Machine Translation Processing Research Articles

From one-dimensional to multidimensional map neural networks

In the contemporary landscape, artificial neural networks transcend their traditional role of function approximation and have found diverse applications in fields such as image classification, machine translation, speech recognition, and natural language processing. In some datasets, traditional architectures exhibit low test and training accuracy, coupled with high loss and prolonged training times. This study aims to introduce innovative neural network architectures that outperform conventional models. The research presents a novel framework integrating one-dimensional and multidimensional map neural networks, consisting of three distinct architectures: 1D-Map, 2D-Map, and 3D-Map. A systematic performance comparison with traditional models is conducted following the implementation of these architectures. The evaluation spans four datasets, encompassing the domains of heat treatment of electroless Ni-P nano coatings, letter recognition, combined cycle power plants, and Seoul bike sharing demand. In the heat treatment dataset, the proposed 3D-Map architecture reached 0.055 higher average test accuracy than traditional MLP architecture. In the letter recognition dataset, the test accuracy of 3D-Map architecture was 0.0523 higher than the test accuracy of the LSTM architecture. In the combined cycle power plant dataset, the test accuracy of the 3D-Map architecture was 0.0612 more than the test accuracy of the MLP architecture. In the Seoul bike-sharing demand dataset, the test accuracy of the 2D-Map architecture was 0.0696 higher than the test accuracy of the LSTM architecture. The study's findings underscore the consistently superior performance of the proposed architectures compared to their traditional counterparts.

Machine Translation and NLP Tools: Developing and Refining Language Technologies for African Languages

Machine Translation (MT) and Natural Language Processing (NLP) tools have significantly evolved over the past few decades, leading to notable advancements in the field of language technology. However, most of these developments have been concentrated on languages with abundant data, such as English, Chinese, and European languages. African languages, with their unique linguistic structures and vocabularies, remain underrepresented in the MT and NLP landscape (Joshi et al., 2020). This article explores the challenges and opportunities in creating and refining machine translation models and NLP tools tailored to the unique structures of African languages. It discusses the specific linguistic features that set African languages apart, reviews the current state of MT and NLP tools for these languages, and outlines strategies for developing more effective models that cater to the diverse linguistic landscape of Africa.

The "machine translation + post-machine translation editing" model on the YiCAT platform: using the example of the discipline "Stylistic post-machine text editing" for first-year graduate students of the Higher School of Translation of Moscow State University

In this article, the author analyzes the process of machine translation and post-machine editing by Chinese students in classes on the discipline "Stylistic post-machine text editing" using the YiCAT translation platform, which uses a model of combining machine translation and post-machine editing in order to organize the educational process and allocate study time. In 2017, the Russian government approved the "Digital Economy Plan of the Russian Federation", as a result of which the digitalization process gradually penetrated into all scientific spheres. The author of the article concludes that Russian universities should pay more attention to teaching machine translation and post-machine translation editing. In addition, the article presents the idea that the translation departments of modern universities should focus on the introduction and application of translation technologies and the latest translation tools in the framework of teaching translation skills. There are only a few hundred articles in Russia dealing with the specifics of machine translation. Most of them are devoted to the study of existing limitations, development opportunities and ways to improve machine translation systems. At the same time, there are extremely few articles dealing with the features of post-machine editing of the translation text. The number of such articles does not exceed several dozen. Thus, there are many challenges in the field of post-machine translation editing research that should be addressed as soon as possible so that the field of post-machine translation editing can correspond to the era of artificial intelligence. At the same time, Russian universities should pay attention to the teaching of disciplines involving machine translation tools and post-machine editing skills. Large translation faculties should actively use translation technologies and machine translation tools in the classroom, add new academic disciplines implying the familiarization and application of such technologies and tools by students, as well as integrate such disciplines into the framework of existing training programs for specialists in the field of translation. All this will allow universities to form a reliable basis for the education of modern and qualified specialists who meet the requirements of the new era.

OpenLogos in the context of custom language models for the business sector: A historical perspective on the roots of natural language generation

In the framework of Multi3Generation COST Action (CA18231), we have provided the OpenLogos tools and resources to the community with the belief that (i) they can be beneficial to Early Research Career researchers and (ii) they can also assist startup companies with limited resources in initiating endeavors to create their Natural Language Generation, Machine Translation, Paraphrasing or other Natural Language Processing systems. In this article, we explore OpenLogos capabilities in an industry case scenario. We provide historical background on the proven importance of the Logos commercial system in shaping the documentation process of a multinational. Understanding the historical significance of Machine Translation is crucial for grasping our present position in Generative Language Models and our role in the domain of Generative Artificial Intelligence. We explore how novel Custom Generative Language Models, drawing inspiration from the Logos Model, can prove beneficial across various industries worldwide.

Talking Hands: Speech to Sign Language Converter

Deaf people face communication challenges in many aspects of their lives. This project proposes a speech-to-sign language converter that can help to bridge the communication gap between deaf and hearing people. The converter would use speech recognition technology to transcribe spoken language into text. This text would then be translated into sign language images or GIFs. The images or GIFs would be displayed on a screen, allowing deaf people to easily understand the message. The converter would be designed to be as accurate and user-friendly as possible. It would also be customizable to support different sign languages. This project has the potential to make a significant impact on the lives of deaf people. It could help them to communicate more effectively in school, at work, and in social settings. It could also help to break down communication barriers and foster greater understanding between deaf and hearing people. The converter would be developed using a variety of technologies, including speech recognition, machine translation, and image processing. The objective of our project is to reduce the communication gap between normal people and disabled people by providing a virtual animation translator for sign language.

The Crisis of (MT) From Arabic into Foreign Languages Case Study : Google Translate

Why do machine translation from Arabic into foreign languages and vice versa constitute a challenge compared to other languages? Is it because traditional grammar rules haven’t been computerized yet? Or because of the lack of technological skills in the Arab world? Or is it simply due to the lack of interest in developing Arabic in order to cope with the digital world needs? The aim of the present study is to investigate the effectiveness of the free online machine translation (GoogleTranslate) from Arabic into English or vice versa. It attempts to define machine translation., Automatic processing of Arabic within the scope of the “machine translation and automatic language processing” axis, We will try to display samples of the machine translation crisis through the Google Translate application . It has been concluded that the efforts of Arab researchers are still in the beginning, and the pattern of teaching pure sciences such as mathematics, physics, and technology in a language other than Arabic constitutes a major hindrance.

The metamorphosis of machine translation: The rise of neural machine translation and its challenges

Machine translation refers to the process of using computers to translate source language into target language, which has undergone significant transformations since its inception, with the current mainstream neural machine translation achieving satisfactory translation performance. This paper overviews the three developmental stages of machine translation: rule-based machine translation, statistical machine translation, and neural machine translation, with a focus on neural machine translation. It introduces the key models that emerged in the development process of neural machine translation, namely the recurrent neural network encoder-decoder model, recurrent neural network search model, and Transformer, and compares their strengths and limitations. Other relevant technologies and models developed alongside neural machine translation are also discussed. Addressing the current challenges of neural machine translation, the paper delves into issues of overfitting, low-resource translation, structural optimization of Transformer models, and enhancement of neural machine translation interpretability. Finally, the paper explores the prospects of applying neural machine translation to multimodal translation.

Machine Translation and Natural Language Processing

Machine translation and natural language processing are powerful tools that allow for the automated translation of text from one language to another. Machine translation systems have evolved from rule-based systems to statistical and neural network-based approaches, with each approach having its own strengths and weaknesses. NLP, on the other hand, focuses on understanding the structure and meaning of natural language and includes tasks such as part-of-speech tagging, named entity recognition, and sentiment analysis. Thegoalofmachinetranslation,a subfield of natural language processing (NLP), is to create platform that translate text or speechautomatically.RBMT provides linguistic accuracy and control, but linguistic resources must be built and maintained meticulously. However, SMT makes use of large-scale parallel corpora to automatically learn translation patterns, making it adaptable to new language pairs and context-dependent translations.However, SMT may struggle with handling grammatical nuances and domain-specific vocabulary. Hybrid approaches combining the best of both RBMT andSMT and newer approaches like neural machine translation (NMT) are being explored to overcome the limitations and improve the quality of translation output.

Evaluating machine translation of literature through rhetorical analysis

This paper looks at how well ChatGPT and DeepL, two AI tools, translate literary works. Not only can ChatGPT translate text, but it can also carry out other jobs. DeepL is a service that performs computer translation and uses neural networks. The paper looks at how ChatGPT and DeepL translate books, poems, and dialogues compared to translations done by humans. The paper also talks about the pros and cons of using machine translation for literary reasons, including issues of creativity, style, and adapting to different cultures. The paper uses both new and old studies on machine translation technologies and how they work with human translation. The paper comes to the conclusion that ChatGPT and DeepL are useful but imperfect tools for translating literature, and they require human review and improvement. The paper adds to the fields of machine translation and natural language processing by looking at how two cutting-edge AI tools, ChatGPT and DeepL, can be used to translate literary works. The paper also adds to literature studies and digital humanities by looking into what machine translation can and can't do for creative writing and dialog systems. The goal of the paper is to encourage researchers, translators, writers, and users from different fields to work together and talk to each other. ⁤

Transformer Based Sentiment Analysis on Code Mixed Data

In India, a country known for its linguistic diversity, code mixing is a common practice, and it has a profound impact on the way people communicate through various mediums, including social media platforms and everyday conversations. The prevalence of code-mixing in social media platforms presents a substantial hurdle for machine translation and language processing tasks. The abundance of unstructured text in code-mixed form on these platforms highlights a crucial research domain within NLP. The blending of Hindi and English, known as Hinglish, and other mixed case text like Malayalam-English, Tamil-English, Telugu- English are particularly prevalent among the younger generation while communication in social media and requires appropriate processing to aid comprehension by both monolingual users and language processing models. Manual translation of this type of data proves to be laborious due to challenges like limited vocabulary, potential misunderstandings of context, grammatical errors, biases, and various other issues. Additionally, existing translation models tend to perform more effectively on monolingual language rather than code-mixed data. Therefore, it is more desirable to build models that can translate code-mixed data.This study tries to convert code-mixed Hinglish, Malayalam-English, Tamil-English, Telugu-English language in Romanised script to monolingual English which can further be given as input to NLP applications like Sentiment Analysis. This is achieved by finetuning pretrained models like IndicLID for Language Identification (LID) module and use an ensemble approach for transliteration + translation using Indictrans and IndicXlit for code mixed machine translation which will be given as input to classification algorithm which performs Sentiment Analysis and predict the sentiment. It is observed that this approach of translation of code-mixed test perform better than traditional machine translation for Indian languages Hindi, Tamil, Telugu and Malayalam.

Cross-language information retrieval for poetry form of literature-based on machine transliteration using CNN

Transliteration is phonetically translating a language’s words into an international or non-native screenplay. The machine translation process now plays an essential role in scholarly research. The most crucial complement criterion of the English translation system is preserving the phonetic qualities of the language specification after English translation in the chosen language. However, a suitable bilingual text corpus is necessary for statistical models to attain improved transliteration accuracy. Marathi-to-English direct machine translation is done through a cross-language information retrieval system using the CNN classifier model in this proposed research. The proposed method considers a sequence labelling issue brought on by the split transliteration units used in the process. All half-consonant clusters in the Devanagari script are effectively mapped as half-consonant “a” s and labelled using the Modified Intermediate Phonetic Code (MIPC). After generating the phonetic units for each feature in the base and aim languages, the weight is assigned to a phonetic unit in both languages, and individual phonetic unit probabilities are computed. If the probability is zero, then segments are established and recalculated for each segment based on the target phonetic unit location in the word. Therefore, the proposed approach classifies the required phonetic unit with a high accuracy rate.

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.

Deep Learning-Based Job Placement in Distributed Machine Learning Clusters With Heterogeneous Workloads

Nowadays, most leading IT companies host a variety of distributed machine learning (ML) workloads in ML clusters to support AI-driven services, such as speech recognition, machine translation, and image processing. While multiple jobs are executed concurrently in a shared cluster to improve resource utilization, interference among co-located ML jobs can lead to significant performance downgrade. Existing cluster schedulers, such as YARN and Mesos, are interference-agnostic in their job placement, leading to suboptimal resource efficiency and usage. Some literature has studied interference-aware job placement policy, but relies on detailed workload profiling and interference modeling, which is not a general solution. In this work, we present Harmony, a deep learning-driven ML cluster scheduler that places heterogeneous training jobs (either with parameter server architecture or all-reduce architecture) in a manner that minimizes interference and maximizes performance (i.e., training completion time minimization). The design of Harmony is based on a carefully designed deep reinforcement learning (DRL) framework enhanced with reward modeling. The DRL integrates a dynamic sequence-to-sequence model with the state-of-the-art techniques to stabilize training and improve convergence, including actor-critic algorithm, job-aware action space exploration, multi-head attention, and experience replay. In view of a common lack of reward samples corresponding to different placement decisions, we build an auxiliary sequence-to-sequence reward prediction model, which is trained with historical samples and used for producing reward for unseen placement. Experiments using real ML workloads in a Kubernetes cluster of 6 GPU servers show that Harmony outperforms representative schedulers by 16%–42% in terms of average job completion time.

Exploring the Application of Artificial Intelligence in Foreign Language Teaching: Challenges and Future Development

With the rapid development of artificial intelligence (AI) technology, it is increasingly being utilized in the field of education, particularly in foreign language teaching. The concept of education meta-universe is also gaining popularity, and the emergence of ChatGPT has revolutionized traditional foreign language teaching methods. AI technologies such as speech recognition, machine translation, and natural language processing have proven to be effective tools to help students improve their foreign language learning outcomes. However, the application of these technologies also brings some challenges and problems. This paper aims to discuss the impact of AI on foreign language teaching, analyze its advantages and disadvantages, explore its future development trend, and provide suggestions for educators to make better use of AI technologies to assist foreign language teaching.

Arabic and computer language; Reading in Arabic linguistic geometry

The translation is an important means of transmitting the intellectual heritage among nations, and the growth of human knowledge. In the face of this rapid scientific progress that the world is witnessing today, translation in general and machine translation, in particular, has become an urgent necessity, especially because the latter is characterized by speed and ease, and its savings of effort, time, and money, but - and unfortunately - there are many The obstacles that prevent the success of the machine translation process, and we will try in this research paper to shed light on one of the most important of these obstacles; It is linguistic relativism, which says that a person’s view of life varies according to his language, and therefore the translation of texts from one language to another will be an incomplete translation

Beyond the Transformer: A Novel Polynomial Inherent Attention (PIA) Model and Its Great Impact on Neural Machine Translation.

This paper describes a novel polynomial inherent attention (PIA) model that outperforms all state-of-the-art transformer models on neural machine translation (NMT) by a wide margin. PIA is based on the simple idea that natural language sentences can be transformed into a special type of binary attention context vectors that accurately capture the semantic context and the relative dependencies between words in a sentence. The transformation is performed using a simple power-of-two polynomial transformation that maintains strict consistent positioning of words in the resulting vectors. It is shown how this transformation reduces the neural machine translation process to a simple neural polynomial regression model that provides excellent solutions to the alignment and positioning problems haunting transformer models. The test BELU scores obtained on the WMT-2014 data set are 75.07 BELU for the EN-FR data set and 66.35 BELU for the EN-DE data set—well above accuracies achieved by state-of-the-art transformer models for the same data sets. The improvements are, respectively, 65.7% and 87.42%.

Advanced Intelligent English Translation Based on Multisensor Data Fusion Optimization

English translation activity course is of great significance to cultivate students’ English translation level. In the context of multisensor data fusion, how to effectively carry out English translation activity course in colleges and universities has become an important topic. The educational value and intellectual property of advanced Intelligent English translation activity course are analyzed. From multisensor data fusion and the improvement of translation, translators psychological changes of the boot and prominent features, English translation activity and translation, the generality of the multisensor data fusion of multisensor data fusion personalization features this four aspects, which is under the background of the sensor data fusion of the practice for college English translation activity. Firstly, the theory of data fusion estimation is elaborated, and various data fusion structures in multisensor systems are summarized. Then, the data fusion estimation model based on Kalman filter is established, and the Kalman filtering algorithms of centralized, sequential, parallel, and joint structures are given, respectively. Simulation experiments are carried out on the algorithms. Experimental results show that the estimation accuracy of the system can be improved by multisensor data fusion. Then a rule-based lexical analyzer is designed. Combined with the system model, a rule-based lexical analyzer and a comprehensive dictionary, the linguistic knowledge source throughout the whole machine translation process, are researched and designed. A hashing algorithm for lexical retrieval is designed, and various rules and data structures related to the lexical analyzer are described in formal language. The analysis algorithms of morphological preprocessing, morphological analysis, unincluded word processing, phrase analysis, and part of speech tagging are introduced.

A machine learning application for raising WASH awareness in the times of COVID-19 pandemic

The COVID-19 pandemic has revealed the power of internet disinformation in influencing global health. The deluge of information travels faster than the epidemic itself and is a threat to the health of millions across the globe. Health apps need to leverage machine learning for delivering the right information while constantly learning misinformation trends and deliver these effectively in vernacular languages in order to combat the infodemic at the grassroot levels in the general public. Our application, WashKaro, is a multi-pronged intervention that uses conversational Artificial Intelligence (AI), machine translation, and natural language processing to combat misinformation (NLP). WashKaro uses AI to provide accurate information matched against WHO recommendations and delivered in an understandable format in local languages. The primary aim of this study was to assess the use of neural models for text summarization and machine learning for delivering WHO matched COVID-19 information to mitigate the misinfodemic. The secondary aim of this study was to develop a symptom assessment tool and segmentation insights for improving the delivery of information. A total of 5026 people downloaded the app during the study window; among those, 1545 were actively engaged users. Our study shows that 3.4 times more females engaged with the App in Hindi as compared to males, the relevance of AI-filtered news content doubled within 45 days of continuous machine learning, and the prudence of integrated AI chatbot “Satya” increased thus proving the usefulness of a mHealth platform to mitigate health misinformation. We conclude that a machine learning application delivering bite-sized vernacular audios and conversational AI is a practical approach to mitigate health misinformation.

BaNeP: An End-to-End Neural Network Based Model for Bangla Parts-of-Speech Tagging

In Natural Language Processing, Parts-of-Speech tagging is a vital component that significantly impacts applications like machine translation, spell-checker, information retrieval, and speech processing. In languages such as English and Dutch, POS tagging is considered a solved problem (accuracy: 97%). However, for low-resource languages like Bangla, challenges are still there. In this article, we have proposed a novel RNN-based network named BaNeP to determine parts of speech for Bangla words. The proposed network extracts structural features through a bidirectional LSTM-based sub-network, and intricate contextual relations among words of a sentence are identified through an elaborate weighted context extraction procedure. These features are then combinedly utilized to generate the final Parts-of-Speech prediction. Training the model requires only an annotated dataset vanishing the need for any hand-crafted features. Experimental results on the LDC2010T16 dataset show significant accuracy improvement compared to existing Bangla POS taggers.

Beyond MT metrics in specialised translation: Automated and manual evaluation of machine translation output for freelance translators and small LSPs in the context of EU documents

This paper discusses simplified methods of translation evaluation in two seemingly disparate areas: machine translation (MT) technology and translation for EU institutions. It provides a brief overview of methods for evaluating MT output and proposes simplified solutions for small LSPs and freelancers dealing with specialised translation of this kind. After discussing the context of the study and the process of machine translation, an analysis of fragments of the selected specialist text (an EU regulation) is carried out. The official English and Polish versions of this document provide the basis for a comparative evaluation of raw machine translation output obtained with selected commercially available (paid) neural machine translation engines (NMT). Quantitative analysis, including the Damerau-Levenshstein edit distance parameters and the number of erroneous segments in the text, combined with a manual qualitative analysis of errors and terminology can be a serviceable method for small LSPs and freelance translators to evaluate the usefulness of neural machine translation engines.