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 Corpus Augmentation for Neural Machine Translation with Chinese-Japanese Parallel Corpora

2019 ◽  
Vol 9 (10) ◽  
pp. 2036
Author(s):  
Jinyi Zhang ◽  
Tadahiro Matsumoto
Keyword(s):  
Machine Translation ◽  
Scientific Paper ◽  
Training Data ◽  
Word Alignment ◽  
Sentence Pair ◽  
Neural Machine Translation ◽  
Parallel Corpora ◽  
Translation Quality ◽  
Parallel Data ◽  
Source Sentence

The translation quality of Neural Machine Translation (NMT) systems depends strongly on the training data size. Sufficient amounts of parallel data are, however, not available for many language pairs. This paper presents a corpus augmentation method, which has two variations: one is for all language pairs, and the other is for the Chinese-Japanese language pair. The method uses both source and target sentences of the existing parallel corpus and generates multiple pseudo-parallel sentence pairs from a long parallel sentence pair containing punctuation marks as follows: (1) split the sentence pair into parallel partial sentences; (2) back-translate the target partial sentences; and (3) replace each partial sentence in the source sentence with the back-translated target partial sentence to generate pseudo-source sentences. The word alignment information, which is used to determine the split points, is modified with “shared Chinese character rates” in segments of the sentence pairs. The experiment results of the Japanese-Chinese and Chinese-Japanese translation with ASPEC-JC (Asian Scientific Paper Excerpt Corpus, Japanese-Chinese) show that the method substantially improves translation performance. We also supply the code (see Supplementary Materials) that can reproduce our proposed method.

scholarly journals Neural machine translation system for the Kazakh language based on synthetic corpora

2019 ◽  
Vol 252 ◽  
pp. 03006
Author(s):  
Ualsher Tukeyev ◽  
Aidana Karibayeva ◽  
Balzhan Abduali
Keyword(s):  
Machine Translation ◽  
Training Data ◽  
Translation System ◽  
Natural Languages ◽  
Neural Machine Translation ◽  
Translation Quality ◽  
Parallel Data ◽  
Machine Translation System ◽  
Turkic Languages

The lack of big parallel data is present for the Kazakh language. This problem seriously impairs the quality of machine translation from and into Kazakh. This article considers the neural machine translation of the Kazakh language on the basis of synthetic corpora. The Kazakh language belongs to the Turkic languages, which are characterised by rich morphology. Neural machine translation of natural languages requires large training data. The article will show the model for the creation of synthetic corpora, namely the generation of sentences based on complete suffixes for the Kazakh language. The novelty of this approach of the synthetic corpora generation for the Kazakh language is the generation of sentences on the basis of the complete system of suffixes of the Kazakh language. By using generated synthetic corpora we are improving the translation quality in neural machine translation of Kazakh-English and Kazakh-Russian pairs.

scholarly journals Machine translation of English content: A comparative study of different methods

2021 ◽  
Vol 30 (1) ◽  
pp. 980-987
Author(s):  
Jinfeng Xue
Keyword(s):  
Comparative Study ◽  
Machine Translation ◽  
Experimental Results ◽  
The Other ◽  
Neural Machine Translation ◽  
Translation Quality ◽  
Operation Speed ◽  
Two Systems

Abstract Based on neural machine translation, this article introduced the ConvS2S system and transformer system, designed a semantic sharing combined transformer system to improve translation quality, and compared the three systems on the NIST dataset. The results showed that the operation speed of the semantic sharing combined transformer system was the highest, reaching 3934.27 words per second; the BLEU value of the ConvS2S system was the smallest, followed by the transformer system and the semantic sharing combined transformer system. Taking NIST08 as an example, the BLEU values of the designed system were 4.74 and 1.49 higher than the other two systems. The analysis of examples showed that the semantic sharing combined transformer had higher translation quality. The experimental results show that the proposed system is reliable in English content translation and can be further promoted and applied in practice.

Non-autoregressive neural machine translation with auxiliary representation fusion

2021 ◽  
pp. 1-11
Author(s):  
Quan Du ◽  
Kai Feng ◽  
Chen Xu ◽  
Tong Xiao ◽  
Jingbo Zhu
Keyword(s):  
Machine Translation ◽  
Experimental Results ◽  
The Other ◽  
Generation Process ◽  
Neural Machine Translation ◽  
Trade Off ◽  
Translation Quality ◽  
Other Hand ◽  
Entire Sequence ◽  
Translation Accuracy

Recently, many efforts have been devoted to speeding up neural machine translation models. Among them, the non-autoregressive translation (NAT) model is promising because it removes the sequential dependence on the previously generated tokens and parallelizes the generation process of the entire sequence. On the other hand, the autoregressive translation (AT) model in general achieves a higher translation accuracy than the NAT counterpart. Therefore, a natural idea is to fuse the AT and NAT models to seek a trade-off between inference speed and translation quality. This paper proposes an ARF-NAT model (NAT with auxiliary representation fusion) to introduce the merit of a shallow AT model to an NAT model. Three functions are designed to fuse the auxiliary representation into the decoder of the NAT model. Experimental results show that ARF-NAT outperforms the NAT baseline by 5.26 BLEU scores on the WMT’14 German-English task with a significant speedup (7.58 times) over several strong AT baselines.

scholarly journals “Bilingual Expert” Can Find Translation Errors

2019 ◽  
Vol 33 ◽  
pp. 6367-6374 ◽  
Author(s):  
Kai Fan ◽  
Jiayi Wang ◽  
Bo Li ◽  
Fengming Zhou ◽  
Boxing Chen ◽  
...  
Keyword(s):  
Machine Translation ◽  
Statistical Machine Translation ◽  
Language Model ◽  
Target Language ◽  
Quality Estimation ◽  
Parallel Corpora ◽  
Translation Quality ◽  
Expert Model ◽  
Parallel Data ◽  
Translation Errors

The performances of machine translation (MT) systems are usually evaluated by the metric BLEU when the golden references are provided. However, in the case of model inference or production deployment, golden references are usually expensively available, such as human annotation with bilingual expertise. In order to address the issue of translation quality estimation (QE) without reference, we propose a general framework for automatic evaluation of the translation output for the QE task in the Conference on Statistical Machine Translation (WMT). We first build a conditional target language model with a novel bidirectional transformer, named neural bilingual expert model, which is pre-trained on large parallel corpora for feature extraction. For QE inference, the bilingual expert model can simultaneously produce the joint latent representation between the source and the translation, and real-valued measurements of possible erroneous tokens based on the prior knowledge learned from parallel data. Subsequently, the features will further be fed into a simple Bi-LSTM predictive model for quality estimation. The experimental results show that our approach achieves the state-of-the-art performance in most public available datasets of WMT 2017/2018 QE task.

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.

scholarly journals Context-Aware Neural Machine Translation for Korean Honorific Expressions

Electronics ◽  
2021 ◽  
Vol 10 (13) ◽  
pp. 1589
Author(s):  
Yongkeun Hwang ◽  
Yanghoon Kim ◽  
Kyomin Jung
Keyword(s):  
Machine Translation ◽  
Deep Neural Networks ◽  
Contextual Information ◽  
Context Aware ◽  
Neural Machine Translation ◽  
Translation Quality ◽  
Sentence Level ◽  
Proposed Model ◽  
The Given ◽  
The Relationship

Neural machine translation (NMT) is one of the text generation tasks which has achieved significant improvement with the rise of deep neural networks. However, language-specific problems such as handling the translation of honorifics received little attention. In this paper, we propose a context-aware NMT to promote translation improvements of Korean honorifics. By exploiting the information such as the relationship between speakers from the surrounding sentences, our proposed model effectively manages the use of honorific expressions. Specifically, we utilize a novel encoder architecture that can represent the contextual information of the given input sentences. Furthermore, a context-aware post-editing (CAPE) technique is adopted to refine a set of inconsistent sentence-level honorific translations. To demonstrate the efficacy of the proposed method, honorific-labeled test data is required. Thus, we also design a heuristic that labels Korean sentences to distinguish between honorific and non-honorific styles. Experimental results show that our proposed method outperforms sentence-level NMT baselines both in overall translation quality and honorific translations.

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.

Improved neural machine translation for low-resource English–Assamese pair

2021 ◽  
pp. 1-12
Author(s):  
Sahinur Rahman Laskar ◽  
Abdullah Faiz Ur Rahman Khilji ◽  
Partha Pakray ◽  
Sivaji Bandyopadhyay
Keyword(s):  
Machine Translation ◽  
Data Augmentation ◽  
Language Translation ◽  
Linguistically Diverse ◽  
Neural Machine Translation ◽  
Low Resource ◽  
Parallel Data ◽  
The World ◽  
Translation Accuracy ◽  
Vocabulary Problems

Language translation is essential to bring the world closer and plays a significant part in building a community among people of different linguistic backgrounds. Machine translation dramatically helps in removing the language barrier and allows easier communication among linguistically diverse communities. Due to the unavailability of resources, major languages of the world are accounted as low-resource languages. This leads to a challenging task of automating translation among various such languages to benefit indigenous speakers. This article investigates neural machine translation for the English–Assamese resource-poor language pair by tackling insufficient data and out-of-vocabulary problems. We have also proposed an approach of data augmentation-based NMT, which exploits synthetic parallel data and shows significantly improved translation accuracy for English-to-Assamese and Assamese-to-English translation and obtained state-of-the-art results.

scholarly journals The Development of a Comprehensive Data Set for Systematic Studies of Machine Translation

2021 ◽  
pp. 248-262
Author(s):  
Jörg Tiedemann
Keyword(s):  
Machine Translation ◽  
Training Data ◽  
Sufficient Information ◽  
Data Set ◽  
Neural Machine Translation ◽  
High Resource ◽  
Language Groups ◽  
Comprehensive Data ◽  
Parallel Data ◽  
Initial Results

This paper presents our on-going efforts to develop a comprehensive data set and benchmark for machine translation beyond high-resource languages. The current release includes 500GB of compressed parallel data for almost 3,000 language pairs covering over 500 languages and language variants. We present the structure of the data set and demonstrate its use for systematic studies based on baseline experiments with multilingual neural machine translation between Finno-Ugric languages and other language groups. Our initial results show the capabilities of training effective multilingual translation models with skewed training data but also stress the shortcomings with low-resource settings and the difficulties to obtain sufficient information through straightforward transfer from related languages.

Sign in / Sign up

Export Citation Format

Share Document