中文
相关论文

相关论文: Towards a Better Understanding of Variations in Ze…

200 篇论文

Massively multilingual models for neural machine translation (NMT) are theoretically attractive, but often underperform bilingual models and deliver poor zero-shot translations. In this paper, we explore ways to improve them. We argue that…

计算与语言 · 计算机科学 2020-04-27 Biao Zhang , Philip Williams , Ivan Titov , Rico Sennrich

Multilingual Neural Machine Translation (NMT) models are capable of translating between multiple source and target languages. Despite various approaches to train such models, they have difficulty with zero-shot translation: translating…

计算与语言 · 计算机科学 2019-03-19 Naveen Arivazhagan , Ankur Bapna , Orhan Firat , Roee Aharoni , Melvin Johnson , Wolfgang Macherey

Multilingual Neural Machine Translation (MNMT) has aroused widespread interest due to its efficiency. An exciting advantage of MNMT models is that they could also translate between unsupervised (zero-shot) language directions. Language tag…

计算与语言 · 计算机科学 2021-06-16 Liwei Wu , Shanbo Cheng , Mingxuan Wang , Lei Li

Zero-shot translation is a promising direction for building a comprehensive multilingual neural machine translation~(MNMT) system. However, its quality is still not satisfactory due to off-target issues. In this paper, we aim to understand…

计算与语言 · 计算机科学 2024-10-22 Wenxuan Wang , Wenxiang Jiao , Shuo Wang , Zhaopeng Tu , Michael R. Lyu

In recent years, Neural Machine Translation (NMT) has been shown to be more effective than phrase-based statistical methods, thus quickly becoming the state of the art in machine translation (MT). However, NMT systems are limited in…

计算与语言 · 计算机科学 2019-09-17 Surafel M. Lakew , Marcello Federico , Matteo Negri , Marco Turchi

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

Recently, neural machine translation (NMT) has been extended to multilinguality, that is to handle more than one translation direction with a single system. Multilingual NMT showed competitive performance against pure bilingual systems.…

计算与语言 · 计算机科学 2018-06-22 Surafel M. Lakew , Mauro Cettolo , Marcello Federico

Zero-shot neural machine translation is an attractive goal because of the high cost of obtaining data and building translation systems for new translation directions. However, previous papers have reported mixed success in zero-shot…

计算与语言 · 计算机科学 2020-11-04 Annette Rios , Mathias Müller , Rico Sennrich

Multilingual Neural Machine Translation (NMT) enables one model to serve all translation directions, including ones that are unseen during training, i.e. zero-shot translation. Despite being theoretically attractive, current models often…

计算与语言 · 计算机科学 2022-01-20 Yilin Yang , Akiko Eriguchi , Alexandre Muzio , Prasad Tadepalli , Stefan Lee , Hany Hassan

Multilingual neural machine translation (NMT) has recently been investigated from different aspects (e.g., pivot translation, zero-shot translation, fine-tuning, or training from scratch) and in different settings (e.g., rich resource and…

计算与语言 · 计算机科学 2019-12-30 Xu Tan , Yichong Leng , Jiale Chen , Yi Ren , Tao Qin , Tie-Yan Liu

Generalization and reliability of multilingual translation often highly depend on the amount of available parallel data for each language pair of interest. In this paper, we focus on zero-shot generalization---a challenging setup that tests…

机器学习 · 计算机科学 2019-04-11 Maruan Al-Shedivat , Ankur P. Parikh

The language-independency of encoded representations within multilingual neural machine translation (MNMT) models is crucial for their generalization ability on zero-shot translation. Neural interlingua representations have been shown as an…

计算与语言 · 计算机科学 2023-05-18 Zhuoyuan Mao , Haiyue Song , Raj Dabre , Chenhui Chu , Sadao Kurohashi

Zero-shot translation, directly translating between language pairs unseen in training, is a promising capability of multilingual neural machine translation (NMT). However, it usually suffers from capturing spurious correlations between the…

计算与语言 · 计算机科学 2021-09-13 Weizhi Wang , Zhirui Zhang , Yichao Du , Boxing Chen , Jun Xie , Weihua Luo

While multilingual neural machine translation has achieved great success, it suffers from the off-target issue, where the translation is in the wrong language. This problem is more pronounced on zero-shot translation tasks. In this work, we…

计算与语言 · 计算机科学 2023-06-05 Liang Chen , Shuming Ma , Dongdong Zhang , Furu Wei , Baobao Chang

Understanding representation transfer in multilingual neural machine translation (MNMT) can reveal the reason for the zero-shot translation deficiency. In this work, we systematically analyze the representational issue of MNMT models. We…

计算与语言 · 计算机科学 2025-04-09 Zhi Qu , Chenchen Ding , Taro Watanabe

Neural Machine Translation (NMT) systems rely on large amounts of parallel data. This is a major challenge for low-resource languages. Building on recent work on unsupervised and semi-supervised methods, we present an approach that combines…

计算与语言 · 计算机科学 2018-05-29 Lierni Sestorain , Massimiliano Ciaramita , Christian Buck , Thomas Hofmann

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

The multilingual neural machine translation (NMT) model has a promising capability of zero-shot translation, where it could directly translate between language pairs unseen during training. For good transfer performance from supervised…

计算与语言 · 计算机科学 2023-05-15 Pengzhi Gao , Liwen Zhang , Zhongjun He , Hua Wu , Haifeng Wang

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

Transferring representations from large supervised tasks to downstream tasks has shown promising results in AI fields such as Computer Vision and Natural Language Processing (NLP). In parallel, the recent progress in Machine Translation…

计算与语言 · 计算机科学 2018-09-14 Akiko Eriguchi , Melvin Johnson , Orhan Firat , Hideto Kazawa , Wolfgang Macherey
‹ 上一页 1 2 3 10 下一页 ›