paper-with-me

Papers

Universal Neural Machine Translation for Extremely Low Resource Languages

2018-02-15 · NAACL 2018 6 · Jiatao Gu, Hany Hassan, Jacob Devlin, Victor O. K. Li

In this paper, we propose a new universal machine translation approach focusing on languages with a limited amount of parallel data. Our proposed approach utilizes a transfer-learning approach to share lexical and sentence level representations across multiple source languages into one target language. The lexical part is shared through a Universal Lexical Representation to support multilingual word-level sharing. The sentence-level sharing is represented by a model of experts from all source languages that share the source encoders with all other languages. This enables the low-resource language to utilize the lexical and sentence representations of the higher resource languages. Our approach is able to achieve 23 BLEU on Romanian-English WMT2016 using a tiny parallel corpus of 6k sentences, compared to the 18 BLEU of strong baseline system which uses multilingual training and back-translation. Furthermore, we show that the proposed approach can achieve almost 20 BLEU on the same dataset through fine-tuning a pre-trained multi-lingual system in a zero-shot setting.

📄 PDF Abstract BibTeX arXiv:1802.05368

Code (0)

등록된 구현이 없습니다.

Tasks

Machine TranslationSentenceTransfer LearningTranslation

Similar Papers 제목 키워드 기반

Using Interlinear Glosses as Pivot in Low-Resource Multilingual Machine Translation

2019-11-07 · Zhong Zhou, Lori Levin, David R. Mortensen, Alex Waibel

We demonstrate a new approach to Neural Machine Translation (NMT) for low-resource languages using a ubiquitous linguistic resource, Interlinear Glossed Text (IGT). IGT represents a non-English sentence as a sequence of …

Machine TranslationNMTSentenceTranslation

Extremely low-resource machine translation for closely related languages

2021-05-27 · NoDaLiDa 2021 5 · Maali Tars, Andre Tättar, Mark Fišel

An effective method to improve extremely low-resource neural machine translation is multilingual training, which can be improved by leveraging monolingual data to create synthetic bilingual corpora using the back-transla…

Low Resource Neural Machine TranslationLow-Resource Neural Machine TranslationMachine TranslationTransfer Learning+1

Learning-From-Mistakes Prompting for Indigenous Language Translation

2024-07-18 · You-Cheng Liao, Chen-Jui Yu, Chi-Yi Lin, He-Feng Yun 외

Using large language models, this paper presents techniques to improve extremely low-resourced indigenous language translations. Our approaches are grounded in the use of (1) the presence of a datastore consisting of a l…

In-Context LearningTranslation

Multilingual Neural Machine Translation with Language Clustering

2019-08-25 · IJCNLP 2019 11 · Xu Tan, Jiale Chen, Di He, Yingce Xia 외

Multilingual neural machine translation (NMT), which translates multiple languages using a single model, is of great practical importance due to its advantages in simplifying the training process, reducing online mainten…

ClusteringMachine TranslationNMTTranslation

Neural Machine Translation for Extremely Low-Resource African Languages: A Case Study on Bambara

2020-11-10 · loresmt (AACL) 2020 12 · Allahsera Auguste Tapo, Bakary Coulibaly, Sébastien Diarra, Christopher Homan 외

Low-resource languages present unique challenges to (neural) machine translation. We discuss the case of Bambara, a Mande language for which training data is scarce and requires significant amounts of pre-processing. Mor…

Machine TranslationTranslation