PECULIARITIES OF TRANSLATION OF ENGLISH LANGUAGE INSTRUCTIONS WITH THE USE OF ADDITIONAL TOOLS IN SDL TRADOS STUDIO AND MEMOQ TRANSLATOR PRO ENVIRONMENTS

The presented research focuses upon the analysis of additional specific tools (namely translation memory (TM) technologies) of SDL Trados Studio 2017 and MemoQ Translator Pro 2017 automated translation systems and their application for translation of English-language instructions into Ukrainian. With the help of the above-mentioned software tools 60 English-language operating instructions for household appliances have been translated into Ukrainian (three projects were created in both systems, each containing 10 instructions). TM is a database consisting of segments of source text (sentences, paragraphs, headings, etc.) and translations of each of these segments. TM, used in both SDL Trados Studio and MemoQ Translator Pro systems, significantly improves the quality, speed, consistency and efficiency of each translation task. SDL Trados Studio 2017 and MemoQ Translator Pro 2017 compare content of the current segment of the source file with segments of the same language already contained in the TM. If the system finds a similar segment that is currently stored in the TM, it prompts the translator to use a ready-made translation. The degree of equivalence between the segment of the source document and the segment contained in the TM is expressed as a percentage. Thus, both software tools capture the cases of «Exact match», «Perfect match» and «Fuzzy match». SDL Trados Studio 2017 andMemoQ Translator Pro 2017 slightly differ in segment statuses and colour segment marking. Both systems do not make adjustments automatically, but their identification and navigation capabilities allow one to quickly correct such errors by hand. Unfortunately, the initial focus on the Russian-language market (and, consequently, on the Russian language system) has led to another peculiarity of automated translation into Ukrainian in SDL Trados Studio and MemoQ Translator Pro systems, namely a large number of stylistic errors that require quality personalized correction.

Towards a Better Integration of Fuzzy Matches in Neural Machine Translation through Data Augmentation

We identify a number of aspects that can boost the performance of Neural Fuzzy Repair (NFR), an easy-to-implement method to integrate translation memory matches and neural machine translation (NMT). We explore various ways of maximising the added value of retrieved matches within the NFR paradigm for eight language combinations, using Transformer NMT systems. In particular, we test the impact of different fuzzy matching techniques, sub-word-level segmentation methods and alignment-based features on overall translation quality. Furthermore, we propose a fuzzy match combination technique that aims to maximise the coverage of source words. This is supplemented with an analysis of how translation quality is affected by input sentence length and fuzzy match score. The results show that applying a combination of the tested modifications leads to a significant increase in estimated translation quality over all baselines for all language combinations.

Tax Burden Shifting: What Happened in Washington, D.C., During the 2007-2009 Recession?

This study examined the effects of the 2007-2009 recession on the distribution of tax burdens within the District of Columbia by constructing a novel dataset via a fuzzy match between two administrative datasets. The findings revealed that homeowners with federal income less than zero experienced a lower tax burden, suggesting that the recession and its negative impact on income from capital gains contributed to a change in the tax burden. The findings also showed that in some cases, filers who reside in properties with high assessed values and who earn high wages accompanied by high capital losses experienced a lower tax liability and tax burden than filers with low wage income and zero or little income from capital gains. Overall, the tax burden shifted from filers with high wages and income from multiple sources to filers with low wages and zero income from other sources. The shift in the burden was primarily driven by a change in the individual income tax share of the total tax burden faced by filers, primarily those with low wages who faced a bigger burden.

Template-Based Model for Mongolian-Chinese Machine Translation

Mongolian and Chinese statistical machine translation (SMT) system has its limitation because of the complex Mongolian morphology, scarce resource of parallel corpus and the significant syntax differences. To address these problems, we propose a template-based machine translation (TBMT) system and combine it with the SMT system to achieve a better translation performance. The TBMT model we proposed includes a template extraction model and a template translation model. In the template extraction model, we present a novel method of aligning and abstracting static words from bilingual parallel corpus to extract templates automatically. In the template translation model, our specially designed method of filtering out the low quality matches can enhance the translation performance. Moreover, we apply lemmatization and Latinization to address data sparsity and do the fuzzy match. Experimentally, the coverage of TBMT system is over 50%. The combined SMT system translates all the other uncovered source sentences. The TBMT system outperforms the baselines of phrase-based and hierarchical phrase-based SMT systems for +3.08 and +1.40 BLEU points. The combined system of TBMT and SMT systems also performs better than the baselines of +2.49 and +0.81 BLEU points.

Fault Diagnosis Simulation of a Space Propulsion System Based on Fuzzy Rule Set Neural Network Method

Based on fuzzy rule sets match method which is a series of fuzzy neural networks, a system framework used for the fault diagnosis is proposed. This fault diagnosis system consists of five parts, including the extraction of fuzzy rules, fuzzy reference rule sets, the fuzzy rule scheduled to detect, the fuzzy match module and the diagnosis logic module. The extraction of fuzzy rules involves two steps: step one adaptively divides the whole space of the trained data into the subspaces in the form of hypersphere, which is expected efficiently to work out the recognition questions in the high dimension space; step two generates a fuzzy rule in each sample subspace and calculates the membership degree of each fuzzy rule. Many fuzzy reference rule sets are produced by the extraction module of fuzzy rules for the offline learning, and a fuzzy rule set to be detected is online formed while the monitoring process is happening. Beliefs estimated from the fuzzy match process of fuzzy rule sets, which indicate the existence of the working classes in the plant, the diagnosis logic module can export fault detection time, fault isolation time, fault type and fault degree. The simulation researches of the fault diagnosis in space propulsion system demonstrate the superior qualities of the fault diagnosis method on the basis of the fuzzy match of the fuzzy rule sets.

An Intuitionistic Fuzzy Set-Based Model for Intelligent Traditional Chinese Medicine Diagnosis

According to the characteristics of Traditional Chinese Medicine, this paper introduces an intuitionistic fuzzy set-based method to realize the intelligent diagnostic decision making. We firstly concentrate on diagnosis of diseases and differentiation of syndromes by modeling medical diagnosis rules via intuitionistic fuzzy relations as well as how to obtain intuitionistic medical knowledge on the basis of intuitionistic fuzzy sets. Subsequently we develop a new approach to point out the final proper diagnosis by largest degree of intuitionistic cognitive fuzzy match between symptoms characteristic for a patient and symptoms indicate the considered illnesses in decision-making process. The new approach allows reaching the intelligent diagnoses reasonably and easily, which benefit TCM syndrome differentiation for the whole diagnosis.