Search

Unlike traditional SMS or MMS, messaging apps offer a broader range of data transmission capabilities. The application utilizes a WIFI or internet connection and enables users to exchange information through various means such as text, voice, and multimedia files. However, popular messaging applications such as WeChat, Telegram, and WhatsApp have limitations in language translation and file uploading size. Thus, this project aims to address these limitations by developing a social messaging application that serves as a comprehensive communication tool. The application will facilitate both written and verbal communication by providing translation services for various languages, including voice messages. The proposed application intends to act as a versatile platform, functioning as a translator while enabling seamless communication between users in different languages. Translation accuracy and BLEU metric are applied to evaluate the efficacy of the enhanced social messaging application. The proposed application is able to translate voice and written messages into another language with the help of Google translation API as well as Speech to text API. The BLEU average score between English and Malay is 0.94 but the translation between Malay and Chinese is 0.82, Chinese and English is 0.70. Though not perfect, the proposed application can enhance the current social messaging application with the speech-to-text feature and message translation feature. Last but not least, a concluding remark is provided to further improve the application in future. [ABSTRACT FROM AUTHOR]

In the context of a more linked and globalized society, the significance of proficient cross-cultural communication has been increasing to a position of utmost importance. Language functions as a crucial medium that establishes connections among people, corporations, and countries, demanding the implementation of precise and effective translation systems. This comprehensive review paper aims to contribute to the evolving landscape of AI-driven language translation by critically examining the existing literature, identifying key debates, and uncovering areas of innovation and limitations. The primary objective is to provide a nuanced understanding of the current state of AI-driven language translation, emphasizing the advancements, challenges, and ethical considerations. In this review, ongoing debates surrounding AI-driven language translations were actively involved. By evaluating different viewpoints and methodologies, insights into unresolved questions that contribute to a broader discourse in the field were provided. The future trajectory of this study involves the incorporation of cross-lingual dialect adaptability and the advancement of Artificial Intelligence translation systems, with a focus on prioritizing inclusion and cultural understanding.

Abstract Global disease registries are critical to capturing common patient related information on rare illnesses, allowing patients and their families to provide information about their condition in a safe, accessible, and engaging manner that enables researchers to undertake critical research aimed at improving outcomes. Typically, English is the default language of choice for these global digital health platforms. Unfortunately, language barriers can significantly inhibit participation from non-English speaking participants. In addition, there is potential for compromises in data quality and completeness. In contrast, multinational commercial entities provide access to their websites in the local language of the country they are operating in, and often provide multiple options reflecting ethnic diversity. This paper presents a case study of how the Global Angelman Syndrome Registry (GASR) has used a novel approach to enable multiple language translations for its website. Using a “semi-automated language translation” approach, the GASR, which was originally launched in English in September 2016, is now available in several other languages. In 2020, the GASR adopted a novel approach using crowd-sourcing and machine translation tools leading to the availability of the GASR in Spanish, Traditional Chinese, Italian, and Hindi. As a result, enrolments increased by 124% percent for Spain, 67% percent for Latin America, 46% percent for Asia, 24% for Italy, and 43% for India. We describe our approach here, which we believe presents an opportunity for cost-effective and timely translations responsive to changes to the registry and helps build and maintain engagement with global disease communities.

Global disease registries are critical to capturing common patient related information on rare illnesses, allowing patients and their families to provide information about their condition in a safe, accessible, and engaging manner that enables researchers to undertake critical research aimed at improving outcomes. Typically, English is the default language of choice for these global digital health platforms. Unfortunately, language barriers can significantly inhibit participation from non-English speaking participants. In addition, there is potential for compromises in data quality and completeness. In contrast, multinational commercial entities provide access to their websites in the local language of the country they are operating in, and often provide multiple options reflecting ethnic diversity. This paper presents a case study of how the Global Angelman Syndrome Registry (GASR) has used a novel approach to enable multiple language translations for its website. Using a "semi-automated language translation" approach, the GASR, which was originally launched in English in September 2016, is now available in several other languages. In 2020, the GASR adopted a novel approach using crowd-sourcing and machine translation tools leading to the availability of the GASR in Spanish, Traditional Chinese, Italian, and Hindi. As a result, enrolments increased by 124% percent for Spain, 67% percent for Latin America, 46% percent for Asia, 24% for Italy, and 43% for India. We describe our approach here, which we believe presents an opportunity for cost-effective and timely translations responsive to changes to the registry and helps build and maintain engagement with global disease communities. [ABSTRACT FROM AUTHOR]

A computer-aided language translation using a Machine translation (MT) is an application performed by computers (machines) that translates one natural language to another. There are many online language translation tools, but thus far none offers a sequence of text translations for the under-resourced Kadazandusun language. Although there are web-based and mobile applications of Kadazandusun dictionaries available, the systems do not translate more than one word. Hence, this paper aims to present the discussion of the preliminary translation of Malay to Kadazandusun. The basic word-to-word with dictionary alignment translation based on Direct Machine Translation (DMT) is selected to begin the exploration of the translation domain where DMT is one of the earliest translation methods which relies on the word-to-word approach (sequence-to-sequence model). This paper aims to investigate the under-resourced language and the task of translating from the Malay language to the Kadazandusun language or vice versa. This paper presents the application and the process as well as the results of the system according to the basic Kadazandusun word arrangement (Verb-Subject-Object) and its translation quality using the Bilingual Evaluation Understudy (BLEU) score. Several phases are involved during the process, including data collection (word pair translation), preprocessing, text selection, translation procedures, and performance evaluation. The preliminary language translation approach is proven to be capable of producing up to 0.5 BLEU scores which indicate that the translation is readable, however, requires post-editing for better comprehension. The findings are significant for the quality of the under-resourced language translation and as a starting point for other machine translation methodologies such as statistical or deep learning-based translation. [ABSTRACT FROM AUTHOR]

This paper examines indigenous epistemologies and the ways in which oral/verbal forms contribute to the archive of a people. By placing the central focus on the 66þ communities who identify under the exonym “Naga” situated across Assam, Manipur, Nagaland, and parts of Arunachal in the north- eastern part of India, the essay hopes to study emerging literature of the Nagas who are striving to find commonality between the language of speech and the language of writing. [ABSTRACT FROM AUTHOR]

Language access barriers for individuals with limited-English proficiency are a challenge to advance care planning (ACP). Whether Spanish-language translations of ACP resources are broadly acceptable by US Spanish-language speakers from diverse countries is unclear. This ethnographic qualitative study ascertained challenges and facilitators to ACP with respect to Spanish-language translation of ACP resources. We conducted focus groups with a heterogeneous sample of 29 Spanish-speaking persons who had experience with ACP as a patient, family member, and/or medical interpreter. We conducted thematic analysis with axial coding. Themes include: (1). ACP translations are confusing; (2). ACP understanding is affected by country of origin; (3). ACP understanding is affected by local healthcare provider culture and practice; and (4). ACP needs to be normalized into local communities. ACP is both a cultural and clinical practice. Recommendations for increasing ACP uptake extend beyond language translation to acknowledging users' culture of origin and local healthcare culture. [ABSTRACT FROM AUTHOR]

Visual impairment can affect a student's ability to learn since their concept development when interacting with educational material is being limited. Learning activities based on images and visually rich content are mainstream learning methods, where facilitating students with visual impairments for engaged learning can be challenging. For comic books, which have shown promising results in engaged student learning, this problem is more severe. To overcome this challenge, this research presents a novel voice synthesised learning method to reduce the gap between the learning experience of a student with visual impairments compared to a mainstream learning activity. Utilising comic books, the proposed technique and the tool developed extracts semantic content, stores them in a database, and generates an audio stream in multiple languages on the user's demand. To assess the usability of the system, a survey for a selected set of students with visual impairments was carried out. The results showed a mean rating of 5.76 out of 7 for the Informative Interest. Furthermore, a concept-mapping approach was used to analyse the feedback given through the open-ended questions. From the analysis, key concepts with an emphasis on positive emotions, willingness to try again, and features to be improved, were identified. [ABSTRACT FROM AUTHOR]

Improvements in the skills of language interpreters are crucial to the growth of communicative communities. Information and communication technology (ICT)-enhanced media for language education and teaching across various subject areas have developed rapidly in recent years. With its unique characteristics, grammatical learning rates are among the most challenging places for learning the language. Still, even the most cutting-edge e-learning technologies have been poorly implemented and underexplored. This study introduces an internet-of-things-assisted smart english language translation and grammar learning (ISLTGL) platform. The study uses the internet of things (IoT) to perform linguistic modeling and reliability tests. On integrating interactive features to aid in designing an information-assisted translation system. The translator still risks introducing grammatical errors into the target language version of the source text when using the conventional translation approach. The offered translation approach facilitates students' reading of English to comprehend literature. Based on this principle, develop and implement an interactive English translation and grammar learning procedure using corpus and text data sets. This method makes the translation shorter and clearer and effectively addresses the problems of massive volumes of text and significant problems of expression. The system analyzes the translation outputs statistically to assess their accuracy and completeness, providing a benchmark for the ultimate function realization. To help students learn English grammar, the ISLTGL combines the IoT system with the current English language translator. The experimental results demonstrated that ISLTGL improves student participation (97.3%), increases fluency (98.4%), boosts efficiency (94.4%), increases satisfaction (90.7%), and predicts words and sentences (95.7%) with the maximum efficiency compared to current methods for teaching English. [ABSTRACT FROM AUTHOR]

The Coping Expectancies Scale (CES) assesses beliefs about the effectiveness of particular coping strategies, with respect to mood regulation (i.e., whether or not a given coping strategy will make them feel better). The current research sought to develop and validate a French version of the Coping Expectancies Scale (CES-F). In Study 1, researchers translated the CES into French in a systematic way and evaluated the equivalence of the translation by administering the scale in both languages to bilingual participants. In Study 2, researchers administered the CES-F to an international sample of French speakers to evaluate its factor structure and convergent validity. The CES-F was found to contain four factors that reflect recognized dimensions of coping in the literature. Subscale scores generally correlate in expected directions with conceptually related measures. The CES-F may be useful in understanding beliefs about coping in French-speaking populations and ultimately helping individuals to cope more effectively. [ABSTRACT FROM AUTHOR]

Information about genetic engineering (GE) for vector control in the United States is disseminated primarily in English, though non-English speakers are equally, and in some geographic regions even more affected by such technologies. Non-English-speaking publics should have equal access to such information, which is especially critical when the technology in question may impact whole communities. We convened an interdisciplinary workgroup to translate previously developed narrated slideshows on gene drive mosquitoes from English into Spanish, reviewing each iteration for scientific accuracy and accessibility to laypeople. Using the finalised stimuli, we conducted five online, chat-based focus groups with Spanish-speaking adults from California. Overall, participants expressed interest in the topic and were able to summarise the information presented in their own words. Importantly, participants asked for clarification and expressed scepticism about the information presented, indicating critical engagement with the material. Through collaboration with Spanish-speaking scientists engaged in the development of GE methods of vector control, we translated highly technical scientific information into Spanish that successfully engaged Spanish-speaking participants in conversations about this topic. In this manuscript, we document the feasibility of consulting Spanish-speaking publics about a complex emerging technology by drawing on the linguistic diversity of the scientific teams developing the technology.

With the rise of AI and Deep Learning technologies, it is now possible to give the visually impaired a sense of sight. This work intends to propose a system, which helps the blind to perceive their surrounding without any extra hand. The system harnesses the power of revolutionary cloud technology, cutting-edge artificial intelligence systems and state of the art language translation technologies for the inevitable cause of assisting the blind. This work mainly focusses on developing a simple gesture-controlled cloud based mobile application, which would allow them to capture their surroundings and help them to navigate through their surroundings in real-time. In this work a real case system architecture is proposed which would analyse the spatial reference of objects in the image and also the custom trained NLP engine generates a description that is narrated in their own native language which stands the unique aspect of the work. The proposed application proves to be a one-stop solution for the visually impaired with real case analysis. To strengthen the analysis of the work, results pertaining to the system architecture emphasising its real-time performance and accessibility are done. [ABSTRACT FROM AUTHOR]

As the U.S. grows more diverse, researchers decide how to include non-English speakers. Budget limitations may not allow for translation of all instruments. Study teams must determine which instruments must receive certified translations. This paper describes the procedures utilized in one U.S.-based, multi-site clinical trial to decide which study instruments should undergo certified translation and discusses dialect review procedures. The team determined which instruments (n = 31) would be translated using a qualitative evaluation to determine the need to obtain a Spanish-language certified translation: 1) "Could the meaning of these questions change (and potentially elicit a different response) if the translations were not consistent?" and 2) "Is it acceptable to have potential inconsistencies in these data?" Instruments for which question 1 was "yes" and question 2 was "no" (e.g., eligibility, outcomes, safety) were marked for certified translation. A dialect committee reviewed all translated patient-reported outcome measures to ensure that the translations had accounted for different meanings of words based on respondents' countries or regions of origin and recommended changes where necessary. Fourteen interview-based instruments underwent certified forward-only translation into U.S. Spanish. The remaining 2 interview-based instruments were translated via real-time conversation with participants by bilingual staff. Six forms were administrative and not translated. Five out of 9 professionally translated patient-reported outcome measures were amended to better reflect relevant dialects. In the absence of specific guidance, it is feasible for study team members to 1) determine which instruments should undergo certified translation and 2) incorporate dialect into translations. [ABSTRACT FROM AUTHOR]

(Series Information) European Papers - A Journal on Law and Integration, 2022 7(1), 465-480 | Article | (Table of Contents) I. Introduction. - II. The multilingual European Union law. - III. Guarantees of clarity in Union law. - IV. Common European legal discourse as a way to overcome relativism. - V. Conclusion. | (Abstract) The European Union as a supranational entity that unites many different legal systems, each with its own linguistic category and distinct legal vocabulary, presents unique challenges in legal translation of European legislation. This Article examines the process of legal-linguistic finalization of EU multi-lingual law and considers the difficulties arising from interpretation of EU acts in light of the linguistic diversity of the Union's 27 Member States. The inquiry reaffirms the importance of the role of the Court of Justice of the European Union to guarantee the uniform functioning of law. Joining the views of some leading researchers in the field, this Article defends the view that a shared European legal discourse is necessary to achieve clarity in European Union law.

Predicting answers for questions based on passages from Tamil and Hindi is a Question Answering (QA) task. It helps us to elicit information that is relevant to the queries from the passage. Answers are predicted by identifying the answer span from the context based on the questions. In this paper, four different approaches are used to solve the QA task for Tamil and Hindi Passages. Zero-shot transfer of QA models has been tested on the QA datasets available for Hindi and Tamil. Comparative analysis between Multilingual models that are fine-tuned using Tamil and Hindi QA datasets is carried out. In addition to that, the performance has also been evaluated after increasing the Hindi data points. As there are very few QA datasets available in Indic Languages, especially Tamil, a possible solution to overcome this challenge was tried and tested using the creation of a QA dataset for Tamil using Indic Language Translation models. Multilingual models were then used for fine-tuning with the translated Tamil QA dataset generated using Language translation and the results have been discussed. The predicted answers will be evaluated using Jaccard Similarity, Exact match (EM), and F1 Scores. [ABSTRACT FROM AUTHOR]

Objective: The National Comprehensive Cancer Network (NCCN) distress thermometer (DT) was developed as a brief screening tool for detecting distress in cancer patients. Conceptually, distress was considered a more acceptable and inclusive term than other psychological terms such as depression or anxiety. It is used extensively in the United States and other English-speaking countries. We aim to describe the translation and validation methods of the DT and describe the recommended cutoff scores used to identify cancer patients experiencing clinically significant distress.Methods: Nine bibliographic databases were searched using keywords to identify original research studies for non-English speaking countries' cancer patients. Full articles were independently assessed for inclusion and data extraction by two authors.Results: The review of 4442 articles yielded 39 articles that validated the DT. We identified 20 languages in 25 countries. In all but one country, investigators were able to agree upon a word or phrase that meant distress in their native language that was subsequently validated against standardized instruments. Asian, Middle Eastern and European counties recommended cutoff score of 4 or 5 to identify clinically significant distress; however, European Union countries had a range of 2 to 7.Conclusions: Use of the translated DT with non-English speaking cancer patients provides a simple and quick tool to identify high distress. Similar to NCCN, the cutoff score of 4 or 5 was suggested by 78% of the studies; however, more studies of different types of cancer and within and among more countries will strengthen a recommended global DT cutoff score. [ABSTRACT FROM AUTHOR]

The present article discusses the translation of linguistic poetry using through-translation. It is a translation method based on the foreignizing of translation and involves replacing the linguistic structures used in a given work with their linguistic equivalents in the target language. By applying this technique, it is possible to convey the original structures of the source language, which constitute the main element of the language poetry works. Hence, through-translation poses a suitable way to translate hapax legomena, word-formation references and puns. Moreover, this technique contributes to the preservation of the metaphors and poetic images contained in the original versions of poems. [ABSTRACT FROM AUTHOR]

Translators and authors need to transform cultural values from one language to another. The cultural values of any society are different and inter-culture harmony is achieved by sharing positive cultural values. Preserving cultural values in language translation has become a challenge. The research investigates the relationship between cultural awareness, linguistic awareness, and language translation for preserving cultural values for translation into English. Current research also aims to determine the mediating role of culture-specific items between cultural awareness and language translation. This is a cross-sectional study, and data is collected from English language translators. The research findings highlight that cultural values can be preserved when translators have information about cultural, linguistic, and culture-specific items. This research is developed on a novel idea and contributes a powerful framework to the body of knowledge. The study has remarkable theoretical and practical implications that are critically important for improving the body of knowledge by addressing the gap. Furthermore, the practical implications of this research would enhance the language translation practices of the translators to improve their better understanding of cultural values preserved in the translation. The research leads to some future directions to be addressed by scholars based on the limitations of this research. [ABSTRACT FROM AUTHOR]

Abstract Machine‐based language translation has been certainly picking up. Still, machines lag behind the cognitive powers of human beings. Neural Machine Translation (NMT) methods require huge datasets and computational power for high‐quality translation. A novel Sequential Adaptive Memory (SAM) cognitive model‐based machine translation system for English to Hindi translation, was proposed. This model is an augmented version of the Cortical Learning Algorithm (CLA). The SAM is based on the architecture of the neocortex region of the brain, where speech and language comprehension and production take place. The proposed model is capable of learning with smaller datasets. This model employs the sequence to sequence learning approach, which provides better quality translation. It enables the creation of word pairs, dictionaries, and rules for translation. The results of the proposed approach are compared with the traditional phrase‐based SMT approach as well as with the state‐of‐the‐art NMT approach. The results are comparable with the results of the conventional approaches. We illustrate that the limitations of the approaches are won over by the proposed SAM approach. It is observed that SAM is capable of exhibiting satisfactory quality translation for low resource languages as well.

Abstract More than 70 million people use at least one sign language (SL) as their main channel of communication. Nevertheless, the absence of effective mechanisms to translate massive information among sign, written and spoken languages is the main cause of a negligible inclusion of deaf people into society. Therefore, SL automatic recognition systems have widely proposed to support the characterisation of the sign structure. Today, natural and continuous SL recognition is an open research problem due to multiple spatio‐temporal shape variations, challenging visual sign characterisation, as well as the non‐linear correlation among signs to express a message. A compact sign is introduced to text architecture that explores motion as an alternative to support sign translation. Such characterisation results are robust to appearance variance with relative support to geometrical variations. The proposed representation focuses on the main spatio‐temporal regions to each corresponding word. The proposed architecture was evaluated in a built SL data set (LSCDv1) dedicated to motion study and also in the state‐of‐the‐art RWTH‐Phoenix. From the LSCDv1 data set, the best configuration reports a BLEU‐4 score of 63.04 in a testing set. Regarding RWTH‐Phoenix, the proposed strategy achieved a BLEU‐4 score in a test of 4.56, improving the results under similar reduced conditions.

Urdu is still considered a low-resource language despite being ranked as world’s $10^{th}$ most spoken language with nearly 230 million speakers. The scarcity of benchmark datasets in low-resource languages has led researchers to utilize more ingenious techniques to curb the issue. One such option widely adopted is to use language translation services to replicate existing datasets from resource-rich languages such as English to low-resource languages, such as Urdu. For most natural language processing tasks, including polarity assessment, words translated via Google translator from one language to another often change the meaning. It results in a polarity shift causing the system’s performance degradation, particularly for sentiment classification and emotion detection tasks. This study evaluates the effect of translation on the sentiment classification task from a resource-rich language to a low-resource language. It identifies and enlists words causing polarity shift into five distinct categories. It further finds the correlation between the language with similar roots. Our study shows 2-3 percentage points performance degradation in sentiment classification due to polarity shift as a result of translation from resource-rich languages to low-resource languages.

The use of computer-based technologies by non-native Arabic-speaking teachers for teaching native Arabic-speaking students can result in higher learner engagement. In this study, a machine translation (MT) system is developed as a learning technology. The proposed system can be linked to a digital podium and projector to reduce multitasking. A total of 25 students from Prince Sattam Bin Abdulaziz University, Saudi Arabia participated in our experiment and survey related to the use of the proposed technology-enhanced MT system. An important reason for using this framework is to exploit the high service bandwidth (up to several bandwidths) made available for interactive translation services. The framework is deployed by linking it to a video camera, digital podium, and projector in each classroom for the translation operation. Accordingly. After employing the system, the effect on the understanding of the students of the technical aspects of the subject that was taught using English was evaluated. The results indicated that the use of the developed technology for translation during classroom sessions was beneficial. Furthermore, the engagement of students in the classes improved their performance and learning outcomes. The students also commented that the proposed framework is useful from two perspectives: vocabulary improvement and subject comprehension. Many of the students indicated that working on assignments and homework using the framework was useful because words difficult to understand were translated. [ABSTRACT FROM AUTHOR]

The image‐to‐image translation, i.e. from source image domain to target image domain, has made significant progress in recent years. The most popular method for unpaired image‐to‐image translation is CycleGAN. However, it always cannot accurately and rapidly learn the key features in target domains. So, the CycleGAN model learns slowly and the translation quality needs to be improved. In this study, a multi‐head mutual‐attention CycleGAN (MMA‐CycleGAN) model is proposed for unpaired image‐to‐image translation. In MMA‐CycleGAN, the cycle‐consistency loss and adversarial loss in CycleGAN are still used, but a mutual‐attention (MA) mechanism is introduced, which allows attention‐driven, long‐range dependency modelling between the two image domains. Moreover, to efficiently deal with the large image size, the MA is further improved to the multi‐head mutual‐attention (MMA) mechanism. On the other hand, domain labels are adopted to simplify the MMA‐CycleGAN architecture, so only one generator is required to perform bidirectional translation tasks. Experiments on multiple datasets demonstrate MMA‐CycleGAN is able to learn rapidly and obtain photo‐realistic images in a shorter time than CycleGAN. [ABSTRACT FROM AUTHOR]

Nowadays, virtualization and real-time systems are increasingly relevant. Real-time virtual machines are adequate for closely-coupled computer systems, execute tasks from associated language only and re-target tasks to the new platform at runtime. Complex systems in space, avionics, and military applications usually operate with Loosely-Coupled Computer Systems in a real-time environment for years. In this paper, a new approach is introduced to support task transfer between loosely-coupled computers in a real-time environment to add more features without software upgrading. The approach is based on automatic source code transformation into a platform-independent “Structured Byte-Code” (SBC) and a real-time virtual machine (SBC-RVM). Unlike Ordinary virtual machines which virtualize a specific processor for a specific code only, SBC-RVM transforms source code from any language with a known grammar into SBC without re-targeting the new platform. SBC-RVM executes local or placed tasks and preserving real-time constraints and adequate for Loosely-coupled computer systems.

This paper shows the improvement in the work carried in Machine Translation as compared to the other techniques used. The work is the enhancement of "Enhancing Bi-Lingual Machine Translation Approach". It shows the development in a Language Translation using Python, which consist of predefined packages like TextBlob and Google-API. The paper talks about enhancing Bilingual Machine Translation. English language into Indian Languages like Hindi, Marathi, Gujarati, Sindhi, Punjabi, Bengali, Urdu, and Dravidian languages. The work shown in the paper is implemented using a speech_recognition module, where speech input is taken from user so as to translate into any Indian language. After comparison with various techniques and research, the paper shows efficient result up to 94% accuracy. [ABSTRACT FROM AUTHOR]

Cochrane produces independent research to improve healthcare decisions. It translates its research summaries into different languages to enable wider access, relying largely on volunteers. Machine translation (MT) could facilitate efficiency in Cochrane’s low-resource environment. We compared three off-the-shelf machine translation engines (MTEs)—DeepL, Google Translate and Microsoft Translator—for Russian translations of Cochrane plain language summaries (PLSs) by assessing the quantitative human post-editing effort within an established translation workflow and quality assurance process. 30 PLSs each were pre-translated with one of the three MTEs. Ten volunteer translators post-edited nine randomly assigned PLSs each—three per MTE—in their usual translation system, Memsource. Two editors performed a second editing step. Memsource’s Machine Translation Quality Estimation (MTQE) feature provided an artificial intelligence (AI)-powered estimate of how much editing would be required for each PLS, and the analysis feature calculated the amount of human editing after each editing step. Google Translate performed the best with highest average quality estimates for its initial MT output, and the lowest amount of human post-editing. DeepL performed slightly worse, and Microsoft Translator worst. Future developments in MT research and the associated industry may change our results.

Ellen Richards, Olivia Knowles Department of Medicine, Barts and the London School of Medicine and Dentistry, London, UKCorrespondence: Ellen RichardsDepartment of Medicine, Barts and the London School of Medicine and Dentistry, London, UKEmail richards@se13.qmul.ac.ukWe read with interest the article by Wang et al, looking into the reliability and diagnostic accuracy of Addenbrooke’s Cognitive Examination III (ACE-III), translated into Chinese, when looking at patients with mild cognitive impairment (MCI). The authors recruited 120 patients with MCI, and 136 healthy controls, and showed a positive correlation between ACE-III results and other common cognitive assessment methods (Montreal Cognitive Assessment (MoCA) and Mini-Mental State Examination (MMSE)). They also showed ACE-III to have higher diagnostic accuracy in detecting MCI when compared with the MMSE.1 We would like to thank the authors for highlighting the success of the Chinese version of ACE-III in diagnosing MCI and would like to offer some comments regarding their study.View the original paper by Wang and colleagues