Logo Lanfrica
  • Accueil
  • Atlas
  • Analyses
  • Documentation
  • Sign in

© 2026 Lanfrica. Tous droits réservés. Tous les droits d'auteur des ressources affichées sur le site Web Lanfrica appartiennent aux détenteurs de droits d'auteur d'origine, sauf indication contraire explicite.

Analyzing Subword Techniques to Improve English to Sinhala Neural Machine Translation

Domaine:

natural language processing

Type de record:

paper
Créateur:
RasRavThiUth
Éditeur:
Wor
Hôte:
Neural machine translation (NMT) is a remarkable approach which performs much better than the Statistical machine translation (SMT) models when there is an abundance of parallel corpus. However, vanilla NMT is primarily based upon word-level with a fixed vocabulary. Therefore, low resource morphologically rich languages such as Sinhala are mostly affected by the out of vocabulary (OOV) and Rare word problems. Recent advancements in subword techniques have opened up opportunities for low resource communities by enabling open vocabulary translation. In this paper, we extend our recently published state-of-the-art EN-SI translation system using the transformer and explore standard subword techniques on top of it to identify which subword approach has a greater effect on English Sinhala language pair. Our models demonstrate that subword segmentation strategies along with the state-of-the-art NMT can perform remarkably when translating English sentences into a rich morphology language regardless of a large parallel corpus.

Visit

doi.org

Tasks

machine translation

Similaires

Klaimohelmi/yoruba-to-english-neural-machine-translationSubword-level Segmentation for Neural Machine Translation of Code-switched Dialectal Egyptian Arabic -English TextDevelopment of English-to-Igala machine translation system using neural machine translation with attention mechanismPidginUNMT: Unsupervised Neural Machine Translation from West African Pidgin to EnglishPidginUNMT: Unsupervised Neural Machine Translation from West African Pidgin to EnglishDeep Recurrent Neural Network in Machine Translation from English to Kichuka

Klaimohelmi/yoruba-to-english-neural-machine-translation

# Yoruba-to-english-neural-machine-translation Machine translation (MT) is a popular Natural Langua

Subword-level Segmentation for Neural Machine Translation of Code-switched Dialectal Egyptian Arabic -English Text

Development of English-to-Igala machine translation system using neural machine translation with attention mechanism

Translation is a matter of absolute necessity in the globally united and yet; linguistically and cul

PidginUNMT: Unsupervised Neural Machine Translation from West African Pidgin to English

Over 800 languages are spoken across West Africa. Despite the obvious diversity among people who spe

PidginUNMT: Unsupervised Neural Machine Translation from West African Pidgin to English

Over 800 languages are spoken across West Africa. Despite the obvious diversity among people who speak these languages, one language significantly unifies them all - West African Pidgin English. There are at least 80 million speakers of West African Pidgin English.

Deep Recurrent Neural Network in Machine Translation from English to Kichuka