Machine Translation Approach Research Articles

Hybrid NMT model and comparison with existing machine translation approaches

Hybrid NMT model and comparison with existing machine translation approaches

Improved Urdu-English Neural Machine Translation with a fully Convolutional Neural Network Encoder

Neural machine translation (NMT) approaches driven by artificial intelligence (AI) has gained more and more attention in recent years, mainly due to their simplicity yet state-of-the-art performance. Despite NMT models with attention mechanism relying heavily on the accessibility of substantial parallel corpora, they have demonstrated efficacy even for languages with limited linguistic resources. The convolutional neural network (CNN) is frequently employed in tasks involving visual and speech recognition. Implementing CNN for MT is still challenging compared to the predominant approaches. Recent research has shown that the CNN-based NMT model cannot capture long-term dependencies present in the source sentence. The CNN-based model can only capture the word dependencies within the width of its filters. This unnatural character often causes a worse performance for CNN-based NMT than the RNN-based NMT models. This study introduces a simple method to improve neural translation of a low-resource language, specifically Urdu-English (UR-EN). In this paper, we use a Fully Convolutional Neural Network (FConv-NN) based NMT architecture to create a powerful MT encoder for UR-EN translation that can capture the long dependency of words in a sentence. Although the model is quite simple, it yields strong empirical results. Experimental results show that the FConv-NN model consistently outperforms the traditional CNN-based model with filters. On the Urdu-English Dataset, the FConv-NN model produces translation with a gain of 18.42 BLEU points. Moreover, the quantitative and comparative analysis shows that in a low-resource setting, FConv-NN-based NMT outperforms conventional CNN-based NMT models.

Integrating Sparse Reward Handling, Ethical Considerations, And Domain-Specific Adaptation In RlBased Machine Translation For Low-Resource Languages

Effective communication across languages remains a critical challenge, particularly in low-resource settings where conventional machine translation approaches falter due to sparse data and limited quality feedback. This paper presents a holistic framework to enhance reinforcement learning (RL) based machine translation systems tailored for such environments. We address the trifecta of challenges: sparse feedback on translation quality, ethical implications in algorithmic decision-making, and the imperative to adapt models to nuanced linguistic domains. This approach integrates advanced techniques in sparse reward handling, ensuring RL models learn efficiently despite limited feedback. Ethical considerations drive our methodology, emphasizing fairness, bias mitigation, and cultural sensitivity to uphold ethical standards in AI-driven translations. Additionally, domain-specific adaptation strategies are explored to tailor models to diverse linguistic contexts, from technical jargon to colloquialisms, enhancing translation accuracy and relevance. Through a rigorous experimental framework, including evaluation metrics like BLEU score and user feedback, we demonstrate substantial improvements in translation quality and ethical compliance compared to traditional methods. This research contributes to the evolution of robust, inclusive translation technologies pivotal for fostering global understanding and equitable access to information. This paper not only addresses current challenges but also sets a precedent for future research in AI ethics and machine learning applications, advocating for responsible innovation in crosscultural communication technologies

LLMs-based machine translation for E-commerce

Large language models(LLMs) have shown promising performance for various downstream tasks, especially machine translation. However, LLMs and Specialized Translation Models (STMs) are designed to handle general translation needs, they are not well-suited for domains with specialized terms and writing styles, such as e-commerce, legal, and medicine. In the e-commerce domain, the text often contains many domain-specific terms and keyword-stacked structures, leading to poor translation quality with existing NMT methods. To tackle these problems, we have collected two resources specifically for the e-commerce domain, including aligned Chinese-English bilingual terms and parallel corpus from real e-commerce scenarios for model fine-tuning. We propose an LLMs-based E-commerce machine translation approach(LEMT) which includes LLMs utilization, e-commerce resources collection, and tokenizer optimization. We conduct two-stage fine-tuning and self-contrastive enhancement based on general LLMs to enable the model to learn translation features in the e-commerce domain. Through comprehensive evaluations on real e-commerce titles, our LEMT methodology demonstrates superior translation quality and robustness, outperforming leading NMT models such as NLLB, LLaMA, and even GPT-4.

An Evaluation of ChatGPT's Translation Accuracy Using BLEU Score

Traditional views have long held that machine translation cannot achieve the quality and accuracy of human translators, especially in complex language pairs like Persian and English. This study challenges this perspective by demonstrating that ChatGPT-4, with access to vast amounts of multilingual data and leveraging advanced large language model algorithms, significantly outperforms widely utilized open-source machine translation tools and approaches the realm of human translation quality. This research aims to critically assess the translation accuracy of ChatGPT-4 against a traditional open-source machine translation tool from Persian to English, highlighting the advancements in artificial intelligence-driven translation technologies. Using Bilingual Evaluation Understudy scores for a comprehensive evaluation, this study compares the translation outputs from ChatGPT-4 with MateCat, providing a quantitative basis for comparing their accuracy and quality. ChatGPT-4 achieves a BLUE score of 0.88 and an accuracy of 0.68, demonstrating superior performance compared to MateCat, with a 0.82 BLUE score and 0.49 accuracy. The results indicate that the translations generated by ChatGPT-4 surpass those produced by MateCat and nearly mirror the quality of human translations. The evaluation demonstrates the effectiveness of OpenAI's large language model algorithms in improving translation accuracy.

Investigating Machine Translation Errors in Rendering English Literary Texts into Arabic

Machine translation is a machine that employs artificial intelligence (AI) to translate texts between languages without human intervention. Machine translation approaches translate text or speech from one language to another, including the contextual, idiomatic and pragmatic issues of both different languages. The present study aims to analyze the translation of literary texts selected from different novels, plays, and poems and clarify the method for translating them from English into Arabic. This study also aims to discover machine translation errors in rendering English literary texts and clarify the translator's role in transferring the rhetorical impact on the reader who reads the (TT). This study hypothesizes that translators(students) face difficulties regarding words and structures when translating literary texts from English into Arabic because they misunderstand rhetorical devices. So they tend to use machine translations that translate literally, such as (Google Translate, Reverso translation and Bing Microsoft translation). This study adopted two models: First, Newmark's translation model (1988b), which includes two basic types of translation: semantic and communicative. This model is used widely in the analysis of literary texts. Second, Harris (2018) linguistic model theory of rhetorical question and the general purpose of the rhetorical devices to analyze the data. Finally, the study ends with the conclusions that all machine translation programs (Google Translate (GT), Reverso Translation (Reverso. T), Bing Microsoft Translation (Bing. M.T) in rendering English literary texts from English into Arabic are unacceptable and have more problems because these programs are just machines and cannot think or feel as well as all these machines renderings are meaningless and ambiguous. So Human translation is better than Machine Translation because the first uses communicative translation while the other uses semantic translation.

English and Sanskrit Language Comparison and Machine Translation Approaches.

English and Sanskrit Language Comparison and Machine Translation Approaches.

Towards Faster k-Nearest-Neighbor Machine Translation

Recent works have proven the effectiveness of k-nearest-neighbor machine translation(a.k.a kNN-MT) approaches to produce remarkable improvement in cross-domain translations. However, these models suffer from heavy retrieve overhead on the entire datastore when decoding each token. We observe that during the decoding phase, about 67% to 84% of tokens are unvaried after searching over the corpus datastore, which means most of the tokens cause futile retrievals and introduce unnecessary computational costs by initiating k-nearestneighbor searches. We consider this phenomenon is explainable in linguistics and propose a simple yet effective multi-layer perceptron (MLP) network to predict whether a token should be translated jointly by the neural machine translation model and probabilities produced by the kNN or just by the neural model. The results show that our method succeeds in reducing redundant retrieval operations and significantly reduces the overhead of 𝑘NN retrievals by up to 53% at the expense of a slight decline in translation quality. Moreover, our method could work together with all existing kNN-MT systems

Decoding Multilingual Topic Dynamics and Trend Identification through ARIMA Time Series Analysis on Social Networks: A Novel Data Translation Framework Enhanced by LDA/HDP Models

In this study, the authors present a novel methodology adept at decoding multilingual topic dynamics and identifying communication trends during crises. We focus on dialogues within Tunisian social networks during the coronavirus pandemic and other notable themes like sports and politics. We start by aggregating a varied multilingual corpus of comments relevant to these subjects. This dataset undergoes rigorous refinement during data preprocessing. We then introduce our No‐English‐to‐English Machine Translation approach to handle linguistic differences. Empirical tests of this method show high accuracy and F1 scores, highlighting its suitability for linguistically coherent tasks. Delving deeper, advanced modeling techniques, specifically LDA and HDP models, are employed to extract pertinent topics from the translated content. This leads to applying ARIMA time series analysis to decode evolving topic trends. Applying our method to a multilingual Tunisian dataset, we effectively identify key topics mirroring public sentiment. Such insights prove vital for organizations and governments striving to understand public perspectives during crises. Compared to standard approaches, our model outperforms, as confirmed by metrics like coherence score, U‐mass, and topic coherence. Additionally, an in‐depth assessment of the identified topics reveals notable thematic shifts in discussions, with the proposed trends’ identification indicating impressive accuracy, backed by RMSE‐based analysis.

A review of existing Machine Translation Approaches, their Challenges and Evaluation Metrics

Machine translation is the process of translating a natural language into another. The primary goal of machine translation is to bridge the linguistic gap between languages. A significant job that may be utilized is to extract information from texts written in different languages through machine translation (MT). Due to the remarkable developments in Machine Translation over the past several years, we have entered the era of Neural Machine Translation (NMT). A review of MT is essential for better understanding of MT in the domain of Natural Language Processing. This paper focuses on Statistical, Corpus, Example, Rule based, Transfer based, direct based and Nural Machine Translation approach, their challenges, and existing evaluation metrics such as BLEU score and Human evaluation metrics.

Filtered data augmentation approach based on model competence evaluation

The scale of parallel corpus plays an important role in training high-quality neural machine translation models. In order to expand the scale of parallel corpus in low-resource scenarios, researchers have proposed a series of data augmentation approaches, in which the most representative work is the back-translation. The back-translation approach uses a basic translation model to translate the target monolingual corpus into the source language, and then combines it into a pseudo parallel corpus to expand the training data. Due to the simple and efficient data expansion strategies, the back-translation approach becomes the mainstream data augmentation approach of neural machine translation. However, in low-resource scenarios, only low-precision basic translation models can be used. The pseudo-parallel corpus translated by this model contains low-quality sentence pairs, which inevitably introduces noises and leads to negative impacts to translation procedure. To improve the performance of low-resource neural machine translation, we propose a filtered data augmentation method based on the model competence evaluation, which can effectively improve the quality of training data by using both the filtered back-translation and dynamic evaluation of translation model capabilities. Comparative experiments show that the proposed approach can improve the quality of training data and the performance of low-resource neural machine translation.

A Neural Machine Translation Approach for Translating Different Languages in English

A Neural Machine Translation Approach for Translating Different Languages in English

A Chinese–Kazakh Translation Method That Combines Data Augmentation and R-Drop Regularization

Low-resource languages often face the problem of insufficient data, which leads to poor quality in machine translation. One approach to address this issue is data augmentation. Data augmentation involves creating new data by transforming existing data through methods such as flipping, cropping, rotating, and adding noise. Traditionally, pseudo-parallel corpora are generated by randomly replacing words in low-resource language machine translation. However, this method can introduce ambiguity, as the same word may have different meanings in different contexts. This study proposes a new approach for low-resource language machine translation, which involves generating pseudo-parallel corpora by replacing phrases. The performance of this approach is compared with other data augmentation methods, and it is observed that combining it with other data augmentation methods further improves performance. To enhance the robustness of the model, R-Drop regularization is also used. R-Drop is an effective method for improving the quality of machine translation. The proposed method was tested on Chinese–Kazakh (Arabic script) translation tasks, resulting in performance improvements of 4.99 and 7.7 for Chinese-to-Kazakh and Kazakh-to-Chinese translations, respectively. By combining the generation of pseudo-parallel corpora through phrase replacement with the application of R-Drop regularization, there is a significant advancement in machine translation performance for low-resource languages.

A Hybrid Optimization Approach for Neural Machine Translation Using LSTM+RNN with MFO for Under Resource Language (Telugu)

NMT (Neural Machine Translation) is an innovative approach in the field of machine translation, in contrast to SMT (statistical machine translation) and Rule-based techniques which has resulted annotable improvements. This is because NMT is able to overcome many of the shortcomings that are inherent in the traditional approaches. The Development of NMT has grown tremendously in the recent years but NMT performance remain under optimal when applied to low resource language pairs like Telugu, Tamil and Hindi. In this work a proposedmethod fortranslating pairs (Telugu to English) is attempted, an optimal approach which enhancesthe accuracy and execution time period.A hybrid method approach utilizing Long short-term memory (LSTM) and traditional Recurrent Neural Network (RNN) are used for testing and training of the dataset. In the event of long-range dependencies, LSTM will generate more accurate results than a standard RNN would endure and the hybrid technique enhances the performance of LSTM. LSTM is used during the encoding and RNN is used in decoding phases of NMT. Moth Flame Optimization (MFO) is utilized in the proposed system for the purpose of providing the encoder and decoder model with the best ideal points for training the data.

Investigating Unsupervised Neural Machine Translation for Low-resource Language Pair English-Mizo via Lexically Enhanced Pre-trained Language Models

The vast majority of languages in the world at present are considered to be low-resource languages. Since the availability of large parallel data is crucial for the success of most modern machine translation approaches, improving machine translation for low-resource languages is a key challenge. Most unsupervised techniques for translation benefit closely related languages with monolingual data of substantial quantity. To facilitate research in this direction for the extremely low resource language pair English ( en ) and Mizo ( lus ), we have developed a parallel and monolingual corpus for the Mizo language from various news websites. We explore Unsupervised Neural Machine Translation (UNMT) based on the developed monolingual data. We observe that cross-lingual embedding (CLWE) initializations on subword segmented data during pre-training, based on both masked language modelling and sequence-to-sequence generation tasks, improve translation performance. We experiment with cross-lingual alignment and combined alignment and joint training for learning the cross-lingual embedding representations. We also report baseline performances and the impact of CLWE initialization using semi-supervised and supervised neural machine translation. Empirical results show that both CLWE initializations work well for the distant pair English-Mizo compared to the baselines.

Dzongkha to English translation using the neural machine translation approach

<span>In this era of technology, a communication barrier is a thing of the past. With each passing day, different types of language-based applications are being launched. There are 109 official languages Google has translated to date. However, the Dzongkha translation has not been studied. The purpose of this paper was to study Dzongkha to English translation. The parallel corpus was collected from the Dzongkha development commission of Bhutan. The dataset consisted of 53018 sentence pairs. Unique words in Dzongkha and English were 13,393 and 12,506 respectively. Different neural machine translation models were implemented. The experimental results show that the bleu score of Seq2Seq models followed a fluctuating trend. However, the bleu score of the transformer model increases gradually. It was observed that the transformer outperformed the Seq2Seq models. The highest accuracy and the lowest training loss obtained were 84.46% and 0.014858 respectively with a bleu score of 64.89.</span>

Prose2Poem: The Blessing of Transformers in Translating Prose to Persian Poetry

Persian poetry has consistently expressed its philosophy, wisdom, speech, and rationale based on its couplets, making it an enigmatic language on its own to both native and non-native speakers. Nevertheless, the noticeable gap between Persian prose and poems has left the two pieces of literature mediumless. Having curated a parallel corpus of prose and their equivalent poems, we introduce a novel Neural Machine Translation approach for translating prose to ancient Persian poetry using transformer-based language models in an exceptionally low-resource setting. Translating input prose into ancient Persian poetry presents two primary challenges: In addition to being reasonable in conveying the same context as the input prose, the translation must also satisfy poetic standards. Hence, we designed our method consisting of three stages. First, we trained a transformer model from scratch to obtain an initial translations of the input prose. Next, we designed a set of heuristics to leverage contextually rich initial translations and produced a poetic masked template. In the last stage, we pretrained different variations of BERT on a poetry corpus to use the masked language modelling technique to obtain final translations. During the evaluation process, we considered both automatic and human assessment. The final results demonstrate the eligibility and creativity of our novel heuristically aided approach among Literature professionals and non-professionals in generating novel Persian poems.

Onception: Active Learning with Expert Advice for Real World Machine Translation

Abstract Active learning can play an important role in low-resource settings (i.e., where annotated data is scarce), by selecting which instances may be more worthy to annotate. Most active learning approaches for Machine Translation assume the existence of a pool of sentences in a source language, and rely on human annotators to provide translations or post-edits, which can still be costly. In this article, we apply active learning to a real-world human-in-the-loop scenario in which we assume that: (1) the source sentences may not be readily available, but instead arrive in a stream; (2) the automatic translations receive feedback in the form of a rating, instead of a correct/edited translation, since the human-in-the-loop might be a user looking for a translation, but not be able to provide one. To tackle the challenge of deciding whether each incoming pair source–translations is worthy to query for human feedback, we resort to a number of stream-based active learning query strategies. Moreover, because we do not know in advance which query strategy will be the most adequate for a certain language pair and set of Machine Translation models, we propose to dynamically combine multiple strategies using prediction with expert advice. Our experiments on different language pairs and feedback settings show that using active learning allows us to converge on the best Machine Translation systems with fewer human interactions. Furthermore, combining multiple strategies using prediction with expert advice outperforms several individual active learning strategies with even fewer interactions, particularly in partial feedback settings.

English–Assamese neural machine translation using prior alignment and pre-trained language model

In a multilingual country like India, automatic natural language translation plays a key role in building a community with different linguistic people. Many researchers have explored and improved the translation process for high-resource languages such as English, German, etc., and achieved state-of-the-art results. However, the unavailability of adequate data is the prime obstacle to automatic natural language translation of low-resource north-eastern Indian languages such as Mizo, Khasi, and Assamese. Though the recent past has witnessed a deluge in several automatic natural language translation systems for low-resource languages, the low values of their evaluation measures indicate the scope for improvement. In the recent past, the neural machine translation approach has significantly improved translation quality, and the credit goes to the availability of a huge amount of data. Subsequently, the neural machine translation approach for low-resource language is underrepresented due to the unavailability of adequate data. In this work, we have considered a low-resource English–Assamese pair using the transformer-based neural machine translation, which leverages the use of prior alignment and a pre-trained language model. To extract alignment information from the source–target sentences, we have used the pre-trained multilingual contextual embeddings-based alignment technique. Also, the transformer-based language model is built using monolingual target sentences. With the use of both prior alignment and a pre-trained language model, the transformer-based neural machine translation model shows improvement, and we have achieved state-of-the-art results for the English-to-Assamese and Assamese-to-English translation, respectively.

CsFEVER and CTKFacts: acquiring Czech data for fact verification

In this paper, we examine several methods of acquiring Czech data for automated fact-checking, which is a task commonly modeled as a classification of textual claim veracity w.r.t. a corpus of trusted ground truths. We attempt to collect sets of data in form of a factual claim, evidence within the ground truth corpus, and its veracity label (supported, refuted or not enough info). As a first attempt, we generate a Czech version of the large-scale FEVER dataset built on top of Wikipedia corpus. We take a hybrid approach of machine translation and document alignment; the approach and the tools we provide can be easily applied to other languages. We discuss its weaknesses, propose a future strategy for their mitigation and publish the 127k resulting translations, as well as a version of such dataset reliably applicable for the Natural Language Inference task—the CsFEVER-NLI. Furthermore, we collect a novel dataset of 3,097 claims, which is annotated using the corpus of 2.2 M articles of Czech News Agency. We present an extended dataset annotation methodology based on the FEVER approach, and, as the underlying corpus is proprietary, we also publish a standalone version of the dataset for the task of Natural Language Inference we call CTKFactsNLI. We analyze both acquired datasets for spurious cues—annotation patterns leading to model overfitting. CTKFacts is further examined for inter-annotator agreement, thoroughly cleaned, and a typology of common annotator errors is extracted. Finally, we provide baseline models for all stages of the fact-checking pipeline and publish the NLI datasets, as well as our annotation platform and other experimental data.