Machine Translation Research Articles

The Use of Google Translate and U-Dictionary as Machine Translation for Translating Text: EFL College Student’s Preference and Perceptions

Several studies have investigated the effects of using Google Translate and U-Dictionary on translation products for English as a foreign language (EFL) student. However, students' preferences regarding these two machines’ translation for translating texts in EFL translation classes in Indonesia still seem relatively few and have not been much explored. This research aimed to determine which machine translation EFL college students prefer for translating their text. This study used a qualitative case study approach. In investigating students’ preferences, questionnaires, and in-depth interview were used as data collection tools. Seventeen students were selected by purposive sampling and were administered an online questionnaire. Then, students participated in in-depth interviews and obtained further information from an online questionnaire. We then analyzed the data using two techniques, including frequency counts for quantitative data and qualitative analysis through thematic analysis for qualitative data. The findings reveal that students prefer Google Translate over U-Dictionary for three reasons. First, they consider Google Translate as a complete machine translation with various features that help them translate text. Second, Google Translate increases student's knowledge of new vocabulary. Third, Google Translate makes the translation process more accessible for students. It is so easy to access. However, U-Dictionary also received high marks because students felt more confident in the accuracy of the U-Dictionary translation results. Therefore, it is believed that combining these two machines’ translations will make the student's translation process more accessible

An Overview of the Application of Convolutional Neural Networks inSentiment Analysis

The field of natural language processing, or NLP, uses its understanding of human language to find practical solutions to issues. It mainly includes two parts: the core task and the application. The core task represents the common problem that needs to be solved in various natural language application directions. It includes language models, morphology, grammar analysis, semantic analysis, etc. At the same time, the application section focuses on specific natural language processing tasks such as machine translation, information retrieval, question-answering systems, dialogue systems, etc. Natural language processing has made a significant contribution to the development of human society and the economy and provides strong support for all aspects of research work. Opinion mining, or sentiment analysis, is a subfield of natural language processing that develops systems for identifying and extracting ideas from text. Sentiment analysis is a hot topic since it has many practical applications. Many opinion-expressing texts are available on review sites, forums, blogs, and social media as the amount of publicly available information on the Internet grows. This unstructured information can then be automatically transformed into structured data about products, services, brands, politics, or other topics on which people can express their opinions using sentiment analysis systems. This information can be used for marketing analytics, public relations, product reviews, network sponsor ratings, product feedback, and customer service. With the rapid growth of labeled sample data sets and the notable enhancement in graphics processor (GPU) performance, convolutional neural network research has advanced rapidly and achieved remarkable leads to various computer vision tasks. By reviewing the application of CNN, we see that convolutional operations are naturally suitable for some text processing and, thus, naturally suitable for the background of sentiment analysis.

Gender Issues in Machine Translation

Gender Issues in Machine Translation

Machine translation: Turkish–English bilingual speakers’ accuracy detection of evidentiality and preference of MT

Machine translation (MT) is the automated process of translating text between different languages, encompassing a wide range of language pairs. This study focuses on non-professional bilingual speakers of Turkish and English, aiming to assess their ability to discern accuracy in machine translations and their preferences regarding MT. A particular emphasis is placed on the linguistically subtle yet semantically meaningful concept of evidentiality. In this experimental investigation, 36 Turkish–English bilinguals, comprising both early and late bilinguals, were presented with simple declarative sentences. These sentences varied in their evidential meaning, distinguishing between firsthand and non-firsthand evidence. The participants were then provided with MT of these sentences in both translation directions (Turkish to English and English to Turkish) and asked to identify the accuracy of these translations. Additionally, participants were queried about their preference for MT in four crucial domains: medical, legal, academic, and daily contexts. The findings of this study indicated that late bilinguals exhibited a superior ability to detect translation accuracy, particularly in the case of firsthand evidence translations, compared to their early bilingual counterparts. Concerning the preference for MT, age of acquisition and the accuracy detection of non-firsthand sentence translations emerged as significant predictors.

기계번역 활용 능력 강화를 위한 고등학생용 인공지능과 영어 교과 융합 교육 콘텐츠 타당성 검증

Objectives This study aimed to validate AI and English Integrated Teaching Materials for High School Students to Improve Machine Translation Literacy.
 Methods To accomplish this, we organized a group of experts in the field of English education and artificial in-telligence integrated education and conducted a Delphi survey. We collected opinions on the necessity of strengthening translator utilization skills, that is, machine translation literacy, as well as the goal, structure, and content of the classes, in order to validate foundational materials for lessons that enhance the utilization skills of artificial intelligence translation systems. After revising the contents, the second Delphi survey was conducted.
 Results The validity of each sub-question was analyzed based on .49 which is the standard value for securing content validity when the number of participants in the expert group was 15. As a result of the 1st Delpi survey, it was found that it was not valid in the content structure(.33), the content of the third class(.33), and the content of the third class worksheet(.46). After revising the contents, the second Delphi survey was conducted. Statistically significant figures were secured in all items such as class necessity, design, structure, and content of each class. The validity of the artificial intelligence convergence English education contents was secured, and the Delphi survey was completed in the second round.
 Conclusions AI-English integrated education is essential to improve Machine Translation Literacy. This study is of great significance in that it has validated AI integrated education contents that can strengthen Machine Translation Literacy by understanding the principles and differences of translators, identifying the causes of trans-lation differences, and judging translation errors. However, since Machine Translation Literacy and students' English skills are inseparable concepts, continuous research will be needed on integrated education methods that can improve them together.

Using Voice-to-Voice Machine Translation to Overcome Language Barriers in Clinical Communication: An Exploratory Study

BackgroundMachine translation (MT) apps are used informally by healthcare professionals in many settings, especially where interpreters are not readily available. As MT becomes more accurate and accessible, it may be tempting to use MT more widely. Institutions and healthcare professionals need guidance on when and how these applications might be used safely and how to manage potential risks to communication.ObjectivesExplore factors that may hinder or facilitate communication when using voice-to-voice MT.DesignHealth professionals volunteered to use a voice-to-voice MT app in routine encounters with their patients. Both health professionals and patients provided brief feedback on the experience, and a subset of consultations were observed.ParticipantsDoctors, nurses, and allied health professionals working in the Primary Care Division of the Geneva University Hospitals, Switzerland.Main MeasuresAchievement of consultation goals; understanding and satisfaction; willingness to use MT again; difficulties encountered; factors affecting communication when using MT.Key ResultsFourteen health professionals conducted 60 consultations in 18 languages, using one of two voice-to-voice MT apps. Fifteen consultations were observed.Professionals achieved their consultation goals in 82.7% of consultations but were satisfied with MT communication in only 53.8%. Reasons for dissatisfaction included lack of practice with the app and difficulty understanding patients. Eighty-six percent of patients thought MT-facilitated communication was easy, and most participants were willing to use MT in the future (73% professionals, 84% patients). Experiences were more positive with European languages. Several conditions and speech practices were identified that appear to affect communication when using MT.ConclusionWhile professional interpreters remain the gold standard for overcoming language barriers, voice-to-voice MT may be acceptable in some clinical situations. Healthcare institutions and professionals must be attentive to potential sources of MT errors and ensure the conditions necessary for safe and effective communication. More research in natural settings is needed to inform guidelines and training on using MT in clinical communication.

University students’ perceptions of artificial intelligence-based tools for English writing courses

This research explores the perceptions of Korean university students regarding artificial intelligence (AI)-based writing tools that include tools guided by machine learning, such as Google Translate and Naver Papago, and generative AI tools, such as Grammarly. A mixed methodology was used, including both quantitative and qualitative data. Among students who have taken English writing courses, 80 Korean university students volunteered for the online survey. After the survey, the research team recruited interview participants, and five volunteered participants joined the focus group interview. The study results indicate that these AI-based writing tools could improve English language learners (ELLs) writing skills. ELLs also noted the strengths and weaknesses of each AI-based tool, including the accessibility of translation machine learning and the error-checking capabilities of generative AI. However, interview data analysis indicates that the excessive use of AI-based writing tools could interfere with ELLs’ English writing process. This study highlights the need to effectively integrate AI-based tools in English language teaching for adult ELLs worldwide.

Titles of Acts: Translation from English into Russian

The article examines titles of English acts such as ‘The Act of Settlement 1701’, ‘The Instrument of Government 1653’, ‘The Act of Supremacy; 1534, 1559, ‘The Reform Act’ 1832, 1867, 1884 and ‘The Test Act’ 1673, 1678 and their translation into the Russian language. The analysis of textbooks and manuals on law and state history of foreign countries in the Russian language shows that their authors refer to the titles that have firmly entrenched in the Russian language, even though some of them have been translated incorrectly. Some researchers provide their own mostly word-for-word translation or totally avoid mentioning the titles of acts in the text. At the same time, adequate translation is essential as it allows readers to elicit necessary information and gain extensive and comprehensive knowledge on the subject. The polysemy of legal terms and the underlying historical background make the process of translation into Russian even more complicated. The differences between legal systems and languages due to their unique historical and cultural development cause difficulties in the translation process even for the most advanced machine translation tools based on neural networks. In order for the translation to be accurate, and therefore the cognitive function to be fully performed in academic texts, it is necessary to be familiar with the field of legal science as a whole, to take into account the historical context as well as the background of a particular act. The lack of background knowledge and the inability to grasp the meaning, role and importance of this or that act of Parliament results in word-for-word erroneous translation that in its turn distorts the original meaning of the text. The polysemy of English terms makes it difficult to find the corresponding equivalent term in Russian. Descriptive translation based on background knowledge with due regard for language peculiarities, as well as the use of such tools as footnotes and comments, can contribute to achieving the purpose.

Research on artificial intelligence machine translation based on BP neural algorithm

The primary focus of artificial intelligence advancement is in machine translation; nonetheless, a prevalent issue persists in the form of imprecise translation. The current challenge faced by artificial intelligence is to effectively executing machine translation from extensive datasets. This research presents a BP neural method that aims to repeatedly analyse translation data and achieve optimisation in machine translation. The findings indicate that the use of BP neural network may enhance the dependability and precision of machine translation, with an accuracy rate over 84%. This performance surpasses that of the online translation approach. Hence, it can be inferred that the use of BP neural algorithms has the potential to fulfil the requirements of machine translation and enhance the precision of online translation conducted by humans.

Deep Learning-based POS Tagger and Chunker for Odia Language Using Pre-trained Transformers

Developing effective natural language processing (NLP) tools for low-resourced languages poses significant challenges. This article centers its attention on the task of Part-of-speech (POS) tagging and chunking, which pertains to the identification and categorization of linguistic units within sentences. POS tagging and Chunking have already produced positive results in English and other European languages. However, in Indian languages, particularly in Odia language, it is not yet well explored because of the lack of supporting tools, resources, and its complex linguistic morphology. This study presents the building of a manually annotated dataset for Odia phrase chunking task and the development of a deep learning-based model specifically tailored to accommodate the distinctive properties of the language. The process of annotating the Odia chunking corpus involved the utilization of inside-outside-begin labels, which were tagged by using designed Odia chunking tagset. We utilize the constructed Odia chunking dataset to build Odia chunker based on deep learning techniques, employing state-of-the-art architectures. Various techniques, such as Recurrent Neural Networks, Convolutional Neural Networks, and transformer-based models, are investigated to determine the most effective approach for Odia POS tagging and chunking. In addition, we conduct experiments utilizing diverse input representations, including Odia word embeddings, character-level representations, and sub-word units, to effectively capture the complex linguistic characteristics of the Odia language. Numerous experiments are conducted that evaluate the performance of our Odia POS tagger and chunker, employing standard evaluation metrics and making comparisons with existing approaches. The results demonstrate that our transformer-based tagger and chunker achieves superior accuracy and robustness in identifying and categorizing linguistic POS tags and chunks within Odia sentences. It outperforms existing work and exhibits consistent performance across diverse linguistic contexts and sentence structures. The developed Odia POS tagger and chunker have enormous potential for a variety of NLP applications, including information extraction, syntactic parsing, and machine translation, all of which are tailored to the low-resource Odia language. This work contributes to developing NLP tools and technologies for low-resource languages, thereby facilitating enhanced language processing capabilities in various linguistic contexts.

A Systematic Review of Cross-Lingual Sentiment Analysis: Tasks, Strategies, and Prospects

Traditional methods for sentiment analysis, when applied in a monolingual context, often yield less than optimal results in multilingual settings. This underscores the need for a more thorough exploration of cross-lingual sentiment analysis (CLSA) methodologies to improve analytical effectiveness. CLSA, confronted with obstacles such as linguistic disparities and a lack of resources, seeks to evaluate sentiments across a range of languages. First, the research background, challenges, existing solution ideas and evaluation tasks of CLSA are summarized. Subsequently, new perspectives including different granularity levels, machine translation support, and sentiment transfer strategies perspectives are highlighted. Finally, potential avenues for future research are discussed.

DSISA: A New Neural Machine Translation Combining Dependency Weight and Neighbors

Most of the previous neural machine translations (NMT) rely on parallel corpus. Integrating explicitly prior syntactic structure information can improve the neural machine translation. In this article, we propose a Syntax Induced Self-Attention (SISA) which explores the influence of dependence relation between words through the attention mechanism and fine-tunes the attention allocation of the sentence through the obtained dependency weight. We present a new model, Double Syntax Induced Self-Attention (DSISA), which fuses the features extracted by SISA and a compact convolution neural network (CNN). SISA can alleviate long dependency in sentence, while CNN captures the limited context based on neighbors. DSISA utilizes two different neural networks to extract different features for richer semantic representation and replaces the first layer of Transformer encoder. DSISA not only makes use of the global feature of tokens in sentences but also the local feature formed with adjacent tokens. Finally, we perform simulation experiments that verify the performance of the new model on standard corpora.

An Ensemble Strategy with Gradient Conflict for Multi-Domain Neural Machine Translation

Multi-domain neural machine translation aims to construct a unified neural machine translation model to translate sentences across various domains. Nevertheless, previous studies have one limitation is the incapacity to acquire both domain-general and domain-specific representations concurrently. To this end, we propose an ensemble strategy with gradient conflict for multi-domain neural machine translation that automatically learns model parameters by identifying both domain-shared and domain-specific features. Specifically, our approach consists of (1) a parameter-sharing framework, where the parameters of all the layers are originally shared and equivalent to each domain, and (2) ensemble strategy, in which we design an Extra Ensemble strategy via a piecewise condition function to learn direction and distance-based gradient conflict. In addition, we give a detailed theoretical analysis of the gradient conflict to further validate the effectiveness of our approach. Experimental results on two multi-domain datasets show the superior performance of our proposed model compared to previous work.

Word Sense Disambiguation applied to Assamese-Hindi Bilingual Statistical Machine Translation

Word Sense Disambiguation (WSD) is concerned with automatically assigning the appropriate sense to an ambiguous word. WSD is an important task and plays a crucial role in many Natural Language Processing (NLP) applications. A Statistical Machine Translation (SMT) system translates a source into a target language based on phrase-based statistical translation. MT plays a crucial role in a WSD system, as a source language word may be associated with multiple translations in the target language. This study aims to apply WSD to the input of the MT system to enhance the disambiguation output. Hindi WordNet was used by selecting the most frequent synonym to obtain the most accurate translation. This study also compared Naïve Bayes (NB) and Decision Tree (DT) to test and build a WSD model. NB was more appropriate for the WSD task than DT when evaluated in the Weka machine learning toolkit. To the best of our knowledge, no such work has been carried out yet for the Assamese Indo-Aryan language. The applied WSD achieved better results than the baseline MT system without embedding the WSD module. The results were analyzed by linguist scholars. Furthermore, the Assamese-Hindi transliteration system was merged with the baseline MT system for the translation of proper nouns. This study marks a remarkable contribution to Assamese NLP, which is a low computationally aware Indian language.

Research of types and current state of machine translation

The background of machine translation dates back to the 1950s when scientists began exploring the use of computers for translation. Motivated by various challenges and needs, such as the high cost of manual translation and cross-cultural communication, machine translation has become a pivotal field. This overview delves into the research background, content, methods, key figures, conclusions, and future prospects of machine translation. It summarizes automatic evaluation metrics, corpus construction, and transfer learning, all of which contribute to enhancing translation performance. Currently, there are three mainstream categories of methods, which include rule-based translation, statistical translation, and neural network-based translation. The rule-based translation method relies on language rules and dictionaries for translation. Statistical machine translation involves the use of extensive bilingual corpora for identification and translation. The conclusion emphasizes the potential of neural machine translation, yet acknowledges challenges in diverse languages, low-resource languages, and specialized terminology.

Machine translation of classical Chinese based on unigram segmentation transformer framework

In the translation work of Chinese ancient books, traditional manual translation is difficult and inefficient. As an important field of natural language processing, machine translation is expected to solve this problem. Due to the rapid development of NLP technology, prior works mainly follow the pipeline of Transformer when dealing with the machine translation task, which can extract the high-quality feature representation with its self-attention mechanism. The great success of Transformer has inspired the direction of our ancient text translation work. In this paper, we screen the Unigram word division by exploring and comparing, and propose a solution for the translation of ancient literary texts. Specifically, we adopt the evaluation of BLEU value and achieve the BLEU values of 43.4 and 40.03 for short and long sentences respectively. When compared with the results of Baidu Translation, our BLEU values increase by 8.12 and 5.18. Additionally, our translation results are more in line with the original text than Baidu Translation, demonstrating the potential and advantage of the model in bridging the ancient and modern Chinese era rift.

Research on sentiment analysis based on the Bilibili video barrage

Based on the analysis of the emotions and mentality of site B users watching videos, this paper proposes a method to visualize important attributes such as high-frequency words, the proportion of positive and negative comments, and word cloud diagrams. In the context of the rise of the Internet and the increasing application of Web 2.0, this paper took the Bilibili barrage text as the research object. Because of the large amount of barrage data, only individual barrages were selected as the analysis objects according to the requirements. The crawler was used to preprocess the crawled video barrage. Then machine translation knowledge and four algorithms such as the word segmentation algorithm and sentiment analysis algorithm were used to analyze the sentiment of the video barrage from three different dimensions and compare the results. Through the analysis of the visualization results, the differences in the emotional distribution of different video barrages were compared, and two important conclusions were drawn: First, the mentality of Bilibili users watching videos is positive; second, there is a certain correlation between the content of the video and the emotional orientation of the barrage, and mutual prediction can be made between the two. However, the research in this paper is only the tip of the iceberg in the research of public opinion analysis. At present, the application of sentiment analysis in public opinion still faces difficulties. How to optimize the algorithm model according to the current situation requires researchers to conduct deeper research and more extensive thinking.

Syntax-aware bidirectional decoding Neural Machine Translation model

The mainstream model in neural machine translation, the Transformer, relies heavily on self-attention mechanisms for translation operations. This approach has significantly improved both accuracy and speed. However, there are still some challenges. For instance, it lacks the incorporation of linguistic knowledge and the ability to leverage syntactic structure information in natural language for translation, leading to issues such as mistranslation and omission. Addressing the limitations of the Transformer's autoregressive decoding, which decodes from left to right without fully utilizing context information and is prone to exposure bias, this paper proposes a syntax-aware bidirectional decoding neural machine translation model. By employing both forward and backward decoders, the generated decoding results can encompass contextual information. Additionally, the model integrates dependency syntax to generate target language sentences with syntactic guidance. Finally, an optimization strategy involving the Teacher Forcing mechanism is introduced to balance the discrepancies between the Teacher Forcing training phase and the autoregressive testing phase, thus alleviating exposure bias issues.

A Literature Survey on SpeakSmart: AI – Enhanced language learning guide

This extensive review of the literature examines the pervasive impact of artificial intelligence (AI) on language learning and teaching, covering innovative uses like real-time language practice, personalized language learning, and automated testing methods in the teaching of English as a foreign language (EFL). The survey covers a wide range of topics, such as the use of Natural Language Processing (NLP) to extract Business Process Models in Business Process Management (BPM), the deployment of English-language chat-bots operating on the WeChat platform that are based on transfer learning, and the incorporation of NLP tools and virtual reality in the e-learning platform Exills. Additionally, it delves into cutting-edge technologies such as chat-bots for language learning, low-resource spoken language learning applications with AI support, and the broad application of AI in EFL teaching, tackling issues and offering encouraging results. The poll also addresses the use of AI in language learning tools, focusing on transparency and ethical issues while utilizing chat-bots, machine translation, speech recognition, and AI-generated content. The study highlights the importance of exposure to different cultures, community interaction, and multilingual voice recognition in creating a comprehensive language learning environment. It also highlights the limitations and enormous possibilities of integrating AI into language instruction.

VisTFC: Vision-guided target-side future context learning for neural machine translation

Visual features encompass visual information extracted from images or videos, serving as supplementary input to enhance the efficacy of neural machine translation (NMT) systems. By seamlessly integrating these visual features into the translation process, NMT models can tap into the expansive visual context, thereby making more precise predictions during translation. Nonetheless, limited efforts have been directed towards exploring the potential of learning target-side future context using visual features to augment NMT performance. To bridge this gap, this paper introduces the Vision-guided Target-side Future Context (VisTFC) learning framework for NMT. Our core objective is to refine translation quality by effectively harnessing and incorporating target-side future contextual insights derived from the visual modality. The VisTFC framework consists of three pivotal components. Firstly, a graph-based multimodal encoder–decoder is established, constructing a bipartite vision-source/target graph. This enables the acquisition of vision-fused textual representations, synthesizing both linguistic and visual attributes to enhance translation accuracy. Secondly, a target-side future context predictor, incorporating a dynamic routing mechanism, infers future context by synergizing visual information. This empowers the model to anticipate and assimilate contextual cues, ensuring more coherent and contextually coherent translations. Thirdly, a sigmoid update gate is introduced, facilitating controlled integration of predicted future context into the decoding process, enabling the decoder to flexibly adapt and utilize the inferred context. Moreover, the VisTFC framework is fortified with additional loss functions that enforce source/target-vision consistency, reinforcing its robustness and effectiveness. Our results demonstrate that our model can achieve substantial improvements, reaching up to 1.0/0.9/1.1 BLEU points beyond the performance of the most robust baselines. This superior performance is evident on both the Test2016 and Test2017 datasets, as well as on the MSCOCO test sets for English-French translation tasks. Furthermore, our experiments underscore the efficacy of VisTFC, even in scenarios with limited resources, such as the English-Hausa language pair. Here, the model achieves notable enhancements, with improvements of up to 1.8/1.9 BLEU points compared to the strongest text-only NMT models on E-Test and C-Test test sets. These findings provide strong evidence supporting our model’s ability to effectively harness target-side future contextual information from the visual modality, resulting in substantial enhancements in machine translation quality. Further analysis and visualization suggest that VisTFC is capable of learning target-side future context from visual signals for better translation. We also have open-sourced our work in Github.11https://github.com/nlpdl/VsiTFC.