中文
相关论文

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

200 篇论文

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,…

计算与语言 · 计算机科学 2022-07-21 Jian Yang , Yuwei Yin , Shuming Ma , Dongdong Zhang , Zhoujun Li , Furu Wei

Although the parallel corpus has an irreplaceable role in machine translation, its scale and coverage is still beyond the actual needs. Non-parallel corpus resources on the web have an inestimable potential value in machine translation and…

计算与语言 · 计算机科学 2014-05-23 Lijiang Chen

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

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…

计算与语言 · 计算机科学 2018-06-15 Shuoyang Ding , Kevin Duh

Triangular machine translation is a special case of low-resource machine translation where the language pair of interest has limited parallel data, but both languages have abundant parallel data with a pivot language. Naturally, the key to…

计算与语言 · 计算机科学 2022-03-18 Meng Zhang , Liangyou Li , Qun Liu

In this paper, we present our first attempts in building a multilingual Neural Machine Translation framework under a unified approach. We are then able to employ attention-based NMT for many-to-many multilingual translation tasks. Our…

计算与语言 · 计算机科学 2016-11-16 Thanh-Le Ha , Jan Niehues , Alexander Waibel

Transfer learning for extremely low resource languages is a challenging task as there is no large scale monolingual corpora for pre training or sufficient annotated data for fine tuning. We follow the work of MetaXL which suggests using…

计算与语言 · 计算机科学 2023-06-02 Liat Bezalel , Eyal Orgad

Unsupervised translation has reached impressive performance on resource-rich language pairs such as English-French and English-German. However, early studies have shown that in more realistic settings involving low-resource, rare languages,…

计算与语言 · 计算机科学 2021-03-15 Xavier Garcia , Aditya Siddhant , Orhan Firat , Ankur P. Parikh

Most pre-trained Vision-Language (VL) models and training data for the downstream tasks are only available in English. Therefore, multilingual VL tasks are solved using cross-lingual transfer: fine-tune a multilingual pre-trained model or…

计算与语言 · 计算机科学 2025-08-18 Andrei-Alexandru Manea , Jindřich Libovický

In this thesis, we address the data scarcity and limitations of linguistic theory by proposing language-agnostic multi-task training methods. First, we introduce a meta-learning-based approach, meta-transfer learning, in which information…

计算与语言 · 计算机科学 2021-04-14 Genta Indra Winata

The integration of language models for neural machine translation has been extensively studied in the past. It has been shown that an external language model, trained on additional target-side monolingual data, can help improve translation…

计算与语言 · 计算机科学 2023-06-09 Christian Herold , Yingbo Gao , Mohammad Zeineldeen , Hermann Ney

An effective method to generate a large number of parallel sentences for training improved neural machine translation (NMT) systems is the use of the back-translations of the target-side monolingual data. The standard back-translation…

计算与语言 · 计算机科学 2021-11-04 Idris Abdulmumin , Bashir Shehu Galadanci , Aliyu Garba

Machine translation (MT) plays an important role in benefiting linguists, sociologists, computer scientists, etc. by processing natural language to translate it into some other natural language. And this demand has grown exponentially over…

计算与语言 · 计算机科学 2019-01-07 Ankush Garg , Mayank Agarwal

Neural machine translation (NMT) has recently gained widespread attention because of its high translation accuracy. However, it shows poor performance in the translation of long sentences, which is a major issue in low-resource languages.…

计算与语言 · 计算机科学 2021-04-20 Seiichiro Kondo , Kengo Hotate , Masahiro Kaneko , Mamoru Komachi

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

This paper examines the problem of adapting neural machine translation systems to new, low-resourced languages (LRLs) as effectively and rapidly as possible. We propose methods based on starting with massively multilingual "seed models",…

计算与语言 · 计算机科学 2018-08-14 Graham Neubig , Junjie Hu

This work focuses on comparing different solutions for machine translation on low resource language pairs, namely, with zero-shot transfer learning and unsupervised machine translation. We discuss how the data size affects the performance…

计算与语言 · 计算机科学 2021-04-02 Aviral Joshi , Chengzhi Huang , Har Simrat Singh

The encoder-decoder framework for neural machine translation (NMT) has been shown effective in large data scenarios, but is much less effective for low-resource languages. We present a transfer learning method that significantly improves…

计算与语言 · 计算机科学 2016-04-11 Barret Zoph , Deniz Yuret , Jonathan May , Kevin Knight

Multilingual machine translation (MMT), trained on a mixture of parallel and monolingual data, is key for improving translation in low-resource language pairs. However, the literature offers conflicting results on the performance of…

计算与语言 · 计算机科学 2024-04-02 Christos Baziotis , Biao Zhang , Alexandra Birch , Barry Haddow

Building Machine Translation (MT) systems for low-resource languages remains challenging. For many language pairs, parallel data are not widely available, and in such cases MT models do not achieve results comparable to those seen with…

计算与语言 · 计算机科学 2020-12-01 Alberto Poncelas , Jan Buts , James Hadley , Andy Way