Naver Labs Europe’s Systems for the WMT19 Machine Translation Robustness Task

Naver Labs Europe’s Systems for the WMT19 Machine Translation Robustness Task
复制标题

Naver Labs Europe 用于 WMT19 机器翻译鲁棒性任务的系统

DOI:
--
复制
发表时间:
2019
期刊:
Conference on Machine Translation
影响因子:
--
通讯作者:
Claude Roux
Claude Roux
中科院分区:
--
文献类型:
--
作者:
Alexandre Berard;Ioan Calapodescu;Claude Roux

文献摘要

参考文献

被引文献

相似文献

本文描述了我们提交给WMT19机器翻译鲁棒性任务的系统。这项任务旨在提高机器翻译对社交媒体上的噪音的鲁棒性,比如非正式语言、拼写错误和其他正字法变化。组织者提供了从社交媒体网站上提取的平行数据,分为两种语言:法语-英语和日语-英语(每种语言方向各一种)。目标是根据自动度量(BLEU)和人工评估,在来自同一来源的未见过的测试集上获得最佳分数。我们提出了一个单一的和一个集成系统为每个翻译方向。根据BLEU的评估,我们的集成模型在所有语言对中排名第一。我们讨论了我们所做的预处理选择,并提出了我们对噪声和域自适应的鲁棒性的解决方案。
This paper describes the systems that we submitted to the WMT19 Machine Translation robustness task. This task aims to improve MT’s robustness to noise found on social media, like informal language, spelling mistakes and other orthographic variations. The organizers provide parallel data extracted from a social media website in two language pairs: French-English and Japanese-English (one for each language direction). The goal is to obtain the best scores on unseen test sets from the same source, according to automatic metrics (BLEU) and human evaluation. We propose one single and one ensemble system for each translation direction. Our ensemble models ranked first in all language pairs, according to BLEU evaluation. We discuss the pre-processing choices that we made, and present our solutions for robustness to noise and domain adaptation.
利用合成噪声提高机器翻译的鲁棒性
DOI: --
发表时间: 2019
期刊: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
影响因子: --
作者:
Vaibhav, Vaibhav;Singh, Sumeet;Stewart, Craig;Neubig, Graham
通讯作者: Neubig, Graham