Automatic RadLex coding of Chinese structured radiology reports based on text similarity ensemble

Background Standardized coding of plays an important role in radiology reports’ secondary use such as data analytics, data-driven decision support, and personalized medicine. RadLex, a standard radiological lexicon, can reduce subjective variability and improve clarity in radiology reports. RadLex coding of radiology reports is widely used in many countries, but translation and localization of RadLex in China are far from being established. Although automatic RadLex coding is a common way for non-standard radiology reports, the high-accuracy cross-language RadLex coding is hardly achieved due to the limitation of up-to-date auto-translation and text similarity algorithms and still requires further research. Methods We present an effective approach that combines a hybrid translation and a Multilayer Perceptron weighting text similarity ensemble algorithm for automatic RadLex coding of Chinese structured radiology reports. Firstly, a hybrid way to integrate Google neural machine translation and dictionary translation helps to optimize the translation of Chinese radiology phrases to English. The dictionary is made up of 21,863 Chinese–English radiological term pairs extracted from several free medical dictionaries. Secondly, four typical text similarity algorithms are introduced, which are Levenshtein distance, Jaccard similarity coefficient, Word2vec Continuous bag-of-words model, and WordNet Wup similarity algorithms. Lastly, the Multilayer Perceptron model has been used to synthesize the contextual, lexical, character and syntactical information of four text similarity algorithms to promote precision, in which four similarity scores of two terms are taken as input and the output presents whether the two terms are synonyms. Results The results show the effectiveness of the approach with an F1-score of 90.15%, a precision of 91.78% and a recall of 88.59%. The hybrid translation algorithm has no negative effect on the final coding, F1-score has increased by 21.44% and 8.12% compared with the GNMT algorithm and dictionary translation. Compared with the single similarity, the result of the MLP weighting similarity algorithm is satisfactory that has a 4.48% increase compared with the best single similarity algorithm, WordNet Wup. Conclusions The paper proposed an innovative automatic cross-language RadLex coding approach to solve the standardization of Chinese structured radiology reports, that can be taken as a reference to automatic cross-language coding.

Machine-translated texts as an alternative to translated dictionaries for LIWC

Linguistic Inquiry and Word Count (LIWC) is a text analysis program developed by James Pennebaker and colleagues. At the basis of LIWC is a dictionary that assigns words to categories. This dictionary is specific to English. Researchers who want to use LIWC on non-English texts have typically relied on translations of the dictionary into the language of the texts. Dictionary translation, however, is a labour-intensive procedure. In this paper, we investigate an alternative approach: to use Machine Translation (MT) to translate the texts that must be analysed into English, and then use the English dictionary to analyse the texts. We test several LIWC versions, languages and MT engines, and consistently find the machine-translated text approach performs better than the translated-dictionary approach. We argue that for languages for which effective MT technology is available, there is no need to create new LIWC dictionary translations.

FEATURES OF TRANSLATION OF UKRAINIAN SERVICE PARTS OF SPEECH INTO ENGLISH

In the system of parts of speech functional words are important, because they serve as indicators of different relationships between words (prepositions), between words and sentences (conjunctions) or provide new words and sentence emotional shades (particles). Prepositions are function words that precede a noun or a word that replaces it, contributing to their joining phrases and sentences. Particles are functional words that are used to provide individual words or sentences more expressive and emotional connotations or creation morphological forms and new words. Conjunction is the functional part of speech that combines parts of a sentence or the sentence, expresses the semantic relations between homogeneous sentence members or parts of a complex sentence. The aim of this work is the analysis of Ukrainian functional parts of speech translation into English means. In order to illustrate translation of Ukrainian functional parts of speech in the artwork we’ve chosen a story written by V. Stefanyk «The stone cross» and its translation by A. Bilenko. This story is full of properly Ukrainian lexicon and complicated by using of Galytsky dialect. Researching the concept of functional parts of speech in modern linguistics, and the Ukrainian prepositions, particles and conjunctions dictionary translation, analysis of the Ukrainian functional words translation in the artwork allows doing the following conclusions. It was set that preposition is unchangable functional word that indicates syntactic subordination of noun (or its equivalent) to other words in the sentence or word-combination; not lexical but grammatical meaning is typical for preposition; the particle as a function word does not fulfill the nominative function, cannot be an independent member of sentences, but plays an important role in the communication process, because it provides new emotionally-expressive and semantic nuances to speech; conjunction is a word which connects two words or clauses or sentences and shows the relation between them. The study of Ukrainian functional parts of speech dictionary translation in English found that a large number of Ukrainian functional words have their equivalents in English. Particles often translated by adverbs or adjectives, prepositions and conjunctions – by their English equivalents.

Bilingual (English to Bengali) Technical E- Dictionary for Aviation OOV Words

E-dictionaries, quite common today are available for multiple languages in monolingual, bilingual and multilingual forms. In NLP they form the core of a series of tools that are used to understand words, sentences and in turn the language itself. These E-Dictionaries work well for any language domain as a whole. For almost all languages E-dictionaries are available, but once specialized technical domains are encountered these E-Dictionaries are quite useless. Aviation is one such specialized domain for which no E-Dictionary, translation or transliteration tool exist. On the other hand the need for such tools for specialized domains are increasing. The tool discussed in this paper is an attempt to bridge the gap that currently exists between English and Bengali languages.