paper-with-me

Papers

Improving Multilingual Neural Machine Translation with Auxiliary Source Languages

2021-11-01 · Findings (EMNLP) 2021 11 · Weijia Xu, Yuwei Yin, Shuming Ma, Dongdong Zhang, Haoyang Huang

Multilingual neural machine translation models typically handle one source language at a time. However, prior work has shown that translating from multiple source languages improves translation quality. Different from existing approaches on multi-source translation that are limited to the test scenario where parallel source sentences from multiple languages are available at inference time, we propose to improve multilingual translation in a more common scenario by exploiting synthetic source sentences from auxiliary languages. We train our model on synthetic multi-source corpora and apply random masking to enable flexible inference with single-source or bi-source inputs. Extensive experiments on Chinese/English-Japanese and a large-scale multilingual translation benchmark show that our model outperforms the multilingual baseline significantly by up to +4.0 BLEU with the largest improvements on low-resource or distant language pairs.

📄 PDF Abstract BibTeX

Code (1)

YuweiYin/MNMT_Aux_Src_Lang 공식 구현 pytorch

Tasks

Machine TranslationTranslation

Similar Papers 제목 키워드 기반

Multilingual word translation using auxiliary languages

2019-11-01 · IJCNLP 2019 11 · Hagai Taitelbaum, Gal Chechik, Jacob Goldberger

Current multilingual word translation methods are focused on jointly learning mappings from each language to a shared space. The actual translation, however, is still performed as an isolated bilingual task. In this stud…

TranslationWord Translation

Analyzing and Improving Cross-lingual Knowledge Transfer for Machine Translation

2026-01-07 · David Stap arxiv

Multilingual machine translation systems aim to make knowledge accessible across languages, yet learning effective cross-lingual representations remains challenging. These challenges are especially pronounced for low-res…

Machine Translation

Multilingual Agreement for Multilingual Neural Machine Translation

2021-08-01 · ACL 2021 5 · Jian Yang, Yuwei Yin, Shuming Ma, Haoyang Huang 외

Although multilingual neural machine translation (MNMT) enables multiple language translations, the training process is based on independent multilingual objectives. Most multilingual models can not explicitly exploit di…

Machine TranslationTranslation

Target Conditioned Sampling: Optimizing Data Selection for Multilingual Neural Machine Translation

2019-05-20 · ACL 2019 7 · Xinyi Wang, Graham Neubig

To improve low-resource Neural Machine Translation (NMT) with multilingual corpora, training on the most related high-resource language only is often more effective than using all data available (Neubig and Hu, 2018). Ho…

Low Resource Neural Machine TranslationLow-Resource Neural Machine TranslationLow Resource NMTMachine Translation+3

Auxiliary Subword Segmentations as Related Languages for Low Resource Multilingual Translation

2022-06-01 · EAMT 2022 6 · Nishant Kambhatla, Logan Born, Anoop Sarkar

We propose a novel technique that combines alternative subword tokenizations of a single source-target language pair that allows us to leverage multilingual neural translation training methods. These alternate segmentati…

Cross-Lingual TransferTranslation