conftrace_

2021 EMNLP EMNLP 2021

The University of Maryland, College Park Submission to Large-Scale Multilingual Shared Task at WMT 2021

Abstract

AbstractThis paper describes the system submitted to Large-Scale Multilingual Shared Task (Small Task #2) at WMT 2021. It is based on the massively multilingual open-source model FLORES101_MM100 model, with selective fine-tuning. Our best-performing system reported a 15.72 average BLEU score for the task.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Natural Language Processing

🐣 Hot Topic Early Bird - low-resource language

Authors

Saptarashmi Bandyopadhyay, Tasnim Kabir, Zizhen Lian, Marine Carpuat

Topics

Deep Learning > Architectures > Transformers Natural Language Processing > Applications > Machine Translation Machine Learning > Learning Types > Transfer Learning Deep Learning > Learning Types > Multimodal Learning Deep Learning > Learning Types > Fine-Tuning

Keywords

machine translation multilingual translation multilingual machine translation low-resource language bleu score selective fine-tuning massively multilingual model

More from EMNLP 2021

All EMNLP 2021 papers →

Transfer Learning with Shallow Decoders: BSC at WMT2021’s Multilingual Low-Resource Translation for Indo-European Languages Shared Task

EdinSaar@WMT21: North-Germanic Low-Resource Multilingual NMT

TenTrans Multilingual Low-Resource Translation System for WMT21 Indo-European Languages Task

To Optimize, or Not to Optimize, That Is the Question: TelU-KU Models for WMT21 Large-Scale Multilingual Machine Translation

MMTAfrica: Multilingual Machine Translation for African Languages

The LMU Munich System for the WMT 2021 Large-Scale Multilingual Machine Translation Shared Task