Neural Machine Translation Systems Research Articles

Reduction of Neural Machine Translation Failures by Incorporating Statistical Machine Translation

This paper proposes a hybrid machine translation (HMT) system that improves the quality of neural machine translation (NMT) by incorporating statistical machine translation (SMT). Therefore, two NMT systems and two SMT systems were built for the Slovenian–English language pair, each for translation in one direction. We used a multilingual language model to embed the source sentence and translations into the same vector space. From each vector, we extracted features based on the distances and similarities calculated between the source sentence and the NMT translation, and between the source sentence and the SMT translation. To select the best possible translation, we used several well-known classifiers to predict which translation system generated a better translation of the source sentence. The proposed method of combining SMT and NMT in the hybrid system is novel. Our framework is language-independent and can be applied to other languages supported by the multilingual language model. Our experiment involved empirical applications. We compared the performance of the classifiers, and the results demonstrate that our proposed HMT system achieved notable improvements in the BLEU score, with an increase of 1.5 points and 10.9 points for both translation directions, respectively.

Exploring Graph-based Transformer Encoder for Low-Resource Neural Machine Translation

The Transformer is commonly used in Neural Machine Translation (NMT), but it faces issues with over-parameterization in low-resource settings. This means that simply increasing the model parameters significantly will not lead to improved performance. In this study, we propose a graph-based approach that slightly increases the parameters while significantly outperforming the scaled version of the Transformer. We accomplish this by utilizing Graph Neural Networks to encode Universal Conceptual Cognitive Annotation (UCCA), allowing the linguistic features of UCCA to be incorporated into the word embeddings. This improves the performance of the NMT system since the word embedding is now more capable and informative. Experimental results demonstrate that the proposed method outperforms the scaled Transformer model by +0.4, +0.41, and +0.33 BLEU, respectively, in English-Vietnamese/French/Czech datasets. Furthermore, this method reduces the number of parameters by 47% when compared to the scaled Transformer. A thorough analysis of error patterns reveals that the proposed method provides structural awareness to translation systems. Our code is available at: https://github.com/nqbinh17/UCCA_GNN.

Quality Evaluation of C-E Translation of Legal Texts by Mainstream Machine Translation Systems—An Example of DeepL and Metasota

Despite significant progress made in machine translation technology and the ongoing efforts in practical and commercial application of neural machine translation systems, their performance in vertical fields remains unsatisfactory. To avoid misunderstandings and excessive expectations of a specific machine translation system, this research selected legal texts as its real data research object. The text translation tasks were accomplished using two popular neural machine translation systems, DeepL and Metasota, both domestically and internationally, and evaluated using internationally recognized BLEU algorithm to reflect their Chinese-to-English translation performance in legal fields. Based on the determined BLEU score, the study adopted an artificial analysis method to analyze the grammatical aspects of the machine translation output, including the accuracy of terminology usage, word order, subject-verb agreement, sentence structure, tense, and voice to enable readers to have a rational understanding of the gap between machine translation and human translation in legal text translation, and objectively assess the application and future development prospects of machine translation in legal text fields. The experimental results indicate that machine translation systems still face challenges in achieving high-quality legal text translations and meeting practical needs, and that further post-translation editing research is needed to improve the accuracy of legal text translation.

Do cues in a video help in handling rare words in a machine translation system under a low-resource setting?

Video modality is an emerging research area among the numerous modalities utilized for multimodal machine translation. Multimodal machine translation uses multiple modalities to improve the machine-translated target language from the source language. However, the currently available multimodal dataset is focused on a few well-studied languages. In this paper, we propose a video-guided multimodal machine translation (VMMT) model under a low-resource setting by building a synthetic multimodal dataset of the English-Hindi language pair, the first one of its kind for this language pair. The VMMT system employs spatio-temporal video context as an additional input modality along with the source text. The spatio-temporal video context is extracted using a pre-trained 3D convolutional neural network. We report how well the VMMT systems outperform the text-only neural machine translation (NMT) system using automatic evaluation metrics and human evaluation on two test datasets: one in-domain and another out-domain. Our results indicate that the use of video context as an additional input modality enhances the performance of the MT system in resolving the various MT challenges, such as handling rare words, ambiguity, etc., in both English→Hindi and Hindi→English translations. Our experimental results show a significant improvement of up to +4.2 BLEU and +0.07 chrF scores in English→Hindi and +5.4 BLEU and +0.07 chrF scores in Hindi→English with our VMMT system over unimodal NMT system. Our findings highlight the potential of visual cues as an additional modality for improving machine translation systems especially in low-resource settings and emphasize the importance of synthetic multimodal datasets in addressing the scarcity of diverse data for less-studied language pairs.

Learning to decode to future success for multi-modal neural machine translation

Existing only-text NMT (neural machine translation) systems can benefit from explicitly modelling target future contexts as recurrent states. However, the modelled target future context is implicit in the conventional only-text NMT as the target is invisible in inference. For the Multi-modal Neural Machine Translation (MNMT), the visual annotation presents the content described in the bilingual parallel sentence pair, so-called multi-modal consistency. This consistency provides an advantage that future target context can be simulated in visual features. This paper proposes a novel translation model that allows MNMT to encode the future target context from the visual annotation in auto-regressive decoding. Our model uses visual-target consistency to enhance the target generation. Moreover, we use the multi-modal consistency that fully uses the visual annotation to encourage the semantic agreement between bilingual parallel sentences and the pivoted visual annotation. Empirical results on several recent multi-model translation datasets demonstrated the MNMT model which we proposed significantly improved translation performance on a strong baseline, especially achieving new state-of-the-art results on all three language pairs with visual annotations. Our code will be available after acceptance.

San-Eng: Sanskrit to English Translator using Machine Learning

In the past decade, machine learning has made great strides in improving automatic translation. In general, machine learning algorithms have been able to achieve better translation quality by learning from large amounts of data. One approach to machine translation is to use a statistical machine translation (SMT) system. SMT systems learn to translate by statistical methods, using a large parallel corpus of text in multiple languages. The most successful SMT systems are based on the translation model known as the phrase-based translation model. In recent years, a new approach to machine translation has emerged, known as neural machine translation (NMT). NMT systems use artificial neural networks to learn to translate. NMT systems have shown to be very successful in translating between languages that are closely related, such as English and Hindi or Reverse is also true. In recent years, a new approach to machine translation has emerged, known as neural machine translation (NMT). NMT systems use artificial neural networks to learn to translate. NMT systems have shown to be very successful in translating between languages that are closely related, such as English and Hindi or Reverse is also true

Human and machine translation of occasionalisms in literary texts

Abstract Literary occasionalisms, new words coined by writers with a particular poetic aim in view, often pose a great challenge for translators. Given recent advances in machine translation (MT), could literary translators benefit from MT when it comes to the translation of occasionalisms? We address this question by considering the work of Austria’s most important nineteenth-century comedy writer, Johann Nestroy (1801–1862). We compare how human translators and two generic neural MT systems (Google Translate, DeepL) translated occasionalisms (compounds, derivations, and blends) in Nestroy’s play Der Talisman into English. While human translators largely refrained from creating new target expressions, the two MT systems generated a number of viable new coinages, most of them by literal translation procedures. In an interactive human-computer environment, using MT output as a repository from which to retrieve novel target solutions or derive inspiration might open up new avenues in the practice of literary translation.

НЕЙРОННИЙ МАШИННИЙ ПЕРЕКЛАД: ОСНОВНІ ПРИНЦИПИ, СИЛЬНІ ТА СЛАБКІ СТОРОНИ

Neural Machine translation (NMT) is a new and advanced method of machine translation based on neural networks. NMT systems use artificial intelligence to predict words in the process of translation. This method allows to achieve high efficiency and goo

On the scalability of data augmentation techniques for low-resource machine translation between Chinese and Vietnamese

ABSTRACT Neural Machine Translation (NMT) has constantly been shown to be a standard choice to build a translation system, in both academia and industry. For low-resource language pairs, data augmentation techniques have been widely used to tackle the data shortage problem in NMT. In this paper, we investigate the scaling behaviour of transformer-based NMT model to the increasing amount of synthetic data. Through the experiments, conducted in the Chinese-to-Vietnamese translation task, we aim to provide a guideline to the application of several methods such as back-translation, tagged back-translation, self-training and sentence concatenation in a low-resource, less-related language pair. Our results suggest that choosing the appropriate amount of synthetic data is a crucial task when building NMT systems. In addition, when combining methods, it is recommended to tag the data sources before training.

Morphologically Motivated Input Variations and Data Augmentation in Turkish-English Neural Machine Translation

Success of neural networks in natural language processing has paved the way for neural machine translation (NMT), which rapidly became the mainstream approach in machine translation. Significant improvement in translation performance has been achieved with breakthroughs such as encoder-decoder networks, attention mechanism, and Transformer architecture. However, the necessity of large amounts of parallel data for training an NMT system and rare words in translation corpora are issues yet to be overcome. In this article, we approach NMT of the low-resource Turkish-English language pair. We employ state-of-the-art NMT architectures and data augmentation methods that exploit monolingual corpora. We point out the importance of input representation for the morphologically rich Turkish language and make a comprehensive analysis of linguistically and non-linguistically motivated input segmentation approaches. We prove the effectiveness of morphologically motivated input segmentation for the Turkish language. Moreover, we show the superiority of the Transformer architecture over attentional encoder-decoder models for the Turkish-English language pair. Among the employed data augmentation approaches, we observe back-translation to be the most effective and confirm the benefit of increasing the amount of parallel data on translation quality. This research demonstrates a comprehensive analysis on NMT architectures with different hyperparameters, data augmentation methods, and input representation techniques, and proposes ways of tackling the low-resource setting of Turkish-English NMT.

Textual Augmentation Techniques Applied to Low Resource Machine Translation: Case of Swahili

In this work we investigate the impact of applying textual data augmentation tasks to low resource machine translation. There has been recent interest in investigating approaches for training systems for languages with limited resources and one popular approach is the use of data augmentation techniques. Data augmentation aims to increase the quantity of data that is available to train the system. In machine translation, majority of the language pairs around the world are considered low resource because they have little parallel data available and the quality of neural machine translation (NMT) systems depend a lot on the availability of sizable parallel corpora. We study and apply three simple data augmentation techniques popularly used in text classification tasks; synonym replacement, random insertion and contextual data augmentation and compare their performance with baseline neural machine translation for English-Swahili (En-Sw) datasets. We also present results in BLEU, ChrF and Meteor scores. Overall, the contextual data augmentation technique shows some improvements both in the EN -> SW and SW -> EN directions. We see that there is potential to use these methods in neural machine translation when more extensive experiments are done with diverse datasets.

Low-Resource Neural Machine Translation Improvement Using Source-Side Monolingual Data

Despite the many proposals to solve the neural machine translation (NMT) problem of low-resource languages, it continues to be difficult. The issue becomes even more complicated when few resources cover only a single domain. In this paper, we discuss the applicability of a source-side monolingual dataset of low-resource languages to improve the NMT system for such languages. In our experiments, we used Wolaytta–English translation as a low-resource language. We discuss the use of self-learning and fine-tuning approaches to improve the NMT system for Wolaytta–English translation using both authentic and synthetic datasets. The self-learning approach showed +2.7 and +2.4 BLEU score improvements for Wolaytta–English and English–Wolaytta translations, respectively, over the best-performing baseline model. Further fine-tuning the best-performing self-learning model showed +1.2 and +0.6 BLEU score improvements for Wolaytta–English and English–Wolaytta translations, respectively. We reflect on our contributions and plan for the future of this difficult field of study.

Hyper-parameter optimization in neural-based translation systems: A case study

Abstract Machine translation (MT) is an important use case in natural language processing (NLP) that converts a source language to a target language automatically. Modern intelligent system or artificial intelligence (AI) uses a machine learning approach and the machine has acquired learning ability using datasets. Nowadays, in the MT domain, the neural machine translation (NMT) system has almost replaced the statistical machine translation (SMT) system. The NMT systems use a deep learning framework in their implementation. To achieve higher accuracy during the training of the NMT model, extensive hyper-parameter tuning is required. The paper highlights the significance of hyper-parameter tuning in various machine learning algorithms. And as a case study, in-house experimentation was conducted on a low-resource English–Bangla language pair by designing an NMT system and the significance of various hyper-parameter optimizations was analyzed while evaluating its performance with an automatic metric BLEU. The BLEU scores obtained for the first, second, and third randomly picked test sentences are 4.1, 3.2, and 3.01, respectively.

Efeitos das operações de pré-edição na tradução audiovisual usando o TRADOS: uma análise experimental das traduções de estudantes sauditas

Abstract Neural Machine Translation (NMT) is a revolutionary innovation that has had a significant impact not only on the translation industry but also on translation studies. This technology is creating new opportunities for shaping identities and generating new knowledge and perspectives. This led researchers to undeniably and increasingly conduct studies to improve NMT performance. These studies involve assessing the quality of the output, determining the extent to which humans can be involved in the machine-based process, and proposing solutions to redress the deficiencies. In this regard, the paper focuses on the impact of pre-editing (PE) operations on the translation of audiovisual children’s literary texts (subtitles) from English to Arabic using TRADOS. The work seeks to accomplish a number of pre-editing-related research goals in the context of Arabic NMT systems. Initially, it aims to define and clarify the idea of PE and its function in enhancing Arabic NMT systems’ performance. Second, it looks at PE mechanisms and methods and how they might improve the appropriateness and accuracy of Arabic machine translation. Additionally, the study attempts to investigate the value of PE in enhancing the Arabic translation of audiovisual children’s literature. The study also seeks to list the difficulties and restrictions related to PE and suggest viable strategies to get over them. Finally, the paper offers suggestions for further investigation into NMT systems using Arabic and PE. To achieve these goals, the researchers conducted a human evaluation of NMT for two animated movie subtitles and determined the necessary PE operations. The findings revealed that PE has the potential to improve the quality of literary translations and enhance their comprehensibility and acceptability.

Document-Level Neural Machine Translation With Recurrent Context States

Integrating contextual information into sentence-level neural machine translation (NMT) systems has been proven to be effective in generating fluent and coherent translations. However, taking too much context into account slows down these systems, especially when context-aware models are applied to the decoder side. To improve efficiency, we propose a simple and fast method to encode all sentences in an arbitrary large context window. It makes contextual representations in the process of translating each sentence so that the overhead introduced by the context model is almost negligible. We experiment with our method on three widely used English-German document-level translation datasets, which obtain substantial improvements over the sentence-level baseline with almost no loss in efficiency. Moreover, our method also achieves comparable performance with previous strong context-aware baselines and speeds up the inference by <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$1.53\times $ </tex-math></inline-formula> . The speed-up is even larger when more contexts are taken into account. On the ContraPro pronoun translation dataset, it significantly outperforms the strong baseline.

DetTrans: A Lightweight Framework to Detect and Translate Noisy Inputs Simultaneously

Neural machine translation (NMT) systems trained on clean data usually suffer from performance degradation when translating noisy inputs. Existing works attempt to improve the robustness of NMT normally via data augmentation, where synthetic noisy data are mixed with original clean data, either for training NMT with the standard NMT loss alone, or for tuning auxiliary tasks in a multi-task learning manner. Typical auxiliary tasks include detecting and correcting noises, exploiting noisy outputs for contrastive learning etc. The aforementioned two auxiliary tasks are generally designed independently, and the modules for detecting and correcting noises are heavyweight. In this article, we propose a new framework, DetTransNet ( <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Det</b> ector- <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Trans</b> lator <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Net</b> work), aiming to detect positions of noises in the input and translate the input simultaneously. The newly introduced noise detector module is essentially a lightweight binary classifier built upon the final layer of the encoder of the original Transformer model for the translation task, which is to identify at which position of the input has potential noise. The module has a very few parameters. In order to help the model capture the relationship between clean instances and their noisy counterparts, an extra loss is further introduced to enhance the interaction between clean and noisy data. In this way, we combine noise detection and contrastive learning together. As the model is able to identify and locate noises, a heuristic method is proposed to correct detected noises, in order to achieve better translations. Experiments show that DetTransNet is robust to four types of noises (deletion, insertion, swapping, keyboard), and obtain a substantial improvement of up to 1.6 BLEU points across different datasets.

A Smaller and Better Word Embedding for Neural Machine Translation

Word embeddings play an important role in Neural Machine Translation (NMT). However, it still has a series of problems such as ignoring the prior knowledge of the association between words, relying on specific task constraints passively in parameter training, and isolating individual embedding’s learning process from one another. In this paper, we propose a new word embedding method to add the prior knowledge of the association between words to the training process, and at the same time to share the iterative training results among all word embeddings. This method is applicable to all mainstream NMT systems. In our experiments, it achieves an improvement of +0.9 BLEU points on the WMT’14 English→German task. On the Global Voices v2018q4 Spanish→Czech low-resource translation tasks, it leads to a more prominent performance improvement over the strong baselines (a +2.6 BLEU improvement on average). As another “bonus”, the new word embedding has far fewer parameters than the traditional word embedding, even as low as 15% of the parameters of the baselines.

Translation Quality Regarding Low-Resource, Custom Machine Translations: A Fine-Grained Comparative Study on Turkish-to-English Statistical and Neural Machine Translation Systems

Corpus-based machine translation (MT) has been the main approach to developing and implementing MT systems in both academia and the industry over the last three decades. In this field, the type and size of the corpus used for training MT engines have presented problems for both statistical MT (SMT) systems as well as neural MT (NMT) systems, being the two dominant corpusbased approaches. Moreover, language pairs such as Turkish-English have been understudied within this framework. This article aims to evaluate the translation quality in Turkish-to-English custom MT systems that have been trained on different corpus sizes and types. Two NMT engines and two SMT engines were trained on the KantanMT platform using two different training corpus types with either only domain-specific cardiology corpus or this corpus plus a mixed-domain corpus. The study conducted both automatic evaluations with metrics including BLEU, F-Measure and TER, as well as a comprehensive human evaluation with metrics including fluency, A/B test, and adequacy. Lastly, the study realized a separate, subjective terminology evaluation in order to investigate how differently MT systems handle terminology, as this is a crucial aspect for specific-domain text types such as cardiology. While the automatic evaluation results suggest the SMT engines to perform better than NMT engines, all human evaluators rated the mixed-domain NMT engine as the highest performing one. However, the terminology evaluation task demonstrated SMT to still be able to perform better and to commit less terminology errors, despite the industry and academia shifting toward NMT engines.

Robust Data Augmentation for Neural Machine Translation through EVALNET

Since building Neural Machine Translation (NMT) systems requires a large parallel corpus, various data augmentation techniques have been adopted, especially for low-resource languages. In order to achieve the best performance through data augmentation, the NMT systems should be able to evaluate the quality of augmented data. Several studies have addressed data weighting techniques to assess data quality. The basic idea of data weighting adopted in previous studies is the loss value that a system calculates when learning from training data. The weight derived from the loss value of the data, through simple heuristic rules or neural models, can adjust the loss used in the next step of the learning process. In this study, we propose EvalNet, a data evaluation network, to assess parallel data of NMT. EvalNet exploits a loss value, a cross-attention map, and a semantic similarity between parallel data as its features. The cross-attention map is an encoded representation of cross-attention layers of Transformer, which is a base architecture of an NMT system. The semantic similarity is a cosine distance between two semantic embeddings of a source sentence and a target sentence. Owing to the parallelism of data, the combination of the cross-attention map and the semantic similarity proved to be effective features for data quality evaluation, besides the loss value. EvalNet is the first NMT data evaluator network that introduces the cross-attention map and the semantic similarity as its features. Through various experiments, we conclude that EvalNet is simple yet beneficial for robust training of an NMT system and outperforms the previous studies as a data evaluator.

An approach based on deep learning for Indian sign language translation

PurposeAccording to the Indian Sign Language Research and Training Centre (ISLRTC), India has approximately 300 certified human interpreters to help people with hearing loss. This paper aims to address the issue of Indian Sign Language (ISL) sentence recognition and translation into semantically equivalent English text in a signer-independent mode.Design/methodology/approachThis study presents an approach that translates ISL sentences into English text using the MobileNetV2 model and Neural Machine Translation (NMT). The authors have created an ISL corpus from the Brown corpus using ISL grammar rules to perform machine translation. The authors’ approach converts ISL videos of the newly created dataset into ISL gloss sequences using the MobileNetV2 model and the recognized ISL gloss sequence is then fed to a machine translation module that generates an English sentence for each ISL sentence.FindingsAs per the experimental results, pretrained MobileNetV2 model was proven the best-suited model for the recognition of ISL sentences and NMT provided better results than Statistical Machine Translation (SMT) to convert ISL text into English text. The automatic and human evaluation of the proposed approach yielded accuracies of 83.3 and 86.1%, respectively.Research limitations/implicationsIt can be seen that the neural machine translation systems produced translations with repetitions of other translated words, strange translations when the total number of words per sentence is increased and one or more unexpected terms that had no relation to the source text on occasion. The most common type of error is the mistranslation of places, numbers and dates. Although this has little effect on the overall structure of the translated sentence, it indicates that the embedding learned for these few words could be improved.Originality/valueSign language recognition and translation is a crucial step toward improving communication between the deaf and the rest of society. Because of the shortage of human interpreters, an alternative approach is desired to help people achieve smooth communication with the Deaf. To motivate research in this field, the authors generated an ISL corpus of 13,720 sentences and a video dataset of 47,880 ISL videos. As there is no public dataset available for ISl videos incorporating signs released by ISLRTC, the authors created a new video dataset and ISL corpus.