Accurate Translation Research Articles

Machine Translation Accuracy by Focusing on Gender Issues for English to Hindi Translation

Machine Translation Accuracy by Focusing on Gender Issues for English to Hindi Translation

『개역개정』 성경 개정을 위한 문체 논의

The reason for revising the Bible is to provide a more accurate and clear translation of the Bible and a Bible that better communicates the meaning to readers of existing Bible translations. Considering this as a premise, the stylistic issues in the revision of the Bible can be summarized as follows:<BR> 1) It is natural to apply the latest Korean orthography to the text.<BR> 2) The style including the sentence ending form should be maintained as it is. This is the same for poetry and prose. If you change the style to the ‘-da’ ending form, there will be strong opposition or you will have to just ignore it.<BR> 3) On the stylistic level, the existing translation should be maintained unless the existing translation is wrong.<BR> 4) Borrowed Chinese words are now part of our language. However, it is difficult for words that do not communicate when written only in Korean to become Korean words. You have to find their alternatives.<BR> 5) With the passage of time, the use of traditional words decreases, and new words can be used more widely. When translating a new Bible, it is desirable to choose a word that is currently used more widely. But when revising an existing Bible, it is necessary to keep the existing terminology for existing Bible readers as long as there is no major problem in communication.<BR> 6) Although translation of human and place names is not meaningful in itself, it is sometimes a factor that makes the Bible difficult. Whether it’s a person with two names or two or three different persons with the same name, it is necessary to find alternatives when it can cause confusion.<BR> 7) When revising a translation of traditional style, attempts to shorten the length of a sentence can be made in very limited cases when it is absolutely necessary. Considering the use of the Bible, it is necessary to examine whether it is possible to break sentences in verse units.<BR> 8) Even if the traditional style is maintained, editing the psalms to have line breaks can help the reading experience of the reader.<BR> 9) Use of punctuation in the Bible text would be a good consideration for Bible readers. Considering that most churches still use the New Korean Revised Version for worship, it will be of great help to readers familiar with modern literature. It can be helpful for preachers who adopt the sermon text on a verse-by-verse basis.<BR> 10) Expressions that are not grammatical must be corrected.

기계번역의 특허 전문용어 한영번역에서 나타나는 오류 양상 분석 – 구글 번역 결과를 중심으로

Terminology translation plays a key role in technical machine translation. This paper conducts quantitative and qualitative evaluation and presents a comprehensive error analysis on terminology translation from Korean to English. For this study, 637 terms are selected from a patent domain corpus. Among them, 425 terms are translated correctly while other 212 terms have one or more errors. Those identified errors are classified into seven error categories which include addition, omission, lexical errors, order errors, morphological errors, partial errors, and miscellanies. Among them, partial errors and morphological errors are the two top error categories, and lexical errors and omission cases are also high. The study also presents n-gram wise error rates. The calculation of n-gram wise terminology translation error rates shows that the curve for the Google Translation results goes upwards with the increasing size of n. This shows that neural machine translation can be vulnerable in translating a higher-order of n-gram terms. This study has implications for Korean-English machine translation research, in that it classifies error cases spotted in machine translation of terminology which is critical in securing accuracy of translations.

Equivalence and the Loss of Originality: A Comparative Study of English Translation of Selected Urdu Idioms

This study attempts to examine the impact of equivalence and the loss of originality issues in the translated Idioms from Urdu to English. Equivalence is considered a principle concept in translation theory but it is replete with problems. This paper aims to highlight the loss of originality in the selected translated idioms because these are considered as frozen patterns of language that allow a very little or almost no variation in form and their meanings cannot be taken from their individual components as per the compositionality principle. i.e. the meaning of a sentence can be deduced from the individual meaning of words. This idea of transferring the different meanings and objectives of a given text poses an important question that the researcher tries to answer in this paper. “Does translation responsible for the loss of originality for being unable to find suitable equivalents at inter-lingual situations”? After reviewing the relevant literature and analyzing different translated idioms from Urdu to English, it elucidates that the translator must be well-educated about both languages and especially for the target language in terms of its norms, social and cultural values in order to produce an accurate translation. This study is qualitative in nature. The data is collected by the observation technique and analyzed from the perspective of equivalence and loss of originality between two languages i.e. English and Urdu.

Toward English-Chinese Translation Based on Neural Networks

In traditional interactive English translation systems, English semantic context is not obvious in the process of the English translation, and the selection of optimal feature semantics does not reach the optimal translation solution, which leads to low translation accuracy. Toward this solation, a neural network (NN) based translation approach is proposed to predict word order differences in language translation and improve translation accuracy in long sentences. In this study, a multilayer NN model has been established to victories the unlabeled text words, realize the combination of word representation, vector features, and extract effective information of various sentences and semantics. In linear ranking frameworks, the NN is used to rank and score words, obtain semantic information of sample data, and predict the difference of word order. Experimental results show that the NN preorder model can significantly improve translation accuracy and system performance. The application of NN-based translation model in the practical translation process can reduce the effort of translation work, improve the efficiency of translation, and has a good practical significance.

Learning the two translations of translation-ambiguous words: Simultaneous vs. consecutive presentation

Some words have more than one translation across languages. Such translation-ambiguous words are harder to learn, recognize, and produce for individuals across the language learning spectrum. Past research demonstrates that learning both translations of translation-ambiguous words on consecutive trials confers an accuracy advantage relative to learning them on separate sessions. We tested the proposal that presenting the two translations of translation-ambiguous words simultaneously on the screen could facilitate the formation of a more integrated mapping, because this would enable learners to make direct comparisons between them, whether implicitly or explicitly. We predicted that this facilitation would especially hold for translation-ambiguous words with related translations. Fifty native English speakers learned 48 German words with one or two translations that varied in the meaning similarity of their translations. Paired associate training took place on a Monday, and a first language (L1) to second language (L2) translation production test took place on Wednesday and Friday. Generally, higher translation similarity facilitated translation speed. In accuracy, training condition interacted with the similarity of the translations; translation accuracy was more affected by translation similarity in the simultaneous condition and went up as similarity increased. Overall, the consecutive condition demonstrated higher accuracy and faster reaction times than the simultaneous training condition, suggesting that learners may have been unable to successfully divide their study time between multiple words on the screen without explicit instruction.

Research on Cultural Translation Based on Neural Network

The translation of pragmatic meaning requires the processing of pragmatic implicit meaning, the translator’s responsibility for the readers of the target language to understand the pragmatic meaning, and the domestication and foreignization of cultural images. The way of pragmatic language equivalence is domestication translation to achieve the fluency of language expression. The creation of foreignized translation in order to foster the equitable interchange and dissemination of culture, which is precisely the aim of cultural translation, is the equivalence of the pragmatic meaning of cultural imagery. Neural network (NN) machine translation technology (MTT) simulates the human brain nervous system. Based on deep learning technology, the whole sentence is used as the basic unit of translation, which greatly improves the accuracy of machine translation. This paper selects the relevant texts of Shaanxi’s red tourism culture and uses the NN translation system to translate. It helps to improve the accuracy of the text translation of Shaanxi red tourism culture by analyzing the translation and providing a reference direction for further revision by neural translation users and promote the overseas dissemination of red culture. The part of the source language side that generates a vector representation of a dense and continuous sentence from the input corresponds to the encoder.

ATA2022 Annual Conference &amp; Expo May 1–3, 2022Boston, Massachusetts

ATA2022 Annual Conference &amp; Expo May 1–3, 2022Boston, Massachusetts

An Analysis of Students’ Strategies in Translating Idioms: A Case Study of English Department of Sultan Ageng Tirtayasa University

The objectives of this research are to find out (1) the strategies that students used by the 6th semester of the English Department of Teacher Training and Education faculty of UNTIRTA in translating idioms and (2) the accuracy of translating idioms by students in the 6th semester of English Department of Teacher Training and Education faculty of UNTIRTA. The researcher used the qualitative research method by applying content analysis research design in conducting the research. In analyzing the idioms and students' translation, theories by Baker (2011) and Nababan (2012) were used. The result of this research showed that: First, there are 3 out of 5 strategies in translating idioms by Baker's theory used by the students (1) using an idiom with similar meaning but different form (1.5%), (2) translation by paraphrase (85.4%), and (3) translation by omission (13%). The most frequent translation strategies used in translating the idioms are translation by paraphrase. Second, the accuracy of translated results by the students showed that 78 data (23.6%) were accurate, 126 data (38.2%) were less accurate, and 126 data (38.2%) were less accurate. So, the accuracy of translation of idioms in A Little Life Philosophy text by students is less accurate and not accurate.

Translation and validation of Arabic version of maternal responsiveness questionnaire

Objectives: Aim to translate the original maternal responsiveness questionnaire from English to Arabic language and validate it. In addition to achieving equivalence between the original and adapted questionnaire. Method: maternal responsiveness questionnaire was translated into the Arabic language by using the WHO guideline of translation technique (translation – back translation and bilingual technique). A cross-cultural study design was used in this study to adapt the English version of the instrument to the new version in the Arabic language. Results: The translated Arabic maternal responsiveness questionnaire demonstrated a high degree of accuracy of translation and high estimates of content validity (S-CVI/Ave =0.96) and the Cronbach alpha showed a high level of internal consistency for questionnaire sub-scale as follow; 0.85 for responsiveness; 0.89 for delayed responsiveness; and 0.73 for non-responsiveness. Conclusion: The Arabic version of the maternal responsiveness questionnaire is highly reliable and has sufficient content validity and a culturally adapted form that can be used to measure the maternal responsiveness for Arabic-speaking mothers.

An Integrated Approach of TBLT and GBP to Medical Translation Instruction: A Suggested Model

Producing an accurate translation means communicating meaning successfully to target text's recipients. It also implies preserving the various relations (i.e., how each linguistic form suggests meaning with regard to a specific context) that the source text exhibits. Hence, translators should first analyze the source text before producing its translation. Medical translation is a technical translation and includes various text types that do not form a homogenous group. However, translator trainers focus only on one text type in class, and less exposure to other text types is expected. The current proposal is based on a needs analysis, based on two types of questionnaires, unstructured interviews, and document analysis of course descriptions and specifications, that aimed at identifying translators' target needs at the English Language Program at the college of Languages and Translation (COLT). Thus, this article suggests an integrated approach of Task-Based Language Teaching (TBLT) and (Genre-Based Pedagogy) GBP for medical translation instruction where attention is paid to text analysis. As TBLT enhances interactivity, critical thinking, problem solving, learner autonomy, etc., GBP encourages the exposure to various genre conventions and enhances textual analysis. The suggested integrated model is of three stages (i.e., pre-tasking, tasking, post-tasking including reporting, analysis, revision, and reflection) and ensures activating a number of components in the translation competence. Besides proposing a model to follow in class, the researcher designed a syllabus that gives importance to certain genres (e.g., forms, emails, policies, terms and conditions, reports, etc.), skills (e.g., using dictionaries, having good research skills, using technology, and time management), and evaluation criteria.

Interpersonal Interface System of Multimedia Intelligent English Translation Based on Deep Learning

Artificial intelligence is a very challenging science, and people who are engaged in this work must understand computer knowledge, psychology, and philosophy. Artificial intelligence includes a wide range of sciences; it is composed of different fields, such as machine learning and computer vision. In recent years, with the rise and joint drive of technologies such as the Internet, big data, the Internet of Things, and voice recognition, the rapid development of artificial intelligence technology has presented new features such as deep learning, cross-border integration, and human-machine collaboration. Intelligent English translation is an innovation and experiment of the English language industry in the field of science and technology. Machine translation is the use of computer programmes to translate natural language into a specific natural language. This interdisciplinary subject includes three subjects: artificial intelligence, computational linguistics, and mathematical logic. Machine translation is becoming more and more popular with the public, and its advantages are mainly that machine translation is much cheaper than manual translation. From this study, it can be seen that the accuracy rate of the traditional ICTCLAS method is 76.40%, while the accuracy rate of the research method in this article is 94.58%, indicating that the research method used in this article is better. Machine translation greatly reduces the cost of translation because there are very few processes that require human participation, and the translation is basically done by computers. It is also an important research content in the field of English major research. Due to the wide range of language cultures and the influence of local culture, thought, and semantic environment, traditional human translation methods have many shortcomings. Nowadays, the demand for translation is unsatisfactory. Based on this, this paper analyzes the application status of intelligent translation, the prospect of intelligent translation, and realizes the optimization design of the human interface system for the intelligent translation of English. Through experiments, it is found that the multimedia intelligent English translation system based on deep learning not only improves the accuracy of English translation but also greatly improves the efficiency of people learning English.

Translation Strategy and Accuracy in Balinese Terms

This research attempts to find out the strategy used by the translator in translating Balinese terms also to explain the accuracy of the translated terms. The data used in this research were in the form of phrases in the book entitled Tigang Satua Bali by Sutjaja (2007). The data collection was done through reading and note taking techniques. The data then were analyzed using theory of translation strategy and accuracy. The result showed that the strategy used within the translation of Balinese terms into target languages (Indonesian and English) are translation by paraphrase, related word, loan phrase, and cultural substitution. Then the accuracy levels of the translation strategy are in three criteria, namely correct, misguided, and unclear.&#x0D; &#x0D;

한영 법령 번역 품질 제고를 위한 번역 방식에 관한 소고 — 직역 문제를 중심으로 —

Literal translation has been a long tradition in legal translation. However, rigid literal translation has lost ground in modern legal translation and given way to sense-for-sense, idiomatic translation. Drawing on the literature on legal translation, this paper examines controversies surrounding literal translation and idiomatic translation in legal translation and seeks ways to improve the quality of Korea statutory translation provided by the Korea Legislation Research Institute. Despite the proclaimed principle of accurate and natural translation that is comprehensible to native speakers of English, literal translation is prevalent in the Institute’s statutory translation, which undermines its translation service quality. Based on a small corpus of Korean-English statutory translation by the Institute, this paper examines instances of literal translation which realized lexical and syntactic equivalence in preference to natural and idiomatic translation. The analysis also shed some light on legal translation strategies based on a recipient-oriented approach and calls for further research on legal translation strategies and legal translation training.

Chinese language learners evaluating machine translation accuracy

Chinese language learners evaluating machine translation accuracy

CATEGORY SHIFT USED IN NOUN PRHASE AND ITS QUALITY IN THE NOVEL DIVERGENT

The aims of this research were to find the type of category shift, and quality assessment of noun phrase translation in the novel Divergent. Based on theory Catford (1965). Also, theory Nababan (2012) for quality assessment. This research used a descriptive–qualitative method. To achieve the aims of this study, the researcher used some techniques to analyze the data such as reading and collecting data, underlining the type of category shift in the text of the novel, categorizing types of translation shift, assessing translation accuracy, assessing translation readability and acceptability. Based on the data analysis, it was found that 92% of the data were accurate because the category shift of noun phrase in the target language has equivalent meaning with the source language; 6% of the data were less accurate because the category shift of noun phrase had no equal meaning with the source language and the equivalence seemed less natural, and 2% of the data were not accurate. Meanwhile, 93% of the data were readable because the translation was very easy to understand; 5% of the data were less readable because the translation was not very easy to understand, and 2% of the data were unreadable because the translation was difficult to understand. Furthermore, 92% of the data were acceptable because the translation sounds natural; the words, phrases, clauses, and sentences of the source text, 6% of data were less acceptable, and 2% of data were not acceptable. The dominant data of category shift are the structure shift which got the percentage of 56%, followed by intra-system shift 32%, class shift 8%, and unit shift 4 %.

Improved neural machine translation for low-resource English–Assamese pair

Language translation is essential to bring the world closer and plays a significant part in building a community among people of different linguistic backgrounds. Machine translation dramatically helps in removing the language barrier and allows easier communication among linguistically diverse communities. Due to the unavailability of resources, major languages of the world are accounted as low-resource languages. This leads to a challenging task of automating translation among various such languages to benefit indigenous speakers. This article investigates neural machine translation for the English–Assamese resource-poor language pair by tackling insufficient data and out-of-vocabulary problems. We have also proposed an approach of data augmentation-based NMT, which exploits synthetic parallel data and shows significantly improved translation accuracy for English-to-Assamese and Assamese-to-English translation and obtained state-of-the-art results.

Hierarchical Triple Model of Hybrid Neural Machine Translation

For more than a decade, PMT and SMT models have dominated the field of machine translation, and neural machine translation has emerged as a new paradigm for machine translation by the 2015. Neural machine translation provides a simple modeling mechanism that is easy to use in practice and science. Thus, it does not require concepts such as word ranking, a key component of the statistical machine translation. While this simplicity may be seen as an advantage, on the other hand, the lack of careful spelling is to lose control of the translation. Even tough, the neural machine translation is more flexible in terms of translations that don’t exactly match the training data. This provides more opportunities for such models, but exempts translation from pre-determined restrictions. Failure to connect specific words can make it difficult to connect the target words you create to the original word. The widespread use of neural machine translation system has the advantage of allowing users to translate certain terms and translate uneducated data to a certain extent. In some cases, however, the structure and the grammar boundary of a sentence is often distorted. The paper is intended to address issues such as the control of neural machine translation, more accurate translation of unidentified data, the accuracy of sentence structure and grammar boundaries. To solve this problem, modern translation theory led to the hybrid model of machine translation. Our model is expansion of this hybrid model with a sentence and a grammar boundary. We named this model as hierarchical triple model (HTM).

Aspects of translating scientific and technical texts from english into russian for specialists with technical education

This article analyzes various difficulties that are usually encountered by specialists with technical education when translating scientific and technical texts. And although the purpose of any translation is to convey the content of any text as accurately as possible, nevertheless, one should not forget about the peculiarities of translating scientific and technical texts. In most English scientific and technical texts there is a huge number of technical terms, and much more than in European languages. Therefore, when translating such kind of texts, it is necessary to take into account their specifics and, accordingly, competently select the means for the most accurate translation of the content of such texts, while preserving its lexical, grammatical and substantive aspects.

Automatic Real-Time Pose Estimation of Machinery from Images.

The automatic positioning of machines in a large number of application areas is an important aspect of automation. Today, this is often done using classic geodetic sensors such as Global Navigation Satellite Systems (GNSS) and robotic total stations. In this work, a stereo camera system was developed that localizes a machine at high frequency and serves as an alternative to the previously mentioned sensors. For this purpose, algorithms were developed that detect active markers on the machine in a stereo image pair, find stereo point correspondences, and estimate the pose of the machine from these. Theoretical influences and accuracies for different systems were estimated with a Monte Carlo simulation, on the basis of which the stereo camera system was designed. Field measurements were used to evaluate the actual achievable accuracies and the robustness of the prototype system. The comparison is present with reference measurements with a laser tracker. The estimated object pose achieved accuracies higher than with the translation components and accuracies higher than with the rotation components. As a result, 3D point accuracies higher than were achieved by the machine. For the first time, a prototype could be developed that represents an alternative, powerful image-based localization method for machines to the classical geodetic sensors.