Skip to content
conftrace_
2020 ACL ACL 2020

Deep Blue Sonics’ Submission to IWSLT 2020 Open Domain Translation Task

Abstract

AbstractWe present in this report our submission to IWSLT 2020 Open Domain Translation Task. We built a data pre-processing pipeline to efficiently handle large noisy web-crawled corpora, which boosts the BLEU score of a widely used transformer model in this translation task. To tackle the open-domain nature of this task, back- translation is applied to further improve the translation performance.

Authors

Enmin Su, Yi Ren

Topics

Interdisciplinary > Linguistics > Computational Linguistics

Keywords

neural machine translation data preprocessing transformer model web-crawled corpus open domain translation
Download PDF

More from ACL 2020

All ACL 2020 papers →
OPPO’s Machine Translation System for the IWSLT 2020 Open Domain Translation Task
Character Mapping and Ad-hoc Adaptation: Edinburgh’s IWSLT 2020 Open Domain Translation System
CASIA’s System for IWSLT 2020 Open Domain Translation
University of Tsukuba’s Machine Translation System for IWSLT20 Open Domain Translation Task
Xiaomi’s Submissions for IWSLT 2020 Open Domain Translation Task
ISTIC’s Neural Machine Translation System for IWSLT’2020