paper-with-me

홈 › Papers

Breaking Down Multilingual Machine Translation

2021-10-15 · Findings (ACL) 2022 5 · Ting-Rui Chiang, Yi-Pei Chen, Yi-Ting Yeh, Graham Neubig

While multilingual training is now an essential ingredient in machine translation (MT) systems, recent work has demonstrated that it has different effects in different multilingual settings, such as many-to-one, one-to-many, and many-to-many learning. These training settings expose the encoder and the decoder in a machine translation model with different data distributions. In this paper, we examine how different varieties of multilingual training contribute to learning these two components of the MT model. Specifically, we compare bilingual models with encoders and/or decoders initialized by multilingual training. We show that multilingual training is beneficial to encoders in general, while it only benefits decoders for low-resource languages (LRLs). We further find the important attention heads for each language pair and compare their correlations during inference. Our analysis sheds light on how multilingual translation models work and enables us to propose methods to improve performance by training with highly related languages. Our many-to-one models for high-resource languages and one-to-many models for LRL outperform the best results reported by Aharoni et al. (2019)

📄 PDF Abstract BibTeX arXiv:2110.08130

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderMachine TranslationTranslation

Similar Papers 제목 키워드 기반

Breaking Down Multilingual Machine Translation

2021-05-16 · ACL ARR November 2021 11 · Anonymous

While multilingual training is now an essential ingredient in machine translation (MT) systems, recent work has demonstrated that it has different effects in different multilingual settings, such as many-to-one, one-to-m…

DecoderMachine TranslationTranslation

Comparative analysis of subword tokenization approaches for Indian languages

2025-05-22 · Sudhansu Bala Das, Samujjal Choudhury, Tapas Kumar Mishra, Bidyut Kr. Patra

Tokenization is the act of breaking down text into smaller parts, or tokens, that are easier for machines to process. This is a key phase in machine translation (MT) models. Subword tokenization enhances this process by …

Machine TranslationTranslation

Evaluating the Cross-Lingual Effectiveness of Massively Multilingual Neural Machine Translation

2019-09-01 · Aditya Siddhant, Melvin Johnson, Henry Tsai, Naveen Arivazhagan 외

The recently proposed massively multilingual neural machine translation (NMT) system has been shown to be capable of translating over 100 languages to and from English within a single model. Its improved translation perf…

Cross-Lingual TransferMachine TranslationNMTTransfer Learning+1

How Robust is Neural Machine Translation to Language Imbalance in Multilingual Tokenizer Training?

2022-04-29 · AMTA 2022 9 · Shiyue Zhang, Vishrav Chaudhary, Naman Goyal, James Cross 외

A multilingual tokenizer is a fundamental component of multilingual neural machine translation. It is trained from a multilingual corpus. Since a skewed data distribution is considered to be harmful, a sampling strategy …

Machine TranslationTranslation

Benefiting from Language Similarity in the Multilingual MT Training: Case Study of Indonesian and Malaysian

2022-10-01 · loresmt (COLING) 2022 10 · Alberto Poncelas, Johanes Effendi

The development of machine translation (MT) has been successful in breaking the language barrier of the world’s top 10-20 languages. However, for the rest of it, delivering an acceptable translation quality is still a ch…

Machine TranslationTranslation