scholarly journals Keeping Models Consistent between Pretraining and Translation for Low-Resource Neural Machine Translation

2020 ◽  
Vol 12 (12) ◽  
pp. 215
Author(s):  
Wenbo Zhang ◽  
Xiao Li ◽  
Yating Yang ◽  
Rui Dong ◽  
Gongxu Luo
Keyword(s):  
Machine Translation ◽  
Language Model ◽  
Neural Machine Translation ◽  
Translation Model ◽  
Parallel Corpus ◽  
Model Experiments ◽  
Low Resource ◽  
Translation Quality ◽  
Number Of Layers ◽  
Cross Lingual

Recently, the pretraining of models has been successfully applied to unsupervised and semi-supervised neural machine translation. A cross-lingual language model uses a pretrained masked language model to initialize the encoder and decoder of the translation model, which greatly improves the translation quality. However, because of a mismatch in the number of layers, the pretrained model can only initialize part of the decoder’s parameters. In this paper, we use a layer-wise coordination transformer and a consistent pretraining translation transformer instead of a vanilla transformer as the translation model. The former has only an encoder, and the latter has an encoder and a decoder, but the encoder and decoder have exactly the same parameters. Both models can guarantee that all parameters in the translation model can be initialized by the pretrained model. Experiments on the Chinese–English and English–German datasets show that compared with the vanilla transformer baseline, our models achieve better performance with fewer parameters when the parallel corpus is small.

Analyzing Subword Techniques to Improve English to Sinhala Neural Machine Translation

2021 ◽  
pp. 2050017
Author(s):  
Rashmini Naranpanawa ◽  
Ravinga Perera ◽  
Thilakshi Fonseka ◽  
Uthayasanker Thayasivam
Keyword(s):  
Machine Translation ◽  
State Of The Art ◽  
Statistical Machine Translation ◽  
Translation System ◽  
Rare Word ◽  
Neural Machine Translation ◽  
Parallel Corpus ◽  
Low Resource ◽  
Word Level ◽  
Morphologically Rich Languages

Neural machine translation (NMT) is a remarkable approach which performs much better than the Statistical machine translation (SMT) models when there is an abundance of parallel corpus. However, vanilla NMT is primarily based upon word-level with a fixed vocabulary. Therefore, low resource morphologically rich languages such as Sinhala are mostly affected by the out of vocabulary (OOV) and Rare word problems. Recent advancements in subword techniques have opened up opportunities for low resource communities by enabling open vocabulary translation. In this paper, we extend our recently published state-of-the-art EN-SI translation system using the transformer and explore standard subword techniques on top of it to identify which subword approach has a greater effect on English Sinhala language pair. Our models demonstrate that subword segmentation strategies along with the state-of-the-art NMT can perform remarkably when translating English sentences into a rich morphology language regardless of a large parallel corpus.

Improving thai-lao neural machine translation with similarity lexicon

2021 ◽  
pp. 1-10
Author(s):  
Zhiqiang Yu ◽  
Yuxin Huang ◽  
Junjun Guo
Keyword(s):  
Machine Translation ◽  
Semantic Information ◽  
Neural Machine Translation ◽  
Low Resource ◽  
Translation Quality ◽  
Decoder Architecture ◽  
Baseline System ◽  
Input Sentence ◽  
Resource Conditions ◽  
Language Pair

It has been shown that the performance of neural machine translation (NMT) drops starkly in low-resource conditions. Thai-Lao is a typical low-resource language pair of tiny parallel corpus, leading to suboptimal NMT performance on it. However, Thai and Lao have considerable similarities in linguistic morphology and have bilingual lexicon which is relatively easy to obtain. To use this feature, we first build a bilingual similarity lexicon composed of pairs of similar words. Then we propose a novel NMT architecture to leverage the similarity between Thai and Lao. Specifically, besides the prevailing sentence encoder, we introduce an extra similarity lexicon encoder into the conventional encoder-decoder architecture, by which the semantic information carried by the similarity lexicon can be represented. We further provide a simple mechanism in the decoder to balance the information representations delivered from the input sentence and the similarity lexicon. Our approach can fully exploit linguistic similarity carried by the similarity lexicon to improve translation quality. Experimental results demonstrate that our approach achieves significant improvements over the state-of-the-art Transformer baseline system and previous similar works.

scholarly journals Augmenting Neural Machine Translation through Round-Trip Training Approach

2019 ◽  
Vol 9 (1) ◽  
pp. 268-278 ◽  
Author(s):  
Benyamin Ahmadnia ◽  
Bonnie J. Dorr
Keyword(s):  
Machine Translation ◽  
Training Data ◽  
Training Dataset ◽  
Round Trip ◽  
Neural Machine Translation ◽  
Low Resource ◽  
Translation Quality ◽  
High Resource ◽  
Training Approach ◽  
Language Pair

AbstractThe quality of Neural Machine Translation (NMT), as a data-driven approach, massively depends on quantity, quality and relevance of the training dataset. Such approaches have achieved promising results for bilingually high-resource scenarios but are inadequate for low-resource conditions. Generally, the NMT systems learn from millions of words from bilingual training dataset. However, human labeling process is very costly and time consuming. In this paper, we describe a round-trip training approach to bilingual low-resource NMT that takes advantage of monolingual datasets to address training data bottleneck, thus augmenting translation quality. We conduct detailed experiments on English-Spanish as a high-resource language pair as well as Persian-Spanish as a low-resource language pair. Experimental results show that this competitive approach outperforms the baseline systems and improves translation quality.

Neural machine translation of low-resource languages using SMT phrase pair injection

2020 ◽  
pp. 1-22
Author(s):  
Sukanta Sen ◽  
Mohammed Hasanuzzaman ◽  
Asif Ekbal ◽  
Pushpak Bhattacharyya ◽  
Andy Way
Keyword(s):  
Machine Translation ◽  
Large Scale ◽  
Production Systems ◽  
Statistical Machine Translation ◽  
Training Data ◽  
Original Training ◽  
Neural Machine Translation ◽  
Parallel Corpus ◽  
Low Resource ◽  
Better Than

Abstract Neural machine translation (NMT) has recently shown promising results on publicly available benchmark datasets and is being rapidly adopted in various production systems. However, it requires high-quality large-scale parallel corpus, and it is not always possible to have sufficiently large corpus as it requires time, money, and professionals. Hence, many existing large-scale parallel corpus are limited to the specific languages and domains. In this paper, we propose an effective approach to improve an NMT system in low-resource scenario without using any additional data. Our approach aims at augmenting the original training data by means of parallel phrases extracted from the original training data itself using a statistical machine translation (SMT) system. Our proposed approach is based on the gated recurrent unit (GRU) and transformer networks. We choose the Hindi–English, Hindi–Bengali datasets for Health, Tourism, and Judicial (only for Hindi–English) domains. We train our NMT models for 10 translation directions, each using only 5–23k parallel sentences. Experiments show the improvements in the range of 1.38–15.36 BiLingual Evaluation Understudy points over the baseline systems. Experiments show that transformer models perform better than GRU models in low-resource scenarios. In addition to that, we also find that our proposed method outperforms SMT—which is known to work better than the neural models in low-resource scenarios—for some translation directions. In order to further show the effectiveness of our proposed model, we also employ our approach to another interesting NMT task, for example, old-to-modern English translation, using a tiny parallel corpus of only 2.7K sentences. For this task, we use publicly available old-modern English text which is approximately 1000 years old. Evaluation for this task shows significant improvement over the baseline NMT.

Automatic translation of spoken English based on improved machine learning algorithm

2020 ◽  
pp. 1-11
Author(s):  
Lin Lin ◽  
Jie Liu ◽  
Xuebing Zhang ◽  
Xiufang Liang
Keyword(s):  
Machine Translation ◽  
Learning Algorithm ◽  
English Word ◽  
Neural Machine Translation ◽  
Parallel Corpus ◽  
Low Resource ◽  
Spoken English ◽  
Automatic Translation ◽  
Study Designs ◽  
Chinese And English

Due to the complexity of English machine translation technology and its broad application prospects, many experts and scholars have invested more energy to analyze it. In view of the complex and changeable English forms, the large difference between Chinese and English word order, and insufficient Chinese-English parallel corpus resources, this paper uses deep learning to complete the conversion between Chinese and English. The research focus of this paper is how to use language pairs with rich parallel corpus resources to improve the performance of Chinese-English neural machine translation, that is, to use multi-task learning to train neural machine translation models. Moreover, this research proposes a low-resource neural machine translation method based on weight sharing, which uses the weight-sharing method to improve the performance of Chinese-English low-resource neural machine translation. In addition, this study designs a control experiment to analyze the effectiveness of this study model. The research results show that the model proposed in this paper has a certain effect.

Low Resource Neural Machine Translation: Assamese to/from Other Indo-Aryan (Indic) Languages

2022 ◽  
Vol 21 (1) ◽  
pp. 1-32
Author(s):  
Rupjyoti Baruah ◽  
Rajesh Kumar Mundotiya ◽  
Anil Kumar Singh
Keyword(s):  
Machine Translation ◽  
Statistical Machine Translation ◽  
Basic Sequence ◽  
Neural Machine Translation ◽  
Parallel Corpus ◽  
Translation Quality ◽  
Evaluation Scores ◽  
Language Characteristics ◽  
The Given ◽  
Family Trees

Machine translation (MT) systems have been built using numerous different techniques for bridging the language barriers. These techniques are broadly categorized into approaches like Statistical Machine Translation (SMT) and Neural Machine Translation (NMT). End-to-end NMT systems significantly outperform SMT in translation quality on many language pairs, especially those with the adequate parallel corpus. We report comparative experiments on baseline MT systems for Assamese to other Indo-Aryan languages (in both translation directions) using the traditional Phrase-Based SMT as well as some more successful NMT architectures, namely basic sequence-to-sequence model with attention, Transformer, and finetuned Transformer. The results are evaluated using the most prominent and popular standard automatic metric BLEU (BiLingual Evaluation Understudy), as well as other well-known metrics for exploring the performance of different baseline MT systems, since this is the first such work involving Assamese. The evaluation scores are compared for SMT and NMT models for the effectiveness of bi-directional language pairs involving Assamese and other Indo-Aryan languages (Bangla, Gujarati, Hindi, Marathi, Odia, Sinhalese, and Urdu). The highest BLEU scores obtained are for Assamese to Sinhalese for SMT (35.63) and the Assamese to Bangla for NMT systems (seq2seq is 50.92, Transformer is 50.01, and finetuned Transformer is 50.19). We also try to relate the results with the language characteristics, distances, family trees, domains, data sizes, and sentence lengths. We find that the effect of the domain is the most important factor affecting the results for the given data domains and sizes. We compare our results with the only existing MT system for Assamese (Bing Translator) and also with pairs involving Hindi.

scholarly journals Synthesizing Parallel Data of User-Generated Texts with Zero-Shot Neural Machine Translation

2020 ◽  
Vol 8 ◽  
pp. 710-725
Author(s):  
Benjamin Marie ◽  
Atsushi Fujita
Keyword(s):  
Social Media ◽  
Machine Translation ◽  
Language Model ◽  
The Other ◽  
Neural Machine Translation ◽  
Translation Quality ◽  
Online Social Media ◽  
Parallel Data

Neural machine translation (NMT) systems are usually trained on clean parallel data. They can perform very well for translating clean in-domain texts. However, as demonstrated by previous work, the translation quality significantly worsens when translating noisy texts, such as user-generated texts (UGT) from online social media. Given the lack of parallel data of UGT that can be used to train or adapt NMT systems, we synthesize parallel data of UGT, exploiting monolingual data of UGT through crosslingual language model pre-training and zero-shot NMT systems. This paper presents two different but complementary approaches: One alters given clean parallel data into UGT-like parallel data whereas the other generates translations from monolingual data of UGT. On the MTNT translation tasks, we show that our synthesized parallel data can lead to better NMT systems for UGT while making them more robust in translating texts from various domains and styles.

scholarly journals Translation Mechanism of Neural Machine Algorithm for Online English Resources

Complexity ◽  
2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Yanping Ye
Keyword(s):  
Data Processing ◽  
Machine Translation ◽  
Statistical Machine Translation ◽  
Language Model ◽  
Processing Methods ◽  
Neural Machine Translation ◽  
Translation Model ◽  
Sentence Similarity ◽  
Alignment Structure ◽  
Data Processing Methods

At the level of English resource vocabulary, due to the lack of vocabulary alignment structure, the translation of neural machine translation has the problem of unfaithfulness. This paper proposes a framework that integrates vocabulary alignment structure for neural machine translation at the vocabulary level. Under the proposed framework, the neural machine translation decoder receives external vocabulary alignment information during each step of the decoding process to further alleviate the problem of missing vocabulary alignment structure. Specifically, this article uses the word alignment structure of statistical machine translation as the external vocabulary alignment information and introduces it into the decoding step of neural machine translation. The model is mainly based on neural machine translation, and the statistical machine translation vocabulary alignment structure is integrated on the basis of neural networks and continuous expression of words. In the model decoding stage, the statistical machine translation system provides appropriate vocabulary alignment information based on the decoding information of the neural machine translation and recommends vocabulary based on the vocabulary alignment information to guide the neural machine translation decoder to more accurately estimate its vocabulary in the target language. From the aspects of data processing methods and machine translation technology, experiments are carried out to compare the data processing methods based on language model and sentence similarity and the effectiveness of machine translation models based on fusion principles. Comparative experiment results show that the data processing method based on language model and sentence similarity effectively guarantees data quality and indirectly improves the algorithm performance of machine translation model; the translation effect of neural machine translation model integrated with statistical machine translation vocabulary alignment structure is compared with other models.

scholarly journals Maximum Expected Likelihood Estimation for Zero-resource Neural Machine Translation

2017 ◽  
Author(s):  
Hao Zheng ◽  
Yong Cheng ◽  
Yang Liu
Keyword(s):  
Machine Translation ◽  
Likelihood Estimation ◽  
Neural Machine Translation ◽  
Parallel Corpora ◽  
Translation Model ◽  
Parallel Corpus ◽  
Target Model ◽  
High Resource ◽  
Remarkable Progress

While neural machine translation (NMT) has made remarkable progress in translating a handful of high-resource language pairs recently, parallel corpora are not always available for many zero-resource language pairs. To deal with this problem, we propose an approach to zero-resource NMT via maximum expected likelihood estimation. The basic idea is to maximize the expectation with respect to a pivot-to-source translation model for the intended source-to-target model on a pivot-target parallel corpus. To approximate the expectation, we propose two methods to connect the pivot-to-source and source-to-target models. Experiments on two zero-resource language pairs show that the proposed approach yields substantial gains over baseline methods. We also observe that when trained jointly with the source-to-target model, the pivot-to-source translation model also obtains improvements over independent training.

scholarly journals Research on Uyghur-Chinese Neural Machine Translation Based on the Transformer at Multistrategy Segmentation Granularity

2021 ◽  
Vol 2021 ◽  
pp. 1-7
Author(s):  
Zhiwang Xu ◽  
Huibin Qin ◽  
Yongzhu Hua
Keyword(s):  
Neural Networks ◽  
Machine Translation ◽  
Semantic Features ◽  
Training Method ◽  
Chinese Translation ◽  
Neural Machine Translation ◽  
Translation Model ◽  
Parallel Corpus ◽  
Model Based ◽  
Translation Systems

In recent years, machine translation based on neural networks has become the mainstream method in the field of machine translation, but there are still challenges of insufficient parallel corpus and sparse data in the field of low resource translation. Existing machine translation models are usually trained on word-granularity segmentation datasets. However, different segmentation granularities contain different grammatical and semantic features and information. Only considering word granularity will restrict the efficient training of neural machine translation systems. Aiming at the problem of data sparseness caused by the lack of Uyghur-Chinese parallel corpus and complex Uyghur morphology, this paper proposes a multistrategy segmentation granular training method for syllables, marked syllable, words, and syllable word fusion and targets traditional recurrent neural networks and convolutional neural networks; the disadvantage of the network is to build a Transformer Uyghur-Chinese Neural Machine Translation model based entirely on the multihead self-attention mechanism. In CCMT2019, dimension results on Uyghur-Chinese bilingual datasets show that the effect of multiple translation granularity training method is significantly better than the rest of granularity segmentation translation systems, while the Transformer model can obtain higher BLEU value than Uyghur-Chinese translation model based on Self-Attention-RNN.

Sign in / Sign up

Export Citation Format

Share Document