Saved in:
Bibliographic Details
Main Authors: Tourni, Isidora Chara, Naskar, Subhajit
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2310.12236
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911880211070976
author Tourni, Isidora Chara
Naskar, Subhajit
author_facet Tourni, Isidora Chara
Naskar, Subhajit
contents Direct neural machine translation (direct NMT) is a type of NMT system that translates text between two non-English languages. Direct NMT systems often face limitations due to the scarcity of parallel data between non-English language pairs. Several approaches have been proposed to address this limitation, such as multilingual NMT and pivot NMT (translation between two languages via English). Task-level Mixture of expert models (Task-level MoE), an inference-efficient variation of Transformer-based models, has shown promising NMT performance for a large number of language pairs. In Task-level MoE, different language groups can use different routing strategies to optimize cross-lingual learning and inference speed. In this work, we examine Task-level MoE's applicability in direct NMT and propose a series of high-performing training and evaluation configurations, through which Task-level MoE-based direct NMT systems outperform bilingual and pivot-based models for a large number of low and high-resource direct pairs, and translation directions. Our Task-level MoE with 16 experts outperforms bilingual NMT, Pivot NMT models for 7 language pairs, while pivot-based models still performed better in 9 pairs and directions.
format Preprint
id arxiv_https___arxiv_org_abs_2310_12236
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Direct Neural Machine Translation with Task-level Mixture of Experts models
Tourni, Isidora Chara
Naskar, Subhajit
Computation and Language
Direct neural machine translation (direct NMT) is a type of NMT system that translates text between two non-English languages. Direct NMT systems often face limitations due to the scarcity of parallel data between non-English language pairs. Several approaches have been proposed to address this limitation, such as multilingual NMT and pivot NMT (translation between two languages via English). Task-level Mixture of expert models (Task-level MoE), an inference-efficient variation of Transformer-based models, has shown promising NMT performance for a large number of language pairs. In Task-level MoE, different language groups can use different routing strategies to optimize cross-lingual learning and inference speed. In this work, we examine Task-level MoE's applicability in direct NMT and propose a series of high-performing training and evaluation configurations, through which Task-level MoE-based direct NMT systems outperform bilingual and pivot-based models for a large number of low and high-resource direct pairs, and translation directions. Our Task-level MoE with 16 experts outperforms bilingual NMT, Pivot NMT models for 7 language pairs, while pivot-based models still performed better in 9 pairs and directions.
title Direct Neural Machine Translation with Task-level Mixture of Experts models
topic Computation and Language
url https://arxiv.org/abs/2310.12236