Neural Machine Translation Systems Research Articles

The impact of contextual understanding on neural machine translation accuracy: A case study of Indonesian cultural idioms in English translation

The translation of Indonesian idiomatic expressions into English using Neural Machine Translation (NMT) systems presents significant challenges due to the intricate nature of idiomatic language. Idioms are culturally embedded constructs conveying meanings different from their literal interpretations. This study explores the effectiveness of NMT systems in capturing and translating Indonesian idiomatic expressions into English. Using a qualitative approach, 150 diverse Indonesian idioms were evaluated through Google Translate and DeepL. Each idiom was assessed for semantic accuracy, syntactic coherence, and contextual fidelity. Qualitative analysis provided a comprehensive evaluation of translation quality. Findings reveal significant challenges for NMT systems in translating idiomatic expressions. Both Google Translate and DeepL show strengths in some areas, but also have limitations. While they generally capture literal meanings, they often miss metaphorical nuances and cultural connotations. Syntactic errors such as incorrect word order and tense inconsistencies are common, especially in complex idioms. In addition, contextual fidelity analysis shows that NMT systems struggle with contextual appropriateness and pragmatic usage, resulting in translations lacking cultural sensitivity and relevance. These challenges highlight the need for improved algorithms to better interpret and translate idiomatic language across cultural contexts. Accurate idiom translation is crucial for language learners to understand cultural nuances and idiomatic usage. Enhancing the capabilities of NMT systems requires refining algorithms, developing context-aware models, and expanding training datasets with diverse idiomatic expressions. Overcoming these challenges will advance machine translation capabilities and improve cross-cultural communication and language learning experiences.

Evaluating the Translation Accuracy of ChatGPT and DeepL Through the Lens of Implied Subjects

This research aims to offer deeper insights into the translation quality of large language models and neural machine translation systems. It compares the performance of two state-of-the-art models, ChatGPT and DeepL, to explore which system achieves higher translation accuracy. This research employs a highly focused and specialized method to evaluate translation performance, enabling the identification of nuanced differences between advanced AI/machine models. It focuses on implied subjects in contemporary Chinese writer Qiuyu Yu’s Iraq travelogue and examines how the two models handle these implied subjects when translating the text into English. The analysis shows that both ChatGPT and DeepL exhibit high-level intelligence when dealing with the implied subjects. They can flexibly adjust sentence structures to maintain the implicitness or to make the implied subjects explicit. The analysis further reveals that ChatGPT performs better in accurately inferring the implied subjects, which thereby reflects ChatGPT’s superior contextual understanding capability. The comparison of the source text and target texts also shows that ChatGPT’s translation is more succinct, nuanced, and easier to read. DeepL’s translation, by comparison, prioritizes reducing potential misunderstanding. This research tentatively concludes that, though not specialized for translation, ChatGPT translates with higher accuracy and demonstrates more sophisticated intelligence compared to DeepL when translating literary texts.

The Future of the Translation Profession in the Era of Artificial Intelligence. Survey Results from Polish Translators, Translation Trainers, and Students of Translation

Technological advancements in computer science have led to the progressive change of the translation profession. In particular, this concerns machine translation, which has fundamentally changed the role of the translator. AI-driven tools, such as neural machine translation systems, have significantly improved translation speed and accuracy, with the translator role resembling that of an editor or proofreader. While translators have viewed the technological progress as a threat to their jobs, machine translation comes with some persistent issues, such as bias or inaccuracies stemming from insufficient context understanding and cultural nuances. Accordingly, the question of the future of human translation is more complex than it may initially appear. This paper presents the results of a pilot study on the perception of the future of the translation profession in the era of artificial intelligence.

Neural Machine Translation Between English And Bangla: A Philosophical Survey Observing Architectures And Performances

Neural Machine Translation (NMT) is a state of the art of machine translations that uses neural network models to translate text from one language to another. Unlike traditional machine translation methods, which rely on statistical models and rule-based systems, NMT leverages the power of deep learning, specifically using techniques such as recurrent neural networks (RNNs), long short-term memory networks (LSTMs), or more recently, transformers. Neural Machine Translation represents a significant dive forward in the field of automatic translation, leveraging the latest advancements in deep learning to deliver more accurate and natural translations. The progress in NMT has been remarkable, driven by advancements in model architectures, multilingual training, pretraining techniques, increased computational power, and the availability of vast multilingual datasets and improved evaluation metrics. These developments have collectively enhanced the quality, efficiency, and applicability of NMT systems across various languages and domains. In this article we will explore the technologies and performances of NMT between English and Bangla Language pair from its launching periods to present.

Efficient incremental training using a novel NMT-SMT hybrid framework for translation of low-resource languages.

The data-hungry statistical machine translation (SMT) and neural machine translation (NMT) models offer state-of-the-art results for languages with abundant data resources. However, extensive research is imperative to make these models perform equally well for low-resource languages. This paper proposes a novel approach to integrate the best features of the NMT and SMT systems for improved translation performance of low-resource English-Tamil language pair. The suboptimal NMT model trained with the small parallel corpus translates the monolingual corpus and selects only the best translations, to retrain itself in the next iteration. The proposed method employs the SMT phrase-pair table to determine the best translations, based on the maximum match between the words of the phrase-pair dictionary and each of the individual translations. This repeating cycle of translation and retraining generates a large quasi-parallel corpus, thus making the NMT model more powerful. SMT-integrated incremental training demonstrates a substantial difference in translation performance as compared to the existing approaches for incremental training. The model is strengthened further by adopting a beam search decoding strategy to produce k best possible translations for each input sentence. Empirical findings prove that the proposed model with BLEU scores of 19.56 and 23.49 outperforms the baseline NMT with scores 11.06 and 17.06 for Eng-to-Tam and Tam-to-Eng translations, respectively. METEOR score evaluation further corroborates these results, proving the supremacy of the proposed model.

A Comparative Study on the Quality of English-Chinese Translation of Legal Texts Between ChatGPT and Neural Machine Translation Systems

A Comparative Study on the Quality of English-Chinese Translation of Legal Texts Between ChatGPT and Neural Machine Translation Systems

Human versus Neural Machine Translation Creativity: A Study on Manipulated MWEs in Literature

In the digital era, the (r)evolution of neural machine translation (NMT) has reshaped both the market and translators’ workflow. However, the adoption of this technology has not fully reached the creative field of literary translation. Against this background, this study aims to explore to what extent NMT systems can be used to translate the creative challenges posed by idioms, specifically manipulated multiword expressions (MWEs) found in literary texts. To carry out this pilot study, five manipulated MWEs were selected from a fantasy novel and machine-translated (English > Spanish) by four NMT systems (DeepL, Google Translate, Bing Translator, and Reverso). Then, each NMT output as well as a human translation are assessed by six professional literary translators by using a human evaluation sheet. Based on these results, the creativity obtained in each translation method was calculated. Despite the satisfactory performance of both DeepL and Google Translate, HT creativity was highly superior in almost all manipulated MWEs. To the best of our knowledge, this paper not only contributes to the ongoing study of NMT applied to literature, but it is also one of the few studies that delve into the almost unexplored field of assessing creativity in neural machine-translated MWEs.

Language-attached Transfer Restrictions in Neural Machine Translation: An Analysis of Tao Te Ching

This study focuses on the language-attached transfer restrictions in Chinese to English neural machine translation (NMT) of Tao Te Ching, an ancient Chinese philosophical text, which aims to identify and analyze the specific challenges and limitations encountered by NMT systems when translating linguistic features that are unique to the source language and how these challenges impact the accuracy and quality of the translated text in English. It contributes to the understanding of the complexities involved in machine translation of ancient Chinese texts and proposes strategies to mitigate the identified transfer restrictions, ultimately aiming to bridge the gap between machine translation capabilities and the richness of Chinese philosophical literature.

An analysis of Google Translate and DeepL translation of source text typographical errors in the economic and legal fields

Training neural machine translation systems with noisy data has been shown to improve robustness (Heigold et al., 2018). The objective of the present study is to test Google Translate and DeepL performance in the detection and correction of typographical errors, by introducing 1,820 source text typos found in a previous work on specialised Spanish-English dictionaries (Rodríguez-Rubio & Fernández-Quesada, 2020a, 2020b; Rodríguez-Rubio Mediavilla, 2021). Typos were introduced in isolation and also in co-text. Results showed that Google Translate clearly outperformed DeepL. Moreover, the repetition of the source typo was found to be the most frequent phenomenon in the machine translation output of both systems. By shedding light on the capacity of systems to deal with source text typographical errors, our study aims to provide a starting point for their refinement.

Scaling neural machine translation to 200 languages

The development of neural techniques has opened up new avenues for research in machine translation. Today, neural machine translation (NMT) systems can leverage highly multilingual capacities and even perform zero-shot translation, delivering promising results in terms of language coverage and quality. However, scaling quality NMT requires large volumes of parallel bilingual data, which are not equally available for the 7,000+ languages in the world1. Focusing on improving the translation qualities of a relatively small group of high-resource languages comes at the expense of directing research attention to low-resource languages, exacerbating digital inequities in the long run. To break this pattern, here we introduce No Language Left Behind—a single massively multilingual model that leverages transfer learning across languages. We developed a conditional computational model based on the Sparsely Gated Mixture of Experts architecture2–7, which we trained on data obtained with new mining techniques tailored for low-resource languages. Furthermore, we devised multiple architectural and training improvements to counteract overfitting while training on thousands of tasks. We evaluated the performance of our model over 40,000 translation directions using tools created specifically for this purpose—an automatic benchmark (FLORES-200), a human evaluation metric (XSTS) and a toxicity detector that covers every language in our model. Compared with the previous state-of-the-art models, our model achieves an average of 44% improvement in translation quality as measured by BLEU. By demonstrating how to scale NMT to 200 languages and making all contributions in this effort freely available for non-commercial use, our work lays important groundwork for the development of a universal translation system.

Large language models "ad referendum": How good are they at machine translation in the legal domain?

This study evaluates the machine translation (MT) quality of two state-of-the-art large language models (LLMs) against a traditional neural machine translation (NMT) system across four language pairs in the legal domain. It combines automatic evaluation metrics (AEMs) and human evaluation (HE) by professional translators to assess translation ranking, fluency and adequacy. The results indicate that while Google Translate generally outperforms LLMs in AEMs, human evaluators rate LLMs, especially GPT-4, comparably or slightly better in terms of producing contextually adequate and fluent translations. This discrepancy suggests LLMs' potential in handling specialized legal terminology and context, highlighting the importance of human evaluation methods in assessing MT quality. The study underscores the evolving capabilities of LLMs in specialized domains and calls for reevaluation of traditional AEMs to better capture the nuances of LLM-generated translations.

A survey of context in neural machine translation and its evaluation

Abstract The question of context in neural machine translation often focuses on topics related to document-level translation or intersentential context. However, there is a wide range of other aspects that can be considered under the umbrella of context. In this work, we survey ways that researchers have incorporated context into neural machine translation systems and the evaluation thereof. This includes building translation systems that operate at the paragraph level or the document level or ones that translate at the sentence level but incorporate information from other sentences. We also consider how issues like terminology consistency, anaphora, and world knowledge or external information can be considered as types of context relevant to the task of machine translation and its evaluation. Closely tied to these topics is the question of how to best evaluate machine translation output in a way that is sensitive to the contexts in which it appears. To this end, we discuss work on incorporating context into both human and automatic evaluations of machine translation quality. Furthermore, we also discuss recent experiments in the field as they relate to the use of large language models in translation and evaluation. We conclude with a view of the future of machine translation, where we expect to see issues of context continue to come to the forefront.

Advancements in Neural Machine Translation: Methodological Innovations and Empirical Insights for Cross-Linguistic Discourse Preservation

Abstract: Natural Language Processing (NLP), in the form recognizable today, really began to take hold in the 1980s, when machine learning helped propel it to soaring heights. However, due to a lack of processing power, machine learning, and to an extent, NLP, started slowing down in innovation and ideas and had almost ground to a relative halt, until the last decade, when a sudden increase in both productivity and interest in the machine learning helped increase the amount of knowledge in the space itself. This review provides several different case studies using different methodologies. The first paper was a deep analysis on how researchers were able to use Tesseract and Google Vision in tandem with automatic data mining methods to enrich the Cherokee language database in order to preserve it from extinction. The second paper takes a query translation-based approach toward translating English to Indian languages and utilizes a Multilingual Cross-Language Information Retrieval (MLCIR) system with tools such as Part of Speech Tagger (POST), Stop-Word, and Porter Stemmer. The third paper presents CoVe, which transfers knowledge from machine translation to improve performance on NLP tasks like sentiment analysis and question answering by using contextualized word vectors along with word embeddings, achieving new state-of-the-art results on some datasets. The fourth paper aims to translate English to Pakistan Sign Language (PSL) and also uses POST and goes through dependency analysis, sentence classification, and PSL using PLS trees. The fifth paper uses a Multilingual Neural Machine Translation (NMT) system for LowResource languages and incorporates two main models: a recurrent NMT and a transformer NMT. The sixth paper analyzes how a fine-tuned transformer model seems to work better than transformer models trained from scratch on high-resource languages, while vice-versa seems to occur for low-resource languages. The seventh paper adds to this by talking about how multilingual translation seems to work better than a back-translation model. Given the diverse array of approaches that could be used, we aim to identify the most efficient and correct methodology for future researchers to use in their work, based on the papers in this literature review.

Ainu–Japanese Bi-directional Neural Machine Translation: A Step Towards Linguistic Preservation of Ainu, An Under-Resourced Indigenous Language in Japan

This study presents a groundbreaking approach to preserving the Ainu language, recognized as critically endangered by UNESCO, by developing a bi-directional neural machine translation (MT) system between Ainu and Japanese. Utilizing the Marian MT framework, known for its effectiveness with resource-scarce languages, the research aims to overcome the linguistic complexities inherent in Ainu's polysynthetic structure. The paper delineates a comprehensive methodology encompassing data collection from diverse Ainu text sources, meticulous preprocessing, and the deployment of neural MT models, culminating in the achievement of significant SacreBLEU scores that underscore the models' translation accuracy. The findings illustrate the potential of advanced MT technology to facilitate linguistic preservation and educational endeavors, advocating for integrating such technologies in safeguarding endangered languages. This research not only underscores the critical role of MT in bridging language divides but also sets a precedent for employing computational linguistics to preserve cultural and linguistic heritage.

Comparison of Translation Quality between Large Language Models and Neural Machine Translation Systems: A Case Study of Chinese-English Language Pair

A number of Neural Machine Translation (NMT) systems have already demonstrated their strength to undertake various translation tasks which are not too demanding. However, the incredible advancement of AI technology in recent years has endowed Large Language Models (LLMs) with great potential, so we may imagine that they may even do better than NMT working as translators. To figure out whether LLMs have better performance than NMT in translation, and how genres and translation directions may influence translation quality, this article chose two LLMs, namely, ChatGPT 3.5 and Wenxin Yiyan, or ERNIE Bot 3.5, and one NMT system, namely, DeepL, to test and compare their performance in Chinese-English translation, employing a quantitative method including BLEU scoring and SPSS analysis. The results show that there is no significant improvement in these LLMs’ translation quality compared with the NMT system, and all the chosen systems tend to perform better in non-literary translation than in literary translation and produce TTs of higher quality in Chinese-English translation than in English-Chinese translation

A Study for Enhancing Low-resource Thai-Myanmar-English Neural Machine Translation

Several methodologies have recently been proposed to enhance the performance of low-resource Neural Machine Translation (NMT). However, these techniques have yet to be explored thoroughly in the low-resource Thai and Myanmar languages. Therefore, we first applied augmentation techniques such as SwitchOut and Ciphertext Based Data Augmentation (CipherDAug) to improve NMT performance in these languages. Second, we enhanced the NMT performance by fine-tuning the pre-trained Multilingual Denoising BART model (mBART), where BART denotes Bidirectional and Auto-Regressive Transformer. We implemented three NMT systems: namely, Transformer+SwitchOut, Multi-Source Transformer+CipherDAug, and fine-tuned mBART in the bidirectional translations of Thai-English-Myanmar language pairs from the ASEAN-MT corpus. Experimental results showed that Multi-Source Transformer+CipherDAug significantly improved Bilingual Evaluation Understudy (BLEU), Character n-gram F-score (ChrF) , and Translation Error Rate (TER) scores over the first baseline Transformer and second baseline Edit-Based Transformer. The model achieved notable BLEU scores: 37.9 (English-to-Thai), 42.7 (Thai-to-English), 28.9 (English-to-Myanmar), 31.2 (Myanmar-to-English), 25.3 (Thai-to-Myanmar), and 25.5 (Myanmar-to-Thai). The fine-tuned mBART model also considerably outperformed the two baselines, except for the Myanmar-to-English pair. SwitchOut improved over the second baseline in all pairs and performed similarly to the first baseline in most cases. Last, we performed detailed analyses verifying that the CipherDAug and mBART models potentially facilitate improving low-resource NMT performance in Thai and Myanmar languages.

Assessing the Impact of Static, Contextual and Character Embeddings for Arabic Machine Translation

Word embeddings/representations are an important component of Natural Language Processing (NLP) tasks. Most Neural Machine Translation (NMT) systems that use such representations disregard word morphology by assigning a unique vector to each unique word in the used vocabulary and thus cannot handle Out-Of-Vocabulary (OOV) words. In some languages, such as Arabic, the meaning of words is associated with the meaning of the individual characters that constitute them, as these characters embody internal information. In this study, a combination of character- and word- level models is used to determine the most effective approaches to semantically and morphologically representing affective Arabic words. Furthermore, this work examines the strategy of combining static, character and contextual word embeddings to obtain richer representations for the Arabic Machine Translation (MT) task. To the best of our knowledge, we are the first to investigate the combination of static word embeddings, contextual ones and character-level representation in Arabic MT. Furthermore, a Deep Learning (DL) architecture is employed on data preprocessed by various prominent preprocessing techniques. Various experiments were conducted and the findings indicate that the integration of various models for word embedding and character-level representation is feasible and more effective than the state-of-the-art Arabic MT systems.

English to Arabic Braille Neural Machine Translation Through Corpus Augmentation

In this paper we have shown the development of English to Arabic Braille Neural Machine Translation (NMT) System. For our experiments we have developed two NMT systems. The first was the baseline NMT system which was trained only on the English-Arabic parallel corpus whereas the second NMT system has some sub modules for handling syntax transfer of English to Arabic and translation/transliteration of English Named Entities into Arabic equivalents. Then the system used this code-mixed text to train the NMT model. The English-Arabic parallel corpus was taken from Opus parallel corpus repository. For preprocessing of the English text Stanford's Stanza NLP Library was used. The trained NMT models were evaluated using standard automatic MT evaluation metrics and their results were also corelated with human judgements. It was found that the corpus augmented NMT system performed better than the baseline NMT system.

Large Language Models are Good Translators

Machine translation, which uses computers to translate one language into another, is one of the most challenging tasks in artificial intelligence. During the last decade, neural machine translation (NMT), which builds translation models based on deep neural networks, has achieved significant improvement. However, NMT still faces several challenges. For example, the translation quality of an NMT system greatly depends on the amount of bilingual training data, which is expensive to acquire. Furthermore, it is difficult to incorporate external knowledge into an NMT system to obtain further improvement for a specific domain. Recently, large language models (LLMs) have demonstrated remarkable capabilities in language understanding and generation. This raises interesting questions about whether LLMs can be good translators and whether it is easy to adapt LLMs to new domains or to meet specific requirements. In this study, we hypothesized that LLMs can be adapted to perform translation by using prompts or fine-tuning and these adapted LLMs would outperform the conventional NMT model in four aspects: translation quality, interactive ability, knowledge incorporation ability, and domain adaptation. We compared GPT-4 and Google Translate, the representative LLM and NMT models, respectively, on the WMT 2019 (Fourth conference on machine translation) dataset. Experimental results showed that GPT-4 outperformed Google Translate in the above four aspects by exploiting appropriate prompts. Further experiments on Llama, an open-source LLM developed by Meta, showed that the translation quality of LLMs can be further improved by fine-tuning on limited language-related bilingual corpus, demonstrating strong adaptation abilities of LLMs.

Machine vs Human Translation of Formal Neologisms in Literature:

This article compares the output of three neural machine translation systems (Google Translate, DeepL, and Phrase TMS) and human translation (undergraduate level students, English into Spanish). It focuses on five formal neologisms extracted from literary texts, thus considering creativity, and technology adoption and training.