Neural Machine Translation Systems Research Articles

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.

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.

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.

Neural machine translation in AVT teaching in China: An in-depth analysis from the readability perspective

As audiovisual translation (AVT) becomes more complex and diverse, the need for advanced machine learning techniques has been increasing sharply, driving the widespread adoption of neural machine translation (NMT) technology in the field. This study contributes to the literature by evaluating the performance of NMT technology in AVT teaching. Based on readability theory, we constructed an evaluation framework with 12 indicators, built comparable corpora consisting of human and post-edited subtitle translations of corporate videos, and used them to examine the performance of four online NMT systems (Google Translate, Baidu Translate, Bing Translator, and Youdao Translate) in AVT teaching. Our statistical analyses and case studies show that Google Translate outperforms the other three platforms in all the readability tests, and it can enhance the readability of post-edited subtitles at five levels (word, syntax, textbase, situation model, genre and rhetorical). The performance of the other three platforms varies across different tests. Concrete examples are provided to substantiate the statistical analyses. Our study adds value to existing research both by examining the application and performance of NMT in AVT teaching and by suggesting potential directions for the refinement of current NMT systems.

Investigating syntactic priming cumulative effects in MT-human interaction.

A question that deserves to be explored is whether the interaction between English language learners and the popular Google neural machine translation (GNMT) system could result in learning and increased production of a challenging syntactic structure in English that differs in word order between speakers first language and second language. In this paper, we shed light on this issue by testing 30 Brazilian Portuguese L2 English speakers in order to investigate whether they tend to describe an image in English with a relation of possession between nouns using a prepositional noun phrase (e.g. the cover of the book is red) or re-use the alternative syntactic structure seen in the output of the GNMT (e.g. the book cover is red), thus manifesting syntactic priming effects. In addition, we tested whether, after continuous exposure to the challenging L2 structure through Google Translate output, speakers would adapt to that structure in the course of the experiment, thus manifesting syntactic priming cumulative effects. Our results show a robust syntactic priming effect as well as a robust cumulative effect. These results suggest that GNMT can influence L2 English learners linguistic behaviour and that L2 English learners unconsciously learn from the GNMT with continuous exposure to its output.

Integrating post-editing into the subtitling classroom: what do subtitlers-to-be think?

In today’s professional landscapes, new technologies have altered media localization workflows as much as practitioners’ workstations and habits. A more comprehensive integration of automation tools, including (neural) machine translation systems, has been ushered in by the proliferation of cloud ecosystems. In a further technological drive in the production of subtitle projects, systems now integrate automatic speech recognition and can machine translate subtitles from pre-spotted templates. The rise of post-editors in media localization, specifically in subtitling, has been a reality for some time now, triggering the need for up-to-date training methods and academic curricula. It is against this backdrop that this article seeks to examine the perception of post-editing among trainees in subtitling. A total of four teaching experiences, conceived as practical experiments in interlingual subtitle post-editing (English into Spanish), involving postgraduate students from both Spain and the United Kingdom, are described here. The sample comprised 36 master’s-level students enrolled in translator training programmes that have a focus on audiovisual translation. A mixed-methods approach was adopted for this study; after each experience, the feedback collated through online questionnaires has proved paramount to understanding the participants’ opinions about post-editing in the subtitling classroom. Interestingly, most of the respondents believe that subtitle post-editing training should feature more prominently in translation curricula even though they have voiced their reluctance to undertake post-editing work professionally.

Translation Performance from the User’s Perspective of Large Language Models and Neural Machine Translation Systems

The rapid global expansion of ChatGPT, which plays a crucial role in interactive knowledge sharing and translation, underscores the importance of comparative performance assessments in artificial intelligence (AI) technology. This study concentrated on this crucial issue by exploring and contrasting the translation performances of large language models (LLMs) and neural machine translation (NMT) systems. For this aim, the APIs of Google Translate, Microsoft Translator, and OpenAI’s ChatGPT were utilized, leveraging parallel corpora from the Workshop on Machine Translation (WMT) 2018 and 2020 benchmarks. By applying recognized evaluation metrics such as BLEU, chrF, and TER, a comprehensive performance analysis across a variety of language pairs, translation directions, and reference token sizes was conducted. The findings reveal that while Google Translate and Microsoft Translator generally surpass ChatGPT in terms of their BLEU, chrF, and TER scores, ChatGPT exhibits superior performance in specific language pairs. Translations from non-English to English consistently yielded better results across all three systems compared with translations from English to non-English. Significantly, an improvement in translation system performance was observed as the token size increased, hinting at the potential benefits of training models on larger token sizes.

Neural machine translation systems for English to Khasi: A case study of an Austroasiatic language

Neural machine translation has predominantly outperformed previous machine translation models primarily for resourceful languages. However, very little work has been reported for resource-constrained languages such as Khasi. The Khasi language belongs to the Mon-Khmer branch of the Austroasiatic language family and is spoken primarily in the state of Meghalaya in India. Although performing neural machine translation for the under-resourced Khasi language is difficult, we build a substantial parallel corpus of English–Khasi. We apply three segmentation methods in the datasets for our experiments: untokenized, tokenized and a subword BPE (Byte Pair Encoding). Experiments are carried out on this dataset with different aspects of neural machine translation systems using cutting-edge architectures such as LSTM (Long Short Term Memory), GRU (Gated Recurrent Unit) and a transformer based model for the English–Khasi language pair. We also carry out experiments by adapting the transfer learning approach using English-Vietnamese as the parent language pair and English-Khasi as the child language pair. This work reports a quantitative and qualitative analysis of several models based on architectural and data segmentation methodologies. The experimental findings show that the model adapted using the transfer learning approach achieved a reasonable improvement in BLEU scores with the highest being 58.1 BLEU on similar domains and 17.7 BLEU for the general domain outscoring the other models for the same language pair. Qualitative analysis is carried out focusing on the morphological inflections of gender identification in the translated output.

North Korean Neural Machine Translation through South Korean Resources

South and North Korea both use the Korean language. However, Korean natural language processing (NLP) research has mostly focused on South Korean language. Therefore, existing NLP systems in the Korean language, such as neural machine translation (NMT) systems, cannot properly process North Korean inputs. Training a model using North Korean data is the most straightforward approach to solving this problem, but the data to train NMT models are insufficient. To solve this problem, we constructed a parallel corpus to develop a North Korean NMT model using a comparable corpus. We manually aligned parallel sentences to create evaluation data and automatically aligned the remaining sentences to create training data. We trained a North Korean NMT model using our North Korean parallel data and improved North Korean translation quality using South Korean resources such as parallel data and a pre-trained model. In addition, we propose Korean-specific pre-processing methods, character tokenization, and phoneme decomposition to use the South Korean resources more efficiently. We demonstrate that the phoneme decomposition consistently improves the North Korean translation accuracy compared to other pre-processing methods.

An empirical analysis on statistical and neural machine translation system for English to Mizo language

An empirical analysis on statistical and neural machine translation system for English to Mizo language

Towards better Chinese-centric neural machine translation for low-resource languages

The last decade has witnessed enormous improvements in science and technology, stimulating the growing demand for economic and cultural exchanges in various countries. Building a neural machine translation (NMT) system has become an urgent trend, especially in the low-resource setting. However, recent work tends to study NMT systems for low-resource languages centered on English, while a few studies focus on low-resource NMT systems centered on other languages such as Chinese. To achieve this, the low-resource multilingual translation challenge of the 2021 iFLYTEK AI Developer Competition provides the Chinese-centric multilingual low-resource NMT tasks, where participants are required to build NMT systems based on the provided low-resource samples. In this paper, we present the competition-winning system that leverages monolingual word embeddings data enhancement, bilingual curriculum learning, and contrastive re-ranking. In addition, a new Incomplete-Trust (In-trust) loss function is proposed to replace the traditional cross-entropy loss when training. The extensive experimental results demonstrate that the implementation of these ideas leads to better performance than other state-of-the-art methods. All the experimental codes are released at: https://github.com/WENGSYX/Low-resource-text-translation.

Algorithmic Translation Correction Mechanisms: An End-to-end Algorithmic Implementation of English-Chinese Machine Translation

INTRODUCTION: Machine translation is a modern natural language processing research field with important scientific and practical significance. In practice, the variation of languages, the limitation of semantic knowledge, and the lack of parallel language resources limit the development of machine translation.
 OBJECTIVES: This paper aims to avoid duplicating neural networks during the learning process and improve the ability to generalize complex neural network machine translation models with limited resources.
 METHODS: Textual material in the source language was studied, and a suitable textual material representation model was used to express complex, high-level, and abstract semantic information. Then, a more efficient neural network machine translation integration model was developed based on the control of written data and algorithms.
 RESULTS: Data mining must be applied to complex neural network machine translation systems based on transfer learning to standardize finite neural network models.
 CONCLUSION: Neural network-based embedded machine translation systems based on migration training require a small number of labelled samples to improve the system's permeability. However, this adaptive migration learning region approach can easily lead to over-learning problems in neural network machine translation models, thus avoiding excessive correspondences during the learning process and improving the generalization ability of the translation model with limited neural network resources.

Automatic Resource Augmentation for Machine Translation in Low Resource Language: EnIndic Corpus

Parallel corpus is the primary ingredient of machine translation. It is required to train the statistical machine translation (SMT) and neural machine translation (NMT) systems. There is a lack of good quality parallel corpus for Hindi to English. Comparable corpora for a given language pair are comparatively easy to find, but this cannot be used directly in SMT or NMT systems. As a result, we generate a parallel corpus from the comparable corpus. For this purpose, the sentences (which are translations of each other) are mined from the comparable corpus to prepare the parallel corpus. The proposed algorithm uses the length of the sentence and word translation model to align sentence pairs that are translations of each other. Then, the sentence pairs that are poor translations of each other (measured by a similarity score based on IBM model 1 translation probability) are filtered out. We apply this algorithm to comparable corpora, which are crawled from speeches of the President and Vice-President of India, and mined parallel corpora out of them. The prepared parallel corpus contains good quality aligned sentences (with 96.338% f-score). Subsequently, incorrect sentence pairs are filtered out manually to make the corpus in qualitative practical use. Finally, we gather various sentences from different sources to prepare the EnIndic corpus, which comprises 1,656,207 English-Hindi sentence pairs (miscellaneous domain). We have deployed this prepared largest English-Hindi parallel corpus at https://github.com/debajyoty/EnIndic.git and the source code at https://github.com/debajyoty/EnIndicSourceCode.git.

Neural machine translation and human translation

Abstract By comparing the Chinese, English and French versions of “Exhortations of Learning” and “On Building a Human Community with a Shared Future,” translated by human translators and the neural machine translation systems respectively, this essay finds out that human translators have addressed the political and ideological factors more tactfully while the working mechanism of the neural machine translation system lacks the formers’ judgment, consideration, flexibility and subjectivity. Moreover, unlike human translators, the neural machine system is not capable of activities such as summarizing the source texts, making comments or annotating. But on the other hand, the neural machine translation system has the advantages of its own. Not affected by bias like human translators, it could perform the translation faster and with a rather objective stance. All in all, there is still a long way to go before it can reveal the political and ideological factors in ways as human translators can achieve.

The creativity and limitations of AI neural machine translation

Abstract This study examines the performance of the neural machine translation system DeepL in translating Shakespeare’s plays Coriolanus and The Merchant of Venice. The aim here is to explore the strengths and limitations of an AI-based English-Chinese translation of literary texts. Adopting a corpus-based approach, the study investigates the accuracy and fluency rates, the linguistic features, and the use of various methods of translation in the Chinese translations of Shakespeare’s plays conducted via DeepL. It compares these to the translations by Liang Shiqiu, a well-known Chinese translator. The study finds that DeepL performs well in translating these works, with an accuracy and fluency rate of above 80% in sampled texts, showing the potential of the use of neural machine translation in translating literary texts across distant languages. Our research further reveals that the DeepL translations exhibit a certain degree of creativity in their use of translation methods such as addition, explicitation, conversion and shift of perspective, and in the use of Chinese sentence-final modal particles, as well as Chinese modal verbs. On the other hand, the system appears to be limited in that a certain amount of translation errors are present, including literal translations.

Grammatical Error Correction: A Survey of the State of the Art

Abstract Grammatical Error Correction (GEC) is the task of automatically detecting and correcting errors in text. The task not only includes the correction of grammatical errors, such as missing prepositions and mismatched subject–verb agreement, but also orthographic and semantic errors, such as misspellings and word choice errors, respectively. The field has seen significant progress in the last decade, motivated in part by a series of five shared tasks, which drove the development of rule-based methods, statistical classifiers, statistical machine translation, and finally neural machine translation systems, which represent the current dominant state of the art. In this survey paper, we condense the field into a single article and first outline some of the linguistic challenges of the task, introduce the most popular datasets that are available to researchers (for both English and other languages), and summarize the various methods and techniques that have been developed with a particular focus on artificial error generation. We next describe the many different approaches to evaluation as well as concerns surrounding metric reliability, especially in relation to subjective human judgments, before concluding with an overview of recent progress and suggestions for future work and remaining challenges.We hope that this survey will serve as a comprehensive resource for researchers who are new to the field or who want to be kept apprised of recent developments.

Prompting Neural Machine Translation with Translation Memories

Improving machine translation (MT) systems with translation memories (TMs) is of great interest to practitioners in the MT community. However, previous approaches require either a significant update of the model architecture and/or additional training efforts to make the models well-behaved when TMs are taken as additional input. In this paper, we present a simple but effective method to introduce TMs into neural machine translation (NMT) systems. Specifically, we treat TMs as prompts to the NMT model at test time, but leave the training process unchanged. The result is a slight update of an existing NMT system, which can be implemented in a few hours by anyone who is familiar with NMT. Experimental results on several datasets demonstrate that our system significantly outperforms strong baselines.