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.

Learning Policies for Multilingual Training of Neural Machine Translation Systems

Domaine:

natural language processing

Type de record:

paper
Créateur:
KumKoeKhu
Hôte:avatar
Low-resource Multilingual Neural Machine Translation (MNMT) is typically tasked with improving the translation performance on one or more language pairs with the aid of high-resource language pairs. In this paper, we propose two simple search based curricula -- orderings of the multilingual training data -- which help improve translation performance in conjunction with existing techniques such as fine-tuning. Additionally, we attempt to learn a curriculum for MNMT from scratch jointly with the training of the translation system with the aid of contextual multi-arm bandits. We show on the FLORES low-resource translation dataset that these learned curricula can provide better starting points for fine tuning and improve overall performance of the translation system. 7 pages, 2 figures

Visit

arxiv.org

Tasks

machine translation

Tags

Computation and Language

Similaires

Multilingual Neural Machine Translation for Zero-Resource LanguagesMultilingual Neural Machine Translation for Low Resource LanguagesGTCOM Neural Machine Translation Systems for WMT21Low Resourced Multilingual Neural Machine Translation for Ometo-EnglishLanguage-Family Adapters for Low-Resource Multilingual Neural Machine TranslationImproving Massively Multilingual Neural Machine Translation and Zero-Shot Translation

Multilingual Neural Machine Translation for Zero-Resource Languages

In recent years, Neural Machine Translation (NMT) has been shown to be more effective than phrase-ba

Multilingual Neural Machine Translation for Low Resource Languages

Neural Machine Translation (NMT) has been shown to be more effective in translation tasks compared t

GTCOM Neural Machine Translation Systems for WMT21

This paper describes the Global Tone Communication Co., Ltd.’s submission of the WMT21 shared news t

Low Resourced Multilingual Neural Machine Translation for Ometo-English

In this paper, we present a new approach to overcome the problem of language resources that share si

Language-Family Adapters for Low-Resource Multilingual Neural Machine Translation

Large multilingual models trained with self-supervision achieve state-of-the-art results in a wide r

Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation

Massively multilingual models for neural machine translation (NMT) are theoretically attractive, but often underperform bilingual models and deliver poor zero-shot translations. In this paper, we explore ways to improve them. We argue that multilingual NMT requires