Logo Lanfrica
  • Home
  • Atlas
  • Insights
  • Docs
  • Sign in

© 2026 Lanfrica. All rights reserved. All copyrights of the resources shown on the Lanfrica website belong to the original copyright holders, unless explicitly stated otherwise.

A3-108 Controlling Token Generation in Low Resource Machine Translation Systems

Domain:

natural language processing

Record type:

paper
Creator:
AssShrivastava, ManishYad
Publisher:
Und
Host:avatar
Translating for low-resource languages is challenging due to limited quality data. We improved translation performance by integrating target sentence length as an additional feature to source sentence during training. We developed transformer models and evaluated across 8 language directions (English <=> Assamese, Manipuri, Khasi, and Mizo), using four different length encoding methods. Comparing these models to the baseline, we submitted two systems per language direction and present our findings here.​

Visit

doi.orgunderline.io

Tasks

machine translation

Tags

Computational LinguisticsNatural Language Processing

Similar

Benchmarking of Low-Resource Machine Translation SystemsTopXGen: Topic-Diverse Parallel Data Generation for Low-Resource Machine TranslationIntegrating Unsupervised Data Generation into Self-Supervised Neural Machine Translation for Low-Resource LanguagesNeural Network Based Machine Translation Systems for Low Resource Languages: A ReviewDeeveshBeegun/low-resource-neural-machine-translationMoneebAliKarrar/low-resource-neural-machine-translation

Benchmarking of Low-Resource Machine Translation Systems

Assessing the performance of machine translation systems is of critical value, especially to languag

TopXGen: Topic-Diverse Parallel Data Generation for Low-Resource Machine Translation

LLMs have been shown to perform well in machine translation (MT) with the use of in-context learning

Integrating Unsupervised Data Generation into Self-Supervised Neural Machine Translation for Low-Resource Languages

For most language combinations, parallel data is either scarce or simply unavailable. To address thi

Neural Network Based Machine Translation Systems for Low Resource Languages: A Review

Machine translation of documents into regional languages has important role nowadays. Deep neural ne

DeeveshBeegun/low-resource-neural-machine-translation

# Transformer Neural Machine Translation for Nguni langauges Neural Machine Translation (NMT) has

MoneebAliKarrar/low-resource-neural-machine-translation

# Machine_Translation # Low-Resource Machine Translation (Arabic–Igbo) ## Overview This project foc