English
Related papers

Related papers: Joint Training for Neural Machine Translation Mode…

200 papers

We propose a method to transfer knowledge across neural machine translation (NMT) models by means of a shared dynamic vocabulary. Our approach allows to extend an initial model for a given language pair to cover new languages by adapting…

Computation and Language · Computer Science 2018-11-06 Surafel M. Lakew , Aliia Erofeeva , Matteo Negri , Marcello Federico , Marco Turchi

In this paper, we propose a two-phase training approach where pre-trained large language models are continually pre-trained on parallel data and then supervised fine-tuned with a small amount of high-quality parallel data. To investigate…

Computation and Language · Computer Science 2024-07-04 Minato Kondo , Takehito Utsuro , Masaaki Nagata

This paper proposes a technique for adding a new source or target language to an existing multilingual NMT model without re-training it on the initial set of languages. It consists in replacing the shared vocabulary with a small…

Computation and Language · Computer Science 2021-10-22 Alexandre Berard

Using pre-trained word embeddings as input layer is a common practice in many natural language processing (NLP) tasks, but it is largely neglected for neural machine translation (NMT). In this paper, we conducted a systematic analysis on…

Computation and Language · Computer Science 2018-06-15 Shuoyang Ding , Kevin Duh

An effective method to improve neural machine translation with monolingual data is to augment the parallel training corpus with back-translations of target language sentences. This work broadens the understanding of back-translation and…

Computation and Language · Computer Science 2018-10-04 Sergey Edunov , Myle Ott , Michael Auli , David Grangier

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-resource languages,…

Computation and Language · Computer Science 2026-01-08 David Stap

Multilingual neural machine translation (MNMT) trained in multiple language pairs has attracted considerable attention due to fewer model parameters and lower training costs by sharing knowledge among multiple languages. Nonetheless,…

Computation and Language · Computer Science 2022-07-21 Jian Yang , Yuwei Yin , Shuming Ma , Dongdong Zhang , Zhoujun Li , Furu Wei

While synthetic bilingual corpora have demonstrated their effectiveness in low-resource neural machine translation (NMT), adding more synthetic data often deteriorates translation performance. In this work, we propose alternated training…

Computation and Language · Computer Science 2021-06-17 Rui Jiao , Zonghan Yang , Maosong Sun , Yang Liu

While recent neural machine translation approaches have delivered state-of-the-art performance for resource-rich language pairs, they suffer from the data scarcity problem for resource-scarce language pairs. Although this problem can be…

Computation and Language · Computer Science 2017-02-22 Yong Cheng , Yang Liu , Qian Yang , Maosong Sun , Wei Xu

Pre-training and fine-tuning have achieved great success in the natural language process field. The standard paradigm of exploiting them includes two steps: first, pre-training a model, e.g. BERT, with a large scale unlabeled monolingual…

Computation and Language · Computer Science 2019-12-05 Rongxiang Weng , Heng Yu , Shujian Huang , Shanbo Cheng , Weihua Luo

Multilingual Neural Machine Translation (MNMT) models are commonly trained on a joint set of bilingual corpora which is acutely English-centric (i.e. English either as the source or target language). While direct data between two languages…

Computation and Language · Computer Science 2020-10-21 Markus Freitag , Orhan Firat

Prior works have demonstrated that a low-resource language pair can benefit from multilingual machine translation (MT) systems, which rely on many language pairs' joint training. This paper proposes two simple strategies to address the rare…

Computation and Language · Computer Science 2021-07-13 Thi-Vinh Ngo , Phuong-Thai Nguyen , Thanh-Le Ha , Khac-Quy Dinh , Le-Minh Nguyen

Multilingual Neural Machine Translation approaches are based on the use of task-specific models and the addition of one more language can only be done by retraining the whole system. In this work, we propose a new training schedule that…

Computation and Language · Computer Science 2019-07-12 Carlos Escolano , Marta R. Costa-Jussà , José A. R. Fonollosa

Machine translation has recently achieved impressive performance thanks to recent advances in deep learning and the availability of large-scale parallel corpora. There have been numerous attempts to extend these successes to low-resource…

Computation and Language · Computer Science 2018-04-16 Guillaume Lample , Alexis Conneau , Ludovic Denoyer , Marc'Aurelio Ranzato

The advent of deep learning has led to a significant gain in machine translation. However, most of the studies required a large parallel dataset which is scarce and expensive to construct and even unavailable for some languages. This paper…

Computation and Language · Computer Science 2023-04-04 Viet H. Pham , Thang M. Pham , Giang Nguyen , Long Nguyen , Dien Dinh

We present an ensemble-driven self-training framework for unsupervised neural machine translation (UNMT). Starting from a primary language pair, we train multiple UNMT models that share the same translation task but differ in an auxiliary…

Computation and Language · Computer Science 2026-03-19 Ido Aharon , Jonathan Shaki , Sarit Kraus

While neural machine translation (NMT) is making good progress in the past two years, tens of millions of bilingual sentence pairs are needed for its training. However, human labeling is very costly. To tackle this training data bottleneck,…

Computation and Language · Computer Science 2016-11-02 Yingce Xia , Di He , Tao Qin , Liwei Wang , Nenghai Yu , Tie-Yan Liu , Wei-Ying Ma

Sequence-to-sequence (S2S) pre-training using large monolingual data is known to improve performance for various S2S NLP tasks in low-resource settings. However, large monolingual corpora might not always be available for the languages of…

Computation and Language · Computer Science 2020-01-24 Haiyue Song , Raj Dabre , Zhuoyuan Mao , Fei Cheng , Sadao Kurohashi , Eiichiro Sumita

In spite of the recent success of neural machine translation (NMT) in standard benchmarks, the lack of large parallel corpora poses a major practical problem for many language pairs. There have been several proposals to alleviate this issue…

Computation and Language · Computer Science 2018-02-27 Mikel Artetxe , Gorka Labaka , Eneko Agirre , Kyunghyun Cho

Continuously-growing data volumes lead to larger generic models. Specific use-cases are usually left out, since generic models tend to perform poorly in domain-specific cases. Our work addresses this gap with a method for selecting…

Computation and Language · Computer Science 2022-02-08 Javad Pourmostafa Roshan Sharami , Dimitar Shterionov , Pieter Spronck