paper-with-me

Papers

Learning Curricula for Multilingual Neural Machine Translation Training

2021-08-01 · MTSummit 2021 8 · Gaurav Kumar, Philipp Koehn, Sanjeev Khudanpur

Low-resource Multilingual Neural Machine Translation (MNMT) is typically tasked with improving the translation performance on one or more language pairs with the aid of high-resource language pairs. In this paper and we propose two simple search based curricula – orderings of the multilingual training data – which help improve translation performance in conjunction with existing techniques such as fine-tuning. Additionally and we attempt to learn a curriculum for MNMT from scratch jointly with the training of the translation system using contextual multi-arm bandits. We show on the FLORES low-resource translation dataset that these learned curricula can provide better starting points for fine tuning and improve overall performance of the translation system.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Machine TranslationTranslation

Similar Papers 제목 키워드 기반

Learning Policies for Multilingual Training of Neural Machine Translation Systems

2021-03-11 · Gaurav Kumar, Philipp Koehn, Sanjeev Khudanpur

Low-resource Multilingual Neural Machine Translation (MNMT) is typically tasked with improving the translation performance on one or more language pairs with the aid of high-resource language pairs. In this paper, we pro…

Machine TranslationTranslation

Domain Curricula for Code-Switched MT at MixMT 2022

2022-10-31 · Lekan Raheem, Maab Elrashid

In multilingual colloquial settings, it is a habitual occurrence to compose expressions of text or speech containing tokens or phrases of different languages, a phenomenon popularly known as code-switching or code-mixing…

Machine TranslationSentenceTranslation

Meta-Curriculum Learning for Domain Adaptation in Neural Machine Translation

2021-03-03 · Runzhe Zhan, Xuebo Liu, Derek F. Wong, Lidia S. Chao

Meta-learning has been sufficiently validated to be beneficial for low-resource neural machine translation (NMT). However, we find that meta-trained NMT fails to improve the translation performance of the domain unseen a…

Domain AdaptationLow Resource Neural Machine TranslationLow-Resource Neural Machine TranslationMachine Translation+3

Curriculum Learning and Minibatch Bucketing in Neural Machine Translation

2017-07-29 · RANLP 2017 9 · Tom Kocmi, Ondrej Bojar

We examine the effects of particular orderings of sentence pairs on the on-line training of neural machine translation (NMT). We focus on two types of such orderings: (1) ensuring that each minibatch contains sentences s…

Machine TranslationNMTSentenceTranslation

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