中文
相关论文

相关论文: A Survey of Methods to Leverage Monolingual Data i…

200 篇论文

In neural machine translation (NMT), monolingual data in the target language are usually exploited through a method so-called "back-translation" to synthesize additional training parallel data. The synthetic data have been shown helpful to…

计算与语言 · 计算机科学 2021-02-01 Benjamin Marie , Atsushi Fujita

We present a simple method to improve neural translation of a low-resource language pair using parallel data from a related, also low-resource, language pair. The method is based on the transfer method of Zoph et al., but whereas their…

计算与语言 · 计算机科学 2017-09-22 Toan Q. Nguyen , David Chiang

Neural machine translation (NMT) approaches have improved the state of the art in many machine translation settings over the last couple of years, but they require large amounts of training data to produce sensible output. We demonstrate…

计算与语言 · 计算机科学 2017-08-22 Robert Östling , Jörg Tiedemann

The quality of a Neural Machine Translation system depends substantially on the availability of sizable parallel corpora. For low-resource language pairs this is not the case, resulting in poor translation quality. Inspired by work in…

计算与语言 · 计算机科学 2018-02-14 Marzieh Fadaee , Arianna Bisazza , Christof Monz

While end-to-end neural machine translation (NMT) has made remarkable progress recently, NMT systems only rely on parallel corpora for parameter estimation. Since parallel corpora are usually limited in quantity, quality, and coverage,…

计算与语言 · 计算机科学 2016-12-13 Yong Cheng , Wei Xu , Zhongjun He , Wei He , Hua Wu , Maosong Sun , Yang Liu

Neural models have drastically advanced state of the art for machine translation (MT) between high-resource languages. Traditionally, these models rely on large amounts of training data, but many language pairs lack these resources.…

计算与语言 · 计算机科学 2023-06-13 Manuel Mager , Rajat Bhatnagar , Graham Neubig , Ngoc Thang Vu , Katharina Kann

Neural Machine Translation (NMT) has obtained state-of-the art performance for several language pairs, while only using parallel data for training. Target-side monolingual data plays an important role in boosting fluency for phrase-based…

计算与语言 · 计算机科学 2016-06-06 Rico Sennrich , Barry Haddow , Alexandra Birch

We explore ways of incorporating bilingual dictionaries to enable semi-supervised neural machine translation. Conventional back-translation methods have shown success in leveraging target side monolingual data. However, since the quality of…

计算与语言 · 计算机科学 2020-04-07 Sreyashi Nag , Mihir Kale , Varun Lakshminarasimhan , Swapnil Singhavi

This paper studies the practicality of the current state-of-the-art unsupervised methods in neural machine translation (NMT). In ten translation tasks with various data settings, we analyze the conditions under which the unsupervised…

计算与语言 · 计算机科学 2020-04-23 Yunsu Kim , Miguel Graça , Hermann Ney

Despite impressive empirical successes of neural machine translation (NMT) on standard benchmarks, limited parallel data impedes the application of NMT models to many language pairs. Data augmentation methods such as back-translation make…

计算与语言 · 计算机科学 2019-10-08 Chunting Zhou , Xuezhe Ma , Junjie Hu , Graham Neubig

While prior work has established that the use of parallel data is conducive for cross-lingual learning, it is unclear if the improvements come from the data itself, or if it is the modeling of parallel interactions that matters. Exploring…

计算与语言 · 计算机科学 2022-12-21 Machel Reid , Mikel Artetxe

While monolingual data has been shown to be useful in improving bilingual neural machine translation (NMT), effectively and efficiently leveraging monolingual data for Multilingual NMT (MNMT) systems is a less explored area. In this work,…

计算与语言 · 计算机科学 2020-10-07 Yiren Wang , ChengXiang Zhai , Hany Hassan Awadalla

Even with the latest developments in deep learning and large-scale language modeling, the task of machine translation (MT) of low-resource languages remains a challenge. Neural MT systems can be trained in an unsupervised way without any…

计算与语言 · 计算机科学 2023-10-24 Ivana Kvapilíková , Ondřej Bojar

This paper proposes a novel multilingual multistage fine-tuning approach for low-resource neural machine translation (NMT), taking a challenging Japanese--Russian pair for benchmarking. Although there are many solutions for low-resource…

计算与语言 · 计算机科学 2019-07-09 Aizhan Imankulova , Raj Dabre , Atsushi Fujita , Kenji Imamura

Neural machine translation requires large amounts of parallel training text to learn a reasonable-quality translation model. This is particularly inconvenient for language pairs for which enough parallel text is not available. In this…

计算与语言 · 计算机科学 2018-05-14 Poorya Zaremoodi , Gholamreza Haffari

Multilingual machine translation addresses the task of translating between multiple source and target languages. We propose task-specific attention models, a simple but effective technique for improving the quality of sequence-to-sequence…

计算与语言 · 计算机科学 2018-06-11 Graeme Blackwood , Miguel Ballesteros , Todd Ward

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…

计算与语言 · 计算机科学 2021-07-13 Thi-Vinh Ngo , Phuong-Thai Nguyen , Thanh-Le Ha , Khac-Quy Dinh , Le-Minh Nguyen

Achieving universal translation between all human language pairs is the holy-grail of machine translation (MT) research. While recent progress in massively multilingual MT is one step closer to reaching this goal, it is becoming evident…

计算与语言 · 计算机科学 2022-01-14 Aditya Siddhant , Ankur Bapna , Orhan Firat , Yuan Cao , Mia Xu Chen , Isaac Caswell , Xavier Garcia

Machine translation systems achieve near human-level performance on some languages, yet their effectiveness strongly relies on the availability of large amounts of parallel sentences, which hinders their applicability to the majority of…

计算与语言 · 计算机科学 2018-08-15 Guillaume Lample , Myle Ott , Alexis Conneau , Ludovic Denoyer , Marc'Aurelio Ranzato

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-translation method. This…

计算与语言 · 计算机科学 2021-05-28 Maali Tars , Andre Tättar , Mark Fišel