中文
相关论文

相关论文: Adapting Multilingual Neural Machine Translation t…

200 篇论文

Machine Translation System (MTS) serves as an effective tool for communication by translating text or speech from one language to another language. The need of an efficient translation system becomes obvious in a large multilingual…

计算与语言 · 计算机科学 2024-03-18 Sudhansu Bala Das , Atharv Biradar , Tapas Kumar Mishra , Bidyut Kumar Patra

We conduct an empirical study of neural machine translation (NMT) for truly low-resource languages, and propose a training curriculum fit for cases when both parallel training data and compute resource are lacking, reflecting the reality of…

Multilingual NMT is a viable solution for translating low-resource languages (LRLs) when data from high-resource languages (HRLs) from the same language family is available. However, the training schedule, i.e. the order of presentation of…

计算与语言 · 计算机科学 2025-06-03 Alexis Allemann , Àlex R. Atrio , Andrei Popescu-Belis

Unsupervised cross-lingual pretraining has achieved strong results in neural machine translation (NMT), by drastically reducing the need for large parallel data. Most approaches adapt masked-language modeling (MLM) to sequence-to-sequence…

计算与语言 · 计算机科学 2021-06-11 Christos Baziotis , Ivan Titov , Alexandra Birch , Barry Haddow

Machine translation (MT) models used in industries with constantly changing topics, such as translation or news agencies, need to adapt to new data to maintain their performance over time. Our aim is to teach a pre-trained MT model to…

计算与语言 · 计算机科学 2021-04-01 Farid Arthaud , Rachel Bawden , Alexandra Birch

This paper considers the unsupervised domain adaptation problem for neural machine translation (NMT), where we assume the access to only monolingual text in either the source or target language in the new domain. We propose a cross-lingual…

计算与语言 · 计算机科学 2021-09-10 Thuy-Trang Vu , Xuanli He , Dinh Phung , Gholamreza Haffari

Recent studies have shown that reinforcement learning (RL) is an effective approach for improving the performance of neural machine translation (NMT) system. However, due to its instability, successfully RL training is challenging,…

机器学习 · 计算机科学 2018-08-28 Lijun Wu , Fei Tian , Tao Qin , Jianhuang Lai , Tie-Yan Liu

Consistency is a key requirement of high-quality translation. It is especially important to adhere to pre-approved terminology and adapt to corrected translations in domain-specific projects. Machine translation (MT) has achieved…

计算与语言 · 计算机科学 2023-05-10 Yasmin Moslem , Rejwanul Haque , John D. Kelleher , Andy Way

An important concern in training multilingual neural machine translation (NMT) is to translate between language pairs unseen during training, i.e zero-shot translation. Improving this ability kills two birds with one stone by providing an…

计算与语言 · 计算机科学 2019-06-21 Ngoc-Quan Pham , Jan Niehues , Thanh-Le Ha , Alex Waibel

Transfer learning or multilingual model is essential for low-resource neural machine translation (NMT), but the applicability is limited to cognate languages by sharing their vocabularies. This paper shows effective techniques to transfer a…

计算与语言 · 计算机科学 2019-06-06 Yunsu Kim , Yingbo Gao , Hermann Ney

Neural Machine Translation (NMT) approaches employing monolingual data are showing steady improvements in resource rich conditions. However, evaluations using real-world low-resource languages still result in unsatisfactory performance.…

计算与语言 · 计算机科学 2021-03-11 Surafel M. Lakew , Matteo Negri , Marco Turchi

Recent advents in Neural Machine Translation (NMT) have shown improvements in low-resource language (LRL) translation tasks. In this work, we benchmark NMT between English and five African LRL pairs (Swahili, Amharic, Tigrigna, Oromo,…

计算与语言 · 计算机科学 2020-04-01 Surafel M. Lakew , Matteo Negri , Marco Turchi

In the current machine translation (MT) landscape, the Transformer architecture stands out as the gold standard, especially for high-resource language pairs. This research delves into its efficacy for low-resource language pairs including…

计算与语言 · 计算机科学 2024-03-05 Séamus Lankford

Recent work on multilingual neural machine translation reported competitive performance with respect to bilingual models and surprisingly good performance even on (zeroshot) translation directions not observed at training time. We…

计算与语言 · 计算机科学 2018-11-06 Surafel M. Lakew , Quintino F. Lotito , Matteo Negri , Marco Turchi , Marcello Federico

In this paper, we propose to extend the recently introduced model-agnostic meta-learning algorithm (MAML) for low-resource neural machine translation (NMT). We frame low-resource translation as a meta-learning problem, and we learn to adapt…

计算与语言 · 计算机科学 2018-08-28 Jiatao Gu , Yong Wang , Yun Chen , Kyunghyun Cho , Victor O. K. Li

Multilingual Neural Machine Translation (MNMT) models leverage many language pairs during training to improve translation quality for low-resource languages by transferring knowledge from high-resource languages. We study the quality of a…

计算与语言 · 计算机科学 2022-12-06 Miguel Rios , Raluca-Maria Chereji , Alina Secara , Dragos Ciobanu

Multimodal machine translation is an attractive application of neural machine translation (NMT). It helps computers to deeply understand visual objects and their relations with natural languages. However, multimodal NMT systems suffer from…

计算与语言 · 计算机科学 2019-04-02 Tosho Hirasawa , Hayahide Yamagishi , Yukio Matsumura , Mamoru Komachi

It has been shown that the performance of neural machine translation (NMT) drops starkly in low-resource conditions, underperforming phrase-based statistical machine translation (PBSMT) and requiring large amounts of auxiliary data to…

计算与语言 · 计算机科学 2019-05-29 Rico Sennrich , Biao Zhang

Conventional retrieval-augmented neural machine translation (RANMT) systems leverage bilingual corpora, e.g., translation memories (TMs). Yet, in many settings, monolingual corpora in the target language are often available. This work…

计算与语言 · 计算机科学 2025-10-02 Maxime Bouthors , Josep Crego , François Yvon

We introduce negative space learning machine translation (NSL-MT), a training method for underresourced languages, that augments limited parallel data with synthetically generated violations of the target language's grammar and explicitly…

机器学习 · 计算机科学 2026-05-07 Mamadou K. Keita , Christopher Homan , Huy Le