</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.18653/v1/2023.wmt-1.91" target="_blank" >10.18653/v1/2023.wmt-1.91</a>

Jazyk výsledku

angličtina

Název v původním jazyce

MUNI-NLP Systems for Low-resource Indic Machine Translation

Popis výsledku v původním jazyce

The WMT 2023 Shared Task on Low-Resource Indic Language Translation featured to and from Assamese, Khasi, Manipuri, Mizo on one side and English on the other. We submitted systems supervised neural machine translation systems for each pair and direction and experimented with different configurations and settings for both preprocessing and training. Even if most of them did not reach competitive performance, our experiments uncovered some interesting points for further investigation, namely the relation between dataset and model size, and the impact of the training framework. Moreover, the results of some of our preliminary experiments on the use of word embeddings initialization, backtranslation, and model depth were in contrast with previous work. The final results also show some disagreement in the automated metrics employed in the evaluation.

Název v anglickém jazyce

MUNI-NLP Systems for Low-resource Indic Machine Translation

Popis výsledku anglicky

The WMT 2023 Shared Task on Low-Resource Indic Language Translation featured to and from Assamese, Khasi, Manipuri, Mizo on one side and English on the other. We submitted systems supervised neural machine translation systems for each pair and direction and experimented with different configurations and settings for both preprocessing and training. Even if most of them did not reach competitive performance, our experiments uncovered some interesting points for further investigation, namely the relation between dataset and model size, and the impact of the training framework. Moreover, the results of some of our preliminary experiments on the use of word embeddings initialization, backtranslation, and model depth were in contrast with previous work. The final results also show some disagreement in the automated metrics employed in the evaluation.

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/LM2023062" target="_blank" >LM2023062: Digitální výzkumná infrastruktura pro jazykové technologie, umění a humanitní vědy</a><br>

Návaznosti

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

Rok uplatnění

2023

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of the Eighth Conference on Machine Translation

ISBN

9798891760417

ISSN

—

e-ISSN

—

Počet stran výsledku

8

Strana od-do

959-966

Název nakladatele

Association for Computational Linguistics

Místo vydání

Singapore

Místo konání akce

Singapore

Datum konání akce

6. 12. 2023

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—