English
Related papers

Related papers: Self-Vocabularizing Training for Neural Machine Tr…

200 papers

Pre-training has proven to be effective in unsupervised machine translation due to its ability to model deep context information in cross-lingual scenarios. However, the cross-lingual information obtained from shared BPE spaces is…

Computation and Language · Computer Science 2019-09-04 Shuo Ren , Yu Wu , Shujie Liu , Ming Zhou , Shuai Ma

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

Subword tokenization algorithms used by Large Language Models are significantly more efficient and can independently build the necessary vocabulary of words and subwords without human intervention. However, those subwords do not always…

Computation and Language · Computer Science 2024-10-04 Óscar García-Sierra , Ana Fernández-Pampillón Cesteros , Miguel Ortega-Martín

A neural machine translation (NMT) system is expensive to train, especially with high-resource settings. As the NMT architectures become deeper and wider, this issue gets worse and worse. In this paper, we aim to improve the efficiency of…

Computation and Language · Computer Science 2020-06-04 Xuebo Liu , Houtim Lai , Derek F. Wong , Lidia S. Chao

In this paper, we investigate the problem of training neural machine translation (NMT) systems with a dataset of more than 40 billion bilingual sentence pairs, which is larger than the largest dataset to date by orders of magnitude.…

Computation and Language · Computer Science 2019-10-08 Yuxian Meng , Xiangyuan Ren , Zijun Sun , Xiaoya Li , Arianna Yuan , Fei Wu , Jiwei Li

Subword regularization, used widely in NLP, improves model performance by reducing the dependency on exact tokenizations, augmenting the training corpus, and exposing the model to more unique contexts during training. BPE and MaxMatch, two…

Computation and Language · Computer Science 2024-08-22 Marco Cognetta , Vilém Zouhar , Naoaki Okazaki

Recent research in decoding methods for Natural Language Generation (NLG) tasks has shown that MAP decoding is not optimal, because model probabilities do not always align with human preferences. Stronger decoding methods, including Quality…

Computation and Language · Computer Science 2024-03-27 Mara Finkelstein , Subhajit Naskar , Mehdi Mirzazadeh , Apurva Shah , Markus Freitag

Linguistic resources such as part-of-speech (POS) tags have been extensively used in statistical machine translation (SMT) frameworks and have yielded better performances. However, usage of such linguistic annotations in neural machine…

Computation and Language · Computer Science 2017-08-04 Jan Niehues , Eunah Cho

Using a vocabulary that is shared across languages is common practice in Multilingual Neural Machine Translation (MNMT). In addition to its simple design, shared tokens play an important role in positive knowledge transfer, assuming that…

Computation and Language · Computer Science 2024-01-23 Di Wu , Christof Monz

Machine translation is a popular test bed for research in neural sequence-to-sequence models but despite much recent research, there is still a lack of understanding of these models. Practitioners report performance degradation with large…

Computation and Language · Computer Science 2018-08-14 Myle Ott , Michael Auli , David Grangier , Marc'Aurelio Ranzato

We participated in the WMT 2016 shared news translation task by building neural translation systems for four language pairs, each trained in both directions: English<->Czech, English<->German, English<->Romanian and English<->Russian. Our…

Computation and Language · Computer Science 2016-06-29 Rico Sennrich , Barry Haddow , Alexandra Birch

In spite of their superior performance, neural probabilistic language models (NPLMs) remain far less widely used than n-gram models due to their notoriously long training times, which are measured in weeks even for moderately-sized…

Computation and Language · Computer Science 2016-06-07 Andriy Mnih , Yee Whye Teh

When training multilingual machine translation (MT) models that can translate to/from multiple languages, we are faced with imbalanced training sets: some languages have much more training data than others. Standard practice is to up-sample…

Computation and Language · Computer Science 2020-09-08 Xinyi Wang , Yulia Tsvetkov , Graham Neubig

Large language models frequently exhibit suboptimal performance on low resource languages, primarily due to inefficient subword segmentation and systemic training data imbalances. In this paper, we propose Variable Entropy Policy…

Computation and Language · Computer Science 2026-03-20 Chonghan Liu , Yimin Du , Qi An , Xin He , Cunqi Zhai , Fei Tan , Weijia Lin , Xiaochun Gong , Yongchao Deng , Shousheng Jia , Xiangzheng Zhang

Machine translation models have discrete vocabularies and commonly use subword segmentation techniques to achieve an 'open vocabulary.' This approach relies on consistent and correct underlying unicode sequences, and makes models…

Computation and Language · Computer Science 2021-12-13 Elizabeth Salesky , David Etter , Matt Post

Lexically constrained decoding for machine translation has shown to be beneficial in previous studies. Unfortunately, constraints provided by users may contain mistakes in real-world situations. It is still an open question that how to…

Computation and Language · Computer Science 2021-01-27 Huayang Li , Guoping Huang , Deng Cai , Lemao Liu

Neural Machine Translation (NMT) systems are known to degrade when confronted with noisy data, especially when the system is trained only on clean data. In this paper, we show that augmenting training data with sentences containing…

Computation and Language · Computer Science 2019-03-13 Antonios Anastasopoulos , Alison Lui , Toan Nguyen , David Chiang

Neural encoder-decoder models of machine translation have achieved impressive results, while learning linguistic knowledge of both the source and target languages in an implicit end-to-end manner. We propose a framework in which our model…

Computation and Language · Computer Science 2018-04-26 Eliyahu Kiperwasser , Miguel Ballesteros

It has been shown that machine translation models usually generate poor translations for named entities that are infrequent in the training corpus. Earlier named entity translation methods mainly focus on phonetic transliteration, which…

Computation and Language · Computer Science 2021-11-16 Junjie Hu , Hiroaki Hayashi , Kyunghyun Cho , Graham Neubig

Both research and commercial machine translation have so far neglected the importance of properly handling the spelling, lexical and grammar divergences occurring among language varieties. Notable cases are standard national varieties such…

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