Machine Translation Techniques Research Articles

Enhancing Chinese–Braille translation: A two-part approach with token prediction and segmentation labeling

Visually assistive systems for the visually impaired play a pivotal role in enhancing the quality of life for the visually impaired. Assistive technologies for the visually impaired have undergone a remarkable transformation with the advent of deep learning and sophisticated assistive devices. In particular, the paper utilizes the latest machine translation models and techniques to accomplish the Chinese–Braille translation task, providing convenience for visually impaired individuals. The Traditional end-to-end Chinese–Braille translation approach incorporates Braille dots and Braille word segmentation symbols as tokens within the model’s vocabulary. However, our findings reveal that Braille word segmentation is significantly more complex than Braille dot prediction. The paper proposes a novel Two-Part Loss (TPL) method that treats these tasks distinctly, leading to significant accuracy improvements. To enhance translation performance further, we introduce a BERT-Enhanced Segmentation Transformer (BEST) method. BEST leverages knowledge distillation techniques to transfer knowledge from a pre-trained BERT model to the translate model, mitigating its limitations in word segmentation. Additionally, soft label distillation is employed to improve overall efficacy further. The TPL approach achieves an average BLEU score improvement of 1.16 and 5.42 for Transformer and GPT models on four datasets, respectively. In addition, The work presents a two-stage deep learning-based translation approach that outperforms traditional multi-step and end-to-end methods. The proposed two-stage translation method achieves an average BLEU score improvement of 0.85 across four datasets.

Neural Machine Translation for Low-Resource Languages from a Chinese-centric Perspective: A Survey

Machine translation—the automatic transformation of one natural language (source language) into another (target language) through computational means—occupies a central role in computational linguistics and stands as a cornerstone of research within the field of Natural Language Processing (NLP). In recent years, the prominence of Neural Machine Translation (NMT) has grown exponentially, offering an advanced framework for machine translation research. It is noted for its superior translation performance, especially when tackling the challenges posed by low-resource language pairs that suffer from a limited corpus of data resources. This article offers an exhaustive exploration of the historical trajectory and advancements in NMT, accompanied by an analysis of the underlying foundational concepts. It subsequently provides a concise demarcation of the unique characteristics associated with low-resource languages and presents a succinct review of pertinent translation models and their applications, specifically within the context of languages with low-resources. Moreover, this article delves deeply into machine translation techniques, highlighting approaches tailored for Chinese-centric low-resource languages. Ultimately, it anticipates upcoming research directions in the realm of low-resource language translation.

Multilingual Neural Machine Translation for Indic to Indic Languages

The method of translation from one language to another without human intervention is known as Machine Translation (MT). Multilingual neural machine translation (MNMT) is a technique for MT that builds a single model for multiple languages. It is preferred over other approaches, since it decreases training time and improves translation in low-resource contexts, i.e., for languages that have insufficient corpus. However, good-quality MT models are yet to be built for many scenarios such as for Indic-to-Indic Languages (IL-IL). Hence, this article is an attempt to address and develop the baseline models for low-resource languages i.e., IL-IL (for 11 Indic Languages (ILs)) in a multilingual environment. The models are built on the Samanantar corpus and analyzed on the Flores-200 corpus. All the models are evaluated using standard evaluation metrics i.e., Bilingual Evaluation Understudy (BLEU) score (with the range of 0 to 100). This article examines the effect of the grouping of related languages, namely, East Indo-Aryan (EI), Dravidian (DR), and West Indo-Aryan (WI) on the MNMT model. From the experiments, the results reveal that related language grouping is beneficial for the WI group only while it is detrimental for the EI group and it shows an inconclusive effect on the DR group. The role of pivot-based MNMT models in enhancing translation quality is also investigated in this article. Owing to the presence of large good-quality corpora from English (EN) to ILs, MNMT IL-IL models using EN as a pivot are built and examined. To achieve this, English-Indic Language (EN-IL) models are developed with and without the usage of related languages. Results show that the use of related language grouping is advantageous specifically for EN to ILs. Thus, related language groups are used for the development of pivot MNMT models. It is also observed that the usage of pivot models greatly improves MNMT baselines. Furthermore, the effect of transliteration on ILs is also analyzed in this article. To explore transliteration, the best MNMT models from the previous approaches (in most of cases pivot model using related groups) are determined and built on corpus transliterated from the corresponding scripts to a modified Indian language Transliteration script (ITRANS). The outcome of the experiments indicates that transliteration helps the models built for lexically rich languages, with the best increment of BLEU scores observed in Malayalam (ML) and Tamil (TA), i.e., 6.74 and 4.72, respectively. The BLEU score using transliteration models ranges from 7.03 to 24.29. The best model obtained is the Punjabi (PA)-Hindi (HI) language pair trained on PA-WI transliterated corpus.

Construction of Algorithm for English Learners to Read Foreign Literature Based on Machine Translation Technology

This study focuses on the development of an algorithm aimed at assisting English learners in comprehending foreign literature through the utilization of machine translation technology. With the growing importance of multilingual proficiency in a globalized world, the ability to read and understand literature in foreign languages is increasingly valued. However, language barriers often hinder learners' comprehension and appreciation of such texts. To address this challenge, our research endeavors to construct an algorithm that leverages machine translation techniques to facilitate the reading process for English learners. By integrating advanced translation algorithms and natural language processing methods, the proposed system aims to provide accurate and contextually relevant translations of foreign literature into English. Additionally, the algorithm will incorporate features tailored to the needs of English learners, such as vocabulary assistance, grammatical explanations, and cultural context annotations, to enhance their reading experience and comprehension levels. Through rigorous experimentation and evaluation, the effectiveness and usability of the algorithm will be assessed, with the ultimate goal of empowering English learners to engage more deeply with foreign literature and broaden their linguistic and cultural horizons.

NLP-reliant Neural Machine Translation techniques used in smart city applications

For smart city applications, Neural Machine Translation (NMT) methods based on Natural Language Processing (NLP) are crucial as they facilitate information sharing and communication among diverse populations. NLP techniques are used in many domains related to smart cities, such as development and research, business, industries, media, healthcare, and residences and communities. The majority of people in India communicate using their regional languages. The majority of applications used by users in smart cities will mostly accept English as input. These people will be able to interact with these smart city devices in their native tongues more effectively with the help of effective machine translation. Just 10% of Indians use English as their primary language of communication; there are 22 official regional languages in India. So, there is requirement of better machine translation using Natural language processing (NLP). Natural language processing for Indian regional languages has a very long way to go until it surpassing the abilities of existing rich NLP applications and techniques for English language. Machine Translation is technique of Natural Language Processing (NLP) which provides better inter-lingual communication. For low resourced Indian languages effective machine translation systems became important for establishing proper communication. Machine Transliteration is a technique to convert source language into target language using machine. The developed system takes English language as input and then applies machine translation techniques to translate the source language into multiple languages using trained RNN model and multi-lingual search model which search the input word across all the datasets and generate the output into other Indian languages such as Hindi, Tamil. Our approach achieves top performance for English-Hindi language pair and comparable results for other cases.

Comparison and analysis of two methods for improving the accuracy of OpenNMT in literary and vernacular Chinese translation

As machine translation advances, challenges persist in achieving high accuracy when translating between Literary and Vernacular Chinese. Literary Chinese is known for its concise writing style, often characterized by monosyllabic words. In contrast, Vernacular Chinese incorporates more polysyllabic words. This study utilizes the OpenNMT system to address these challenges and employs different Classical Chinese word segmentation tools to train 2-layer Long Short-Term Memory and Transformer models. These models are then compared and analyzed to measure the improvement in precision. The research findings reveal that adopting a character-level-based word segmentation method for Classical Chinese, coupled with training the Transformer model using OpenNMT, significantly enhances precision. This outcome validates the current observation that existing Classical Chinese word segmentation methods lack sufficient accuracy, consequently impacting the quality of translations between Literary and Vernacular Chinese. By exploring and investigating these approaches, this study contributes to advancing machine translation techniques for improving accuracy in rendering Literary and Vernacular Chinese translations.

Exploring Web-Based Translation Resources Applied to Hindi-English Cross-Lingual Information Retrieval

Internet users perceive a multilingual web but are unfamiliar with it due to communication in their regional language called Cross-Lingual Information Retrieval (CLIR). In CLIR, a translation technique is used to translate the user queries into the target document’s language. Conventional translation techniques are based on either a manual dictionary or a parallel corpus, whereas the trending Statistical Machine Translation (SMT) and Neural Machine Translation (NMT) techniques are trained on a parallel corpus. NMT is not so mature for Hindi-English translation, according to the literature, and SMT performs better than the NMT. SMT provides a static translation due to the limited vocabularies in the available parallel corpus. It may not provide the translations for missing or unseen words, whereas the web provides a dynamic interface where multiple users are updating information at the same time. The web may provide the translations for missing or unseen words, and therefore the web is effectively used for technically developed languages like English, German, Spanish, Russian, and Chinese. In this article, different web resources such as Wikipedia, Hindi WordNet and Indo WordNet, ConceptNet, and online dictionary based translation techniques are proposed and applied to Hindi-English CLIR. Wikipedia-based translation approach incorporates three modules—exactly matched, partially matched, and disambiguation—to address the issues of wrong inter-wiki links, partially matched terms, and ambiguous articles. Hindi WordNet and Indo WorNet attribute “English synset” and ConceptNet attributes “Related term” & “Synonymy” are used for obtaining translations. Further, WordNet path similarity is used to disambiguate translations. Various online dictionaries are available that return multiple relevant and irrelevant translations. The proposed approaches are compared to the SMT where the Wikipedia-based approach achieves approximately similar mean average precision to SMT.

Intelligent Translation System Aiding High-Quality Writing in English in the Age of the Internet

Abstract This study focuses on applying intelligent translation systems in assisting high-quality English writing in the Internet era. The study analyzes statistical machine translation techniques, especially N-gram language modeling and word alignment techniques, and their crucial role in translation quality improvement. In English writing, the intelligent translation system significantly improves the quality of students’ Writing through word block translation. By analyzing 320 students, the mean value of self-efficacy in writing skills of students in the high-quality writing group was 3.78, significantly higher than that of the low-quality group, which was 2.82. After the experiment, 0.57 students indicated that they would improve their English writing vocabulary with the aid of the Intelligent Translation System, which showed the potential of the Intelligent Translation System to enhance students’ interest in and autonomy in Writing. Average distribution analysis shows that word block usage positively correlates with writing performance, with an R Square value of 0.6726. The intelligent translation system improves students’ English writing and enhances their self-efficacy, which is of great significance to English teaching.

Testing of detection tools for AI-generated text

Recent advances in generative pre-trained transformer large language models have emphasised the potential risks of unfair use of artificial intelligence (AI) generated content in an academic environment and intensified efforts in searching for solutions to detect such content. The paper examines the general functionality of detection tools for AI-generated text and evaluates them based on accuracy and error type analysis. Specifically, the study seeks to answer research questions about whether existing detection tools can reliably differentiate between human-written text and ChatGPT-generated text, and whether machine translation and content obfuscation techniques affect the detection of AI-generated text. The research covers 12 publicly available tools and two commercial systems (Turnitin and PlagiarismCheck) that are widely used in the academic setting. The researchers conclude that the available detection tools are neither accurate nor reliable and have a main bias towards classifying the output as human-written rather than detecting AI-generated text. Furthermore, content obfuscation techniques significantly worsen the performance of tools. The study makes several significant contributions. First, it summarises up-to-date similar scientific and non-scientific efforts in the field. Second, it presents the result of one of the most comprehensive tests conducted so far, based on a rigorous research methodology, an original document set, and a broad coverage of tools. Third, it discusses the implications and drawbacks of using detection tools for AI-generated text in academic settings.

LoGenText-Plus : Improving Neural Machine Translation Based Logging Texts Generation with Syntactic Templates

Developers insert logging statements in the source code to collect important runtime information about software systems. The textual descriptions in logging statements (i.e., logging texts) are printed during system executions and exposed to multiple stakeholders including developers, operators, users, and regulatory authorities. Writing proper logging texts is an important but often challenging task for developers. Prior studies find that developers spend significant efforts modifying their logging texts. However, despite extensive research on automated logging suggestions, research on suggesting logging texts rarely exists. To fill this knowledge gap, we first propose LoGenText (initially reported in our conference paper), an automated approach that uses neural machine translation (NMT) models to generate logging texts by translating the related source code into short textual descriptions. LoGenText takes the preceding source code of a logging text as the input and considers other context information, such as the location of the logging statement, to automatically generate the logging text. LoGenText ’s evaluation on 10 open source projects indicates that the approach is promising for automatic logging text generation and significantly outperforms the state-of-the-art approach. Furthermore, we extend LoGenText to LoGenText-Plus by incorporating the syntactic templates of the logging texts. Different from LoGenText , LoGenText-Plus decomposes the logging text generation process into two stages. LoGenText-Plus first adopts an NMT model to generate the syntactic template of the target logging text. Then LoGenText-Plus feeds the source code and the generated template as the input to another NMT model for logging text generation. We also evaluate LoGenText-Plus on the same 10 projects and observe that it outperforms LoGenText on 9 of them. According to a human evaluation from developers’ perspectives, the logging texts generated by LoGenText-Plus have a higher quality than those generated by LoGenText and the prior baseline approach. By manually examining the generated logging texts, we then identify five aspects that can serve as guidance for writing or generating good logging texts. Our work is an important step toward the automated generation of logging statements, which can potentially save developers’ efforts and improve the quality of software logging. Our findings shed light on research opportunities that leverage advances in NMT techniques for automated generation and suggestion of logging statements.

Document AI: A Comparative Study of Transformer-Based, Graph-Based Models, and Convolutional Neural Networks for Document Layout Analysis

Document AI aims to automatically analyze documents by leveraging natural language processing and computer vision techniques. One of the major tasks of Document AI is document layout analysis, which structures document pages by interpreting the content and spatial relationships of layout, image, and text. This task can be image-centric, wherein the aim is to identify and label various regions such as authors and paragraphs, or text-centric, where the focus is on classifying individual words in a document. Although there are increasingly sophisticated methods for improving layout analysis, doubts remain about the extent to which their findings can be generalized to a broader context. Specifically, prior work developed systems based on very different architectures, such as transformer-based, graph-based, and CNNs. However, no work has mentioned the effectiveness of these models in a comparative analysis. Moreover, while language-independent Document AI models capable of knowledge transfer have been developed, it remains to be investigated to what degree they can effectively transfer knowledge. In this study, we aim to fill these gaps by conducting a comparative evaluation of state-of-the-art models in document layout analysis and investigating the potential of cross-lingual layout analysis by utilizing machine translation techniques.

HINDI TEXT CATEGORIZATION & TRANSLATION

The Hindi Text Translation and Categorization aims to develop a comprehensive system for translating and categorizing Hindi text content. This project addresses the growing need for effective language processing tools in the context of Hindi, one of the most widely spoken languages globally. The project consists of two primary components: translation and categorization. The translation module employs state-of-the-art machine translation techniques to provide accurate and contextually relevant translations between Hindi and other languages. This functionality is essential for breaking down language barriers and facilitating communication across diverse linguistic communities. The categorization module focuses on organizing and classifying Hindi text content into relevant categories or topics. Leveraging advanced natural language processing (NLP) algorithms, the system can analyze the semantic meaning of text and assign it to appropriate categories. This categorization enhances content management, information retrieval, and overall user experience, particularly in applications such as content recommendation systems and information filtering.

A Review of Machine Translation Techniques and Proposal to Automatic Translation of Videos

Translation of videos including propulsion technology videos has been one of the toughest jobs to do during the eLearning development process. We have tried it earlier by involving mostly manual work and found it to be tiresome. After the fast evolution of Machine learning and Natural language processing techniques, it is feasible now to do the translation involving and inculcating intelligent techniques in the process. We have reviewed the technologies and techniques and presenting it in this paper.

Machine Translation on Dravidian Languages

The Dravidian languages are spoken all over the world. Despite their distinctiveness, Dravidian languages haven’t gotten much attention because there aren’t enough resources to handle tasks like translation that require language technology. Since Dravidian languages are largely spoken in southern India, machine translation is necessary. For those who speak these regional languages, this would improve information creation and access. It can be challenging to translate between languages, particularly that of Dravidian, because of lexical divergence, ambiguity, and other, lexical, syntactic and semantic issues. This research looks into a number of machine translation models for different languages, conducts a thorough literature review on the various machine translation techniques from earlier studies, and analyses their methodology. The major objective of this research is to evaluate the viability and effectiveness of a machine translation process for Dravidian languages.

Localization of Terms Associated with the Covid-19 Pandemic from English to Arabic: A Study of Linguistic Means and Machine Translation Techniques

The emergency conditions experienced by the world during the COVID-19 pandemic have led to radical changes in both the lexicographic and semantic levels of the Arabic language. As with other languages around the world, Arabic had to keep up with the rapid development and massive flow of information and to be able to localize the terminology associated with the pandemic in the English language as the dominant global language, especially in the scientific field. The period of the COVID-19 virus outbreak and its accompanying effects and developments witnessed the production of a huge number of newly coined terms in the English language, which posed a major challenge for Arabic translators and required them to search for linguistic means to localize these new terms, ranging from derivation and borrowing to translation and the use of machine translation techniques based on artificial intelligence programs."

Towards Retrieval-Based Neural Code Summarization: A Meta-Learning Approach

Code summarization aims to generate code summaries automatically, and has attracted a lot of research interest lately. Recent approaches to it commonly adopt neural machine translation techniques, which train a Seq2Seq model on a large corpus and assume it could work on various new code snippets. However, codes are highly varied in practice due to different domains, businesses or programming styles. Therefore, it is challenging to learn such a variety of patterns into a single model. In this paper, we propose a brand-new framework for code summarization based on meta-learning and code retrieval, named MLCS to tackle this issue. In this framework, the summarization of each target code is formalized as a few-shot learning task, where its similar examples are used as training data and the testing example is itself. We retrieve examples similar to the target code in a rank-and-filter manner. Given a neural code summarizer, we optimize it into a meta-learner via Model-Agnostic Meta-Learning (MAML). During inference, the meta-learner first adapts to the retrieved examples and yields an exclusive model for the target code, and then generates its summary. Extensive experiments on real-world datasets show: (1) Utilizing MLCS, a standard Seq2Seq model is able to outperform previous state-of-the-art approaches, including both neural models and retrieval-based neural models; (2) MLCS can flexibly adapt to existing neural code summarizers without modifying their architecture, and could significantly improve their performance with the relative gain of up to 112.7% on BLEU-4, 23.2% on ROUGE-L, and 31.5% on METEOR; (3) Compared to the existing retrieval-based neural approaches, MLCS can better leverage multiple similar examples, and shows better generalization ability on different retrievers, unseen retrieval corpus and low-frequency words.

SeqTrans: Automatic Vulnerability Fix Via Sequence to Sequence Learning

Software vulnerabilities are now reported unprecedentedly due to the recent development of automated vulnerability hunting tools. However, fixing vulnerabilities still mainly depends on programmers’ manual efforts. Developers need to deeply understand the vulnerability and affect the system’s functions as little as possible. In this paper, with the advancement of Neural Machine Translation (NMT) techniques, we provide a novel approach called SeqTrans to exploit historical vulnerability fixes to provide suggestions and automatically fix the source code. To capture the contextual information around the vulnerable code, we propose to leverage data-flow dependencies to construct code sequences and feed them into the state-of-the-art transformer model. The fine-tuning strategy has been introduced to overcome the small sample size problem. We evaluate SeqTrans on a dataset containing 1,282 commits that fix 624 CVEs in 205 Java projects. Results show that the accuracy of SeqTrans outperforms the latest techniques and achieves 23.3% in statement-level fix and 25.3% in CVE-level fix. In the meantime, we look deep inside the result and observe that the NMT model performs very well in certain kinds of vulnerabilities like CWE-287 (Improper Authentication) and CWE-863 (Incorrect Authorization).

Toward the Multilingual Semantic Web: Multilingual Ontology Matching and Assessment

The amount of multilingual data on the Web proliferates; therefore, developing ontologies in various natural languages is attracting considerable attention. In order to achieve semantic interoperability for the multilingual Web, cross-lingual ontology matching techniques are highly required. This paper proposes a Multilingual Ontology Matching (MoMatch) approach for matching ontologies in different natural languages. MoMatch uses machine translation and various string similarity techniques to identify correspondences across different ontologies. Furthermore, we propose a Quality Assessment Suite for Ontologies (QASO) that comprises 14 metrics, out of which seven metrics are used to assess the quality of the matching process and seven metrics are used to evaluate the quality of the ontology. We present an in-depth comparison of different string similarity techniques across various languages to get the most effective similarity measure(s) between multilingual terms. To illustrate the applicability of our approach and how it can be used in different domains, we present two use cases. MoMatch has been implemented using Scala and Apache Spark under an open-source license. We have compared our results with the results from the Ontology Alignment Evaluation Initiative (OAEI 2020). MoMatch has achieved significantly high precision, recall, and F-measure compared to five state-of-the-art matching approaches.

Fitting missing API puzzles with machine translation techniques

While implementing software projects, developers do not reinvent the wheel but try to reuse existing API calls and source code. In recent years, the problems related to recommending APIs and code snippets have been intensively investigated. Although current approaches have achieved encouraging performance, there is still the need to improve the recommendation process’s effectiveness and efficiency. In this work, we reformulate the problem of API recommendations by proposing learning and recommending API sequences relevant to a given coding context. We present LUPE, a novel approach to API and code recommendation, exploiting cutting-edge deep learning techniques. Thanks to the underlying Encoder–Decoder architecture specialized in transforming sequences, LUPE can effectively learn the order in which invocations occur. The approach has been evaluated on two Android datasets and compared with GAPI and FACER, two state-of-the-art API recommender systems. Being fed with augmented training data, our conceived approach can obtain a high prediction accuracy, and produce a perfect match in several cases, hence outperforming the baselines.

Automated conversion of engineering rules: Towards flexible manufacturing collaboration

Rapid on-demand manufacturing resource sharing within and between factories are critical to achieving responsive autonomous manufacturing collaborations towards mass personalization. To this end, cloud manufacturing technologies allow resource owners/service providers to virtualize and encapsulate their resources as services accessible over the Internet. Decision-making in cloud manufacturing needs to utilize real-world engineering knowledge from different parties. Many existing systems have adopted the semantic web-based decision-making framework, in which engineering knowledge is modeled using structured syntax. However, manually converting engineering rules to semantic rules is time-consuming and error prone. This research proposes a machine learning model, based on the Transformer model, that uses neural machine translation techniques to convert engineering knowledge expressed in natural language to structured semantic rules directly. The model is implemented using neural network. The model is first trained using typical sentences that are used for describing engineering knowledge. From these sample sentences, the model learns the patterns and the meaning of the sentences. This allows the model to identify the service providers, resource users, and the resources described in the sentences. As a result, the corresponding semantic rules can be constructed. Compared with previous approaches, the proposed scheme not only improves the conversion accuracy but also reduces the amount of required human interaction, simplifying the system and its use.