Applying assessment holistic method to the translation exam in Yemen

Babel ◽  
2016 ◽  
Vol 62 (1) ◽  
pp. 135-149 ◽  
Author(s):  
Adel Salem Bahameed
Keyword(s):  
Quality Assessment ◽  
Female Students ◽  
Assessment Process ◽  
Final Exam ◽  
Translation Quality ◽  
Holistic Method ◽  
Method Of Assessment ◽  
Main Factor

This paper is an attempt to guide the teachers how the assessment process should be and it highlights the effectiveness and suitability of adopting the holistic method of assessment. This method was applied to the correction of students’ translations of the final exam containing different texts to be translated in both directions between English and Arabic. The exam was done by 36 female students at the Faculty for Women – Seiyun, Yemen on the undergraduate degree course of Translation (2). The hypothesis regarding the suitability and effectiveness of using the assessment holistic method and the possibility to improve the quality of the assessing the students’ translations in future based on this method has not been verified. This study concluded that the main factor which is clearly identifiable was translation competence and that this method was found out to be too lenient to give impartial translation quality assessment for the students’ translations.

scholarly journals Toward an Automatic Quality Assessment of Voice-Based Telemedicine Consultations: A Deep Learning Approach

Sensors ◽  
2021 ◽  
Vol 21 (9) ◽  
pp. 3279
Author(s):  
Maria Habib ◽  
Mohammad Faris ◽  
Raneem Qaddoura ◽  
Manal Alomari ◽  
Alaa Alomari ◽  
...  
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Quality Assessment ◽  
Transcript Level ◽  
Assessment Process ◽  
Classification Model ◽  
Systematic Evaluation ◽  
Transcript Levels ◽  
Perceptual Evaluation

Maintaining a high quality of conversation between doctors and patients is essential in telehealth services, where efficient and competent communication is important to promote patient health. Assessing the quality of medical conversations is often handled based on a human auditory-perceptual evaluation. Typically, trained experts are needed for such tasks, as they follow systematic evaluation criteria. However, the daily rapid increase of consultations makes the evaluation process inefficient and impractical. This paper investigates the automation of the quality assessment process of patient–doctor voice-based conversations in a telehealth service using a deep-learning-based classification model. For this, the data consist of audio recordings obtained from Altibbi. Altibbi is a digital health platform that provides telemedicine and telehealth services in the Middle East and North Africa (MENA). The objective is to assist Altibbi’s operations team in the evaluation of the provided consultations in an automated manner. The proposed model is developed using three sets of features: features extracted from the signal level, the transcript level, and the signal and transcript levels. At the signal level, various statistical and spectral information is calculated to characterize the spectral envelope of the speech recordings. At the transcript level, a pre-trained embedding model is utilized to encompass the semantic and contextual features of the textual information. Additionally, the hybrid of the signal and transcript levels is explored and analyzed. The designed classification model relies on stacked layers of deep neural networks and convolutional neural networks. Evaluation results show that the model achieved a higher level of precision when compared with the manual evaluation approach followed by Altibbi’s operations team.

Development of a method for assessing the quality of machine translation based on ensemble methods in machine learning

2021 ◽  
Author(s):  
A.V. Kozina ◽  
Yu.S. Belov
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Quality Assessment ◽  
Machine Translation ◽  
Translation System ◽  
Human Judgment ◽  
Translation Quality ◽  
Machine Translation System ◽  
Translation Systems

Automatically assessing the quality of machine translation is an important yet challenging task for machine translation research. Translation quality assessment is understood as predicting translation quality without reference to the source text. Translation quality depends on the specific machine translation system and often requires post-editing. Manual editing is a long and expensive process. Since the need to quickly determine the quality of translation increases, its automation is required. In this paper, we propose a quality assessment method based on ensemble supervised machine learning methods. The bilingual corpus WMT 2019 for the EnglishRussian language pair was used as data. The text data volume is 17089 sentences, 85% of the data was used for training, and 15% for testing the model. Linguistic functions extracted from the text in the source and target languages were used as features for training the system, since it is these characteristics that can most accurately characterize the translation in terms of quality. The following tools were used for feature extraction: a free language modeling tool based on SRILM and a Stanford POS Tagger parts of speech tagger. Before training the system, the text was preprocessed. The model was trained using three regression methods: Bagging, Extra Tree, and Random Forest. The algorithms were implemented in the Python programming language using the Scikit learn library. The parameters of the random forest method have been optimized using a grid search. The performance of the model was assessed by the mean absolute error MAE and the root mean square error RMSE, as well as by the Pearsоn coefficient, which determines the correlation with human judgment. Testing was carried out using three machine translation systems: Google and Bing neural systems, Mouses statistical machine translation systems based on phrases and based on syntax. Based on the results of the work, the method of additional trees showed itself best. In addition, for all categories of indicators under consideration, the best results are achieved using the Google machine translation system. The developed method showed good results close to human judgment. The system can be used for further research in the task of assessing the quality of translation.

IQ and Reading Comprehension in Translation Quality

2017 ◽  
Vol 5 (4) ◽  
pp. 48 ◽  
Author(s):  
Mohsen Askari ◽  
Azam Samadi Rahim
Keyword(s):  
Reading Comprehension ◽  
Quality Assessment ◽  
Translation Studies ◽  
Study Data ◽  
Significant Finding ◽  
Translation Quality ◽  
Determining Factors ◽  
Almost All ◽  
Raven's Advanced Progressive Matrices

Having a deeper understanding of determining factors in the quality of translation is in the interest of almost all scholars of translation studies. Students’ intelligence is being measured constantly in order to determine their aptitude for entering into different programs. However, in translation studies, the variable of intelligence quotient (IQ) has been curiously ignored among researchers. This study aimed to explore the strength of both IQ and reading comprehension in predicting translation quality among Iranian translation students.  A sample of forty-six translation students from Alborz University of Qazvin participated in this study. Data were collected using three tests including Raven’s Advanced Progressive Matrices, Colina’s (2008) componential translation quality rating scheme and the reading comprehension test of IELTS. The results show IQ test scores and reading comprehension significantly predict translation quality assessment. Surprisingly, the most significant finding is that IQ score is by far a better predictor of translation quality than reading comprehension. Overall, it is concluded that translation quality assessment is more of a deeper cognitive function than solely language process, which could lead to more research on cognitive aspects of translation.

Method and algorithm of automatic color rendition quality assessment of digital aerial and space photos

2018 ◽  
Vol 937 (7) ◽  
pp. 45-56
Author(s):  
I.A. Anikeeva
Keyword(s):  
Quality Assessment ◽  
Experimental Verification ◽  
Experimental Check ◽  
Automatic Assessment ◽  
Assessment Criterion ◽  
Space Images ◽  
Quality Research ◽  
Research Problems ◽  
Method Of Assessment

Today the photographic quality assessment of aerial and space images is made visually, with a big deal of subjectivity. The main problems are the lack of parameters characterizing the photographic quality of images and the lack of methods for determining these parameters. The correctness of color rendition is one of the most important indicators of the photographic aerial and space images’ quality. Research problems included the developing methods for determining the color imbalance of digital images; developing the assessment criterion of color imbalance and a method of its calculation; as well as the experimental verification of the suggested method by correcting the color balance of an image. The article describes the algorithm for automatic color imbalance detection of a digital image that enables searching pixels as parts of gray field areas of an image; the value of a color imbalance is estimated by selected gray pixels. One of the most important indicators of the photographic quality of aerial and space images was determined, it is the color imbalance expressed numerically. The method of automatic assessment of color rendition correctness is offered, the criterion of estimation of color imbalance of the photographic image and a method of its calculation is specified, results of the experimental check of the offered method of assessment of color rendition correctness are given.

scholarly journals Assessing the English Translation of BFSU’s New Motto

2016 ◽  
Vol 6 (6) ◽  
pp. 45
Author(s):  
Zuqiong Ma
Keyword(s):  
Higher Education ◽  
Quality Assessment ◽  
English Translation ◽  
Social Research ◽  
Native Language ◽  
Modified Model ◽  
Translation Quality ◽  
Chinese University ◽  
Marketing Tool

<p>The motto is a potent marketing tool in today’s globalized site of higher education. Beijing Foreign Studies University (BFSU) adopted a new motto in 2011 to reflect its new self-branding as a cosmopolitan scholar-doer. Its English translation has since then triggered much discussion about quality assessment. The current study critically surveys the existing literature on translation quality assessment (TQA), in an effort to identify an appropriate framework to assess the translation of Chinese university mottos. House’s model (2015) is found the most appropriate and applied to the official translation of the BFSU motto, after being adjusted in two important aspects. One, in regard to the rise of English as a language of global communication, it is proposed that more broad-based English norms than those of English as a native language be established for the purpose of adjudicating cultural filtering. Two, the use of corpus-based contrastive pragmatics is expanded to gauge the justifiability of overt as well as covert mismatches. While the errors identified by such a modified model are better intersubjectively verifiable, it remains to see how social research can be incorporated into the system to assess the degrees different errors may impact on the perceived quality of a translation.</p>

scholarly journals Translation Quality Assessment of Proverbs from English into Arabic: The Case Study of One Thousand and One English Proverbs Translated into Arabic

2020 ◽  
Author(s):  
Bodour Abdulaziz Alfaleh
Keyword(s):  
Error Analysis ◽  
Quality Assessment ◽  
Analysis Model ◽  
Language And Culture ◽  
Lexical Choice ◽  
Translation Quality ◽  
Literal Translation ◽  
Translation Errors

Proverbs are very important in every language and culture. However, translators sometimes mistranslate them. Thus, this study sheds light on the translation quality assessment of proverbs. These proverbs are collected from One thousand and one English proverbs translated into Arabic by Omar Jabak. This study aims at pointing out the most frequently used strategies for translating proverbs, and investigating how far Na Pham's error analysis model is appropriate for the description and assessment of the strategies used in translating these proverbs. Na Pham's error analysis model is used to identify comprehension, linguistic and translation errors. Moreover, this study aims at detecting the most common errors under each strategy used. The findings of this study show that Na Pham's error analysis model is appropriate for the assessment. It also reveals that there are certain types of errors which are committed more often than others. In addition, it uncovers that the types of errors detected when translating proverbs using partial equivalence and paraphrasing are very similar. Comprehension errors, giving an inaccurate meaning, and distorting the meaning are the most frequently detected errors when translating proverbs using partial equivalents and paraphrasing. On the other hand, wrong lexical choice and too-literal translation are the most frequently detected errors when using literal translation. Finally, this study suggests solutions for improving the quality of Arabic translations of proverbs. In addition, some recommendations for further studies are suggested.

scholarly journals Teaching Specialised Translation Through Corpus Linguistics: Translation Quality Assessment and Methodology Evaluation and Enhancement by Experimental Approach

2019 ◽  
Vol 63 (3) ◽  
pp. 807-825
Author(s):  
Natalie Kübler* ◽  
Alexandra Mestivier* ◽  
Mojca Pecman*
Keyword(s):  
Quantitative Analysis ◽  
Quality Assessment ◽  
Corpus Linguistics ◽  
Experimental Approach ◽  
Global Communication ◽  
High Quality ◽  
Translation Quality ◽  
Research Material ◽  
Current Context

In the current context of rapid and constant evolution of global communication and specialised discourses, the need for devising methods for ensuring both high quality levels of specialised translation and successful translation training is becoming a true challenge. Steady renewal in knowledge paradigms leads to an increase in term coinage, modifications in lexical and phraseological patterns, and accommodations in discourse conventions. This situation requires teachers in specialised translation to train future translators to develop the skills meant to help them adapt rapidly to change. The tools brought by corpus linguistics offer access to the language-in-the-making and continuously emerging knowledge fields. However, methods for their efficient exploitation in translation classes can still be improved. In the current study, we present the translation-teaching framework devised specifically for such contexts. It is based on corpus linguistics, terminology management, collaboration with experts, and the quantitative analysis of the quality of finished translations, which can then, in turn, be used to improve the overall framework and to provide research material on specialised translation problems.

scholarly journals Learners’ Difficulties in Self-evaluation in English Vietnamese Translation Quality Assessment

2020 ◽  
Vol 3 (10) ◽  
pp. 156-163
Author(s):  
Tri Minh Nguyen ◽  
Trang Xuan Phuong Dao
Keyword(s):  
Quality Assessment ◽  
Mixed Method ◽  
Time Constraints ◽  
Translation Process ◽  
Independent Basis ◽  
Self Evaluation ◽  
Translation Quality ◽  
University Curriculum ◽  
Target Culture

The field of English translation and interpretation has shown an increasing popularity in Vietnam in the context of globalization. However, translation in the target culture still has a certain number of problems in transferring the equivalence between two languages, which causes some ambiguities and misunderstandings for readers (House, 2015). Hence, translation quality assurance is significant in ensuring the degree of suitability of the texts as a post-translation process (Munday, 2016). This paper aimed to investigate the difficulties of English majors of translation and interpretation in assessing the quality of texts translated from English to Vietnamese during the learning process on an independent basis. The study employed the mixed method with 50 fourth-year students at Nguyen Tat Thanh University via questionnaires. The findings revealed that those majors had to deal with five main groups of troubles including (1) time constraints, (2) non-equivalence between English and Vietnamese, (3) insufficient cultural understandings, (4) inadequate supports from lecturers, and especially (5) the lack of official framework for translation quality assessment. This paper also proposes the fundamental for university curriculum developments from the learners’ perspectives.

scholarly journals Teknik dan Kualitas Penerjemahan Frasa Washfi pada Novel Zeina Karya Nawal El Sadawi

2021 ◽  
Vol 4 (1) ◽  
pp. 66-98
Author(s):  
Aditya Prayogo ◽  
Fitria Sari Yunianti
Keyword(s):  
Quality Assessment ◽  
Descriptive Analysis ◽  
Qualitative Approach ◽  
The Novel ◽  
Analysis Method ◽  
Translation Quality ◽  
Literal Translation ◽  
Translation Technique ◽  
Translation Techniques

This research explain the techniques and quality assessment of the translation of washfi phrases in the novel Zeina's translation by Nawal El Saadawi. This research is a part of translation criticism by using the descriptive analysis method. This research uses a qualitative approach in analyzing translation techniques by applying Newmark's theory of translation techniques. In addition, a quantitative approach is also used in assessing the quality of translation by applying the theory of translation quality assessment by Nababan. The results of this research indicate that there are 348 data on washfi phrases in the novel Zeina and 40 data on washfi phrases in this study. The techniques used in translation are 10 of 16 Newmark translation techniques. The ten techniques are literal translation technique, transference, reduction, expansion, transposition, synonymy, modulation, naturalization, paraphrasing, and recognized translation technique. As for the assessment of translation quality, the most acceptable translation qualities were literal translation techniques and synonymy techniques (77%). Meanwhile, the lowest acceptance quality was naturalization technique, which was 62%. Then, the quality of easy / high readability is in the paraphrasing technique, which is 76%. While the quality of the lowest readability is naturalization technique, which is 46%.

scholarly journals Data Quality Assessment and the Long-Term Trend of Ground Solar Radiation in China

2008 ◽  
Vol 47 (4) ◽  
pp. 1006-1016 ◽  
Author(s):  
Guang-Yu Shi ◽  
Tadahiro Hayasaka ◽  
Atsumu Ohmura ◽  
Zhi-Hua Chen ◽  
Biao Wang ◽  
...  
Keyword(s):  
Time Series ◽  
Solar Radiation ◽  
Data Quality ◽  
Quality Assessment ◽  
Global Radiation ◽  
Assessment Process ◽  
Radiation Data ◽  
Data Quality Assessment

Abstract Solar radiation is one of the most important factors affecting climate and the environment. Routine measurements of irradiance are valuable for climate change research because of long time series and areal coverage. In this study, a set of quality assessment (QA) algorithms is used to test the quality of daily solar global, direct, and diffuse radiation measurements taken at 122 observatories in China during 1957–2000. The QA algorithms include a physical threshold test (QA1), a global radiation sunshine duration test (QA2), and a standard deviation test applied to time series of annually averaged solar global radiation (QA3). The results show that the percentages of global, direct, and diffuse solar radiation data that fail to pass QA1 are 3.07%, 0.01%, and 2.52%, respectively; the percentages of global solar radiation data that fail to pass the QA2 and QA3 are 0.77% and 0.49%, respectively. The method implemented by the Global Energy Balance Archive is also applied to check the data quality of solar radiation in China. Of the 84 stations with a time series longer that 20 yr, suspect data at 35 of the sites were found. Based on data that passed the QA tests, trends in ground solar radiation and the effect of the data quality assessment on the trends are analyzed. There is a decrease in ground solar global and direct radiation in China over the years under study. Although the quality assessment process has significant effects on the data from individual stations and/or time periods, it does not affect the long-term trends in the data.

Sign in / Sign up

Export Citation Format

Share Document