What do post-editors correct? A fine-grained analysis of SMT and NMT errors

The recent improvements in neural MT (NMT) have driven a shift from statistical MT (SMT) to NMT. However, to assess the usefulness of MT models for post-editing (PE) and have a detailed insight of the output they produce, we need to analyse the most frequent errors and how they affect the task. We present a pilot study of a fine-grained analysis of MT errors based on post-editors corrections for an English to Spanish medical text translated with SMT and NMT. We use the MQM taxonomy to compare the two MT models and have a categorized classification of the errors produced. Even though results show a great variation among post-editors’ corrections, for this language combination fewer errors are corrected by post-editors in the NMT output. NMT also produces fewer accuracy errors and errors that are less critical.

Different Data Mining Approaches Based Medical Text Data

The amount of medical text data is increasing dramatically. Medical text data record the progress of medicine and imply a large amount of medical knowledge. As a natural language, they are characterized by semistructured, high-dimensional, high data volume semantics and cannot participate in arithmetic operations. Therefore, how to extract useful knowledge or information from the total available data is very important task. Using various techniques of data mining can extract valuable knowledge or information from data. In the current study, we reviewed different approaches to apply for medical text data mining. The advantages and shortcomings for each technique compared to different processes of medical text data were analyzed. We also explored the applications of algorithms for providing insights to the users and enabling them to use the resources for the specific challenges in medical text data. Further, the main challenges in medical text data mining were discussed. Findings of this paper are benefit for helping the researchers to choose the reasonable techniques for mining medical text data and presenting the main challenges to them in medical text data mining.

STRUCTURE AND CONTENT CHARACTERISTICS OF THE DISSERTATION AS A GENRE OF WRITTEN SCIENTIFIC MEDICAL TEXT IN ENGLISH

Статья посвящена описанию структурных и содержательных характеристик трактатов и диссертаций XVII века, а также современной диссертации на английском языке. Выполняется сравнительный анализ научных трудов на начальном этапе национализации медицинской науки в Великой Британии, и современных диссертаций - в период функционирования английского языка как lingua franca в мировой науке. This research is devoted to the linguistic study of English dissertations in medicine. The scientific works are represented by the genre of a written scientific medical text in English with the characteristic of functional features and they were defended in Great Britain. Diachronic research of linguistic phenomena involves the study of written scientific works and they belong to different periods of British history and medical science and it is important to correlate the studied phenomenon at different stages with the medicine development.

An Unsupervised Approach to Structuring and Analyzing Repetitive Semantic Structures in Free Text of Electronic Medical Records

Electronic Medical Records (EMR) contain a lot of valuable data about patients, which is however unstructured. There is a lack of labeled medical text data in Russian and there are no tools for automatic annotation. We present an unsupervised approach to medical data annotation. Morphological and syntactical analyses of initial sentences produce syntactic trees, from which similar subtrees are then grouped by Word2Vec and labeled using dictionaries and Wikidata categories. This method can be used to automatically label EMRs in Russian and proposed methodology can be applied to other languages, which lack resources for automatic labeling and domain vocabularies.

Medical Text Classification Using Hybrid Deep Learning Models with Multihead Attention

To unlock information present in clinical description, automatic medical text classification is highly useful in the arena of natural language processing (NLP). For medical text classification tasks, machine learning techniques seem to be quite effective; however, it requires extensive effort from human side, so that the labeled training data can be created. For clinical and translational research, a huge quantity of detailed patient information, such as disease status, lab tests, medication history, side effects, and treatment outcomes, has been collected in an electronic format, and it serves as a valuable data source for further analysis. Therefore, a huge quantity of detailed patient information is present in the medical text, and it is quite a huge challenge to process it efficiently. In this work, a medical text classification paradigm, using two novel deep learning architectures, is proposed to mitigate the human efforts. The first approach is that a quad channel hybrid long short-term memory (QC-LSTM) deep learning model is implemented utilizing four channels, and the second approach is that a hybrid bidirectional gated recurrent unit (BiGRU) deep learning model with multihead attention is developed and implemented successfully. The proposed methodology is validated on two medical text datasets, and a comprehensive analysis is conducted. The best results in terms of classification accuracy of 96.72% is obtained with the proposed QC-LSTM deep learning model, and a classification accuracy of 95.76% is obtained with the proposed hybrid BiGRU deep learning model.

The Dissemination and Practice of Primary Care Medicine by the Scholar-Gentry: A Study of Prescriptions of Local Botanicals for Emergency Use, a Medical Text of Koryŏ from the Thirteenth-Fourteenth Centuries

Prescriptions of Local Botanicals for Emergency Use (K. Hyang’yak Kugŭppang 鄕藥救急方) is the oldest medical text extant on the Korean Peninsula and known to have been compiled during the latter half of the Koryŏ 高麗 dynasty (918–1392 ce). The key value of this work lies in the dissemination and praxis of medical knowledge. First, the author used annotations in order to record Koryŏ people’s pronunciations of the names of medicinal ingredients and symptoms introduced in the main body of the text. In addition, he made use of actual empirical cases to enhance the persuasiveness of treatment methods and integrated medicine newly introduced from Song 宋 China (960–1279) into medicine familiarly used from before. Finally, he edited this text with a focus on important and simple yet efficacious treatment methods. The book continued to be used steadily following publication. It was additionally printed no fewer than twice by the government of the Chosŏn 朝鮮 dynasty (1392–1910), which ousted Koryŏ, with its clinical usefulness heightened through the supplementation of explanations on medicinal ingredients use in these processes. In particular, the quotation of sentences from Prescriptions for Emergency Use in medical texts published by the Chosŏn government implies that the utility of the medical knowledge in this work was amply acknowledged. The intended readership of the medical information in Prescriptions for Emergency Use was the not the general populace who lived in the Korean Peninsula in the thirteenth-fourteenth centuries. They not only lacked the financial means to pay physicians but also were illiterate, so that they could not even read medical texts. In order for this work to be effective, it was necessary for it to address those who could read medical texts and put their contents into practice. In the end, the author of this book assumed scholar-gentry equipped with academic knowledge as its readers and sought to provide medical information tailored to their level and to realize medical service through them. Through this work, it is possible to see in a very concrete and vivid manner how medical knowledge was disseminated and, furthermore, how medical knowledge thus disseminated was put to use in an era when medical resources were insufficient.