NMT Systems Research Articles

Investigating Problems Related to the Translation of Idiomatic Expressions in the Arabic Novels Using Neural Machine Translation

NMT systems encounter many challenges and problems when rendering Arabic idiomatic expressions into English. The current research tackled some examples selected from Arabic corpora and their English translations generated by the selected NMT systems and the English versions of the selected corpora. The research presents a qualitative analysis of the selected samples from three novels (The Season of Migration to the North, the Fall of the Imam and the Girls of Riyadh). The research is mainly focusing on the problems resulted when rendering Arabic idiomatic expressions into English.

Traduction automatique et désambiguïsation des sens des mots. Le cas du verbe français louer

Machine translators such as those offered by Google, Deep, ChatGPT and others are already using NMT systems. They apply the techniques of artificial intelligence that are constantly being developed, so they are currently providing increasingly correct and suitable translations. In the first part of this article, the author examines the case of the French verb louer by having it translated in different contexts by three automatic translators mentioned to see how effective they currently are as translation tools. Next, the verb louer is presented and analyzed as seen through the prism of the Antidote 8 dictionary. The last part of the article is devoted to the French-Polish description of the verb studied using the Object-Oriented Approach, with the aim of disambiguating it and developing the system of syntactico-semantic rules (object classes, frames, scripts) enabling the appropriate automatic translation of sentences in which it may appear.

THE PROBLEM OF CORRELATION BETWEEN MANUAL AND AUTOMATIZED ASSESSMENT OF MACHINE TRANSLATION

The article under review outlines the problems of development and assessment of machine translation that can greatly facilitate global communication, despite the imperfect quality of the source text. Most often the results of online tools require post-editing and can only be effectively used by those who already speak the target language to some extent. The need for a competent translation is growing every year. Today, the search for an algorithm to deliver this quality of translation is one of the most important questions in computer science and linguistics, therefore informing the scientific relevance of this work. It is analyzed different approaches to the machine translation systems, their characteristics, efficacy and the quality of their output. Different approaches to the machine translation systems, their characteristics, efficacy and the quality of their output are analyzed in the article. The main problems we see arising from such translations goes from the fact that the systems depend on a large amount of high-quality data sets (i.e., corpora of texts for specific language pairs). The quality of these sets directly influences the quality of the output, which in our case is the quality of the target language text. It can be seen by comparing the average quality of translation between Google’s and Microsoft’s systems. The former one makes less mistakes on average and does not have as many issues in regards to identifying a contextual meaning of a polysemantic lexeme. It is underlined in the article, that this issue can be fixed to a certain extent one of two ways: hiring professional translators and linguists to compile those parallel corpora or create a possibility for every person to contribute to this process even on a small scale. The first approach would be very time and labor consuming, but would ultimately provide us with a higher quality data set, which may lead to further improvements in MT. The second is already being deployed by all three major NMT systems but may lead slower progression due to lack of quality control and oversight. The potential prospect of this research is seen in widening the subject area of texts chosen to reflect the variety of writing styles in use on the Internet right now. Inclusion of texts from confessional, business, and other styles may allow us to highlight more lacunae in the neural network models and to suggest further means of improvement. Key words: machine translation, target language, source language, improvement, contextual meaning, communication.

CONTEMPORARY TENDENCIES IN DEVELOPMENT OF MACHINE TRANSLATION FROM ENGLISH INTO UKRAINIAN

Novikova Olha,
 Suima Irina,
 Shevchyk K.
 Contemporary tendencies in development of machine translation from English into Ukrainian
 Background. Today machine translation is one of types of human activity. Machine translation can greatly facilitate global communication, accelerating the translation process, despite the imperfect quality of the source text. Most often the results of online tools require post-editing and can only be effectively used by those who already speak the target language to some extent. The need for a competent translation is growing every year. Today, the search for an algorithm to deliver this quality of translation is one of the most important questions in computer science and linguistics, therefore informing the scientific relevance of this work.
 The purpose of this paper is to analyze different approaches to the machine translation systems, their characteristics, efficacy and the quality of their output on the examples from Google Translate, Microsoft Translator and Yandex.
 To achieve this aim, the following tasks were set:
 
 to identify the most capable algorithms of MT in use today;
 to compare the results of translations made by online translators;
 to analyze typical stylistic, lexical and grammatical errors that appear in the translation;
 to identify the advantages and disadvantages of online translators;
 to provide recommendations for improving machine translation.
 
 To solve these tasks, we use such methods over the course of this work: descriptive, comparative, analysis, experiment and the method of linguistic interpretation of the results obtained.
 Results. Machine translation of belletristic texts was handled exceptionally well by Yandex and was quite acceptable (barring numerous grammatical errors) on Google’s platform. The outlier in this case is Microsoft Translator, whose mistranslation of realia and same aforementioned mistakes make its output much less readable that its competitors.
 The main problems we see arising from such translations arise from the fact that the systems depend on a large amount of high-quality data sets (i.e., corpora of texts for specific language pairs). The quality of these sets directly influences the quality of the output, which in our case is the quality of the target language text. It can be seen by comparing the average quality of translation between Google’s and Microsoft’s systems. The former one makes less mistakes on average and does not have as many issues in regards to identifying a contextual meaning of a polysemantic lexeme.
 We believe that this issue can be fixed to a certain extent one of two ways: hiring professional translators and linguists to compile those parallel corpora or create a possibility for every person to contribute to this process even on a small scale. The first approach would be very time and labor consuming, but would ultimately provide us with a higher quality data set, which may lead to further improvements in MT. The second is already being deployed by all three major NMT systems but may lead slower progression due to lack of quality control and oversight.
 For us, another potential prospect of this research lies in widening the subject area of texts chosen to reflect the variety of writing styles in use on the Internet right now. Inclusion of texts from confessional, business, and other styles may allow us to highlight more lacunae in the neural network models and to suggest further means of improvement.
 Key words: machine translation, target language, source language, improvement, contextual meaning, communication.

METHOD OF SYSTEM ENGINEERING OF NEURAL MACHINE TRANSLATION SYSTEMS

Background. There are not many machine translation companies on the market whose products are in demand. These are, for example, free and commercial products such as “GoogleTranslate”, “DeepLTranslator”, “ModernMT”, “Apertium”, “Trident”, to name a few. To implement a more efficient and productive process for developing high-quality neural machine translation systems (NMTS), appropriate scientifically based methods of NMTS engineering are needed in order to get a high-quality and competitive product as quickly as possible. Objective. The purpose of this article is to apply the Eriksson-Penker business profile to the development and formalization of a method for system engineering of NMTS. Methods. The idea behind the neural machine translation system engineering method is to apply the Eriksson-Penker system engineering methodology and business profile to formalize an ordered way to develop NMT systems. Results. The method of developing NMT systems based on the use of system engineering techniques consists of three main stages. At the first stage, the structure of the NMT system is modelled in the form of an Eriksson-Penker business profile. At the second stage, a set of processes is determined that is specific to the class of Data Science systems, and the international CRISP-DM standard. At the third stage, verification and validation of the developed NMTS is carried out. Conclusions. The article proposes a method of system engineering of NMTS based on the modified Erickson-Penker business profile representation of the system at the meta-level, as well as international process standards of Data Science and Data Mining. The effectiveness of using this method was studied on the example of developing a bidirectional English-Ukrainian NMTS EUMT (English-Ukrainian Machine Translator) and it was found that the EUMT system is at least as good as the quality of English-Ukrainian translation of the popular Google Translate translator. The full version code of the EUMT system is published on the GitHub platform and is available at: https://github.com/EugeneSel/EUMT.

Learning cross-lingual phonological and orthagraphic adaptations: a case study in improving neural machine translation between low-resource languages

Out-of-vocabulary (OOV) words can pose serious challenges for machine translation (MT) tasks, and in particular, for low-resource language (LRL) pairs, i.e., language pairs for which few or no parallel corpora exist. Our work adapts variants of seq2seq models to perform transduction of such words from Hindi to Bhojpuri (an LRL instance), learning from a set of cognate pairs built from a bilingual dictionary of Hindi - Bhojpuri words. We demonstrate that our models can be effectively used for language pairs that have limited parallel corpora; our models work at the character level to grasp phonetic and orthographic similarities across multiple types of word adaptations, whether synchronic or diachronic, loan words or cognates. We describe the training aspects of several character level NMT systems that we adapted to this task and characterize their typical errors. Our method improves BLEU score by 6.3 on the Hindi-to-Bhojpuri translation task. Further, we show that such transductions can generalize well to other languages by applying it successfully to Hindi - Bangla cognate pairs. Our work can be seen as an important step in the process of: (i) resolving the OOV words problem arising in MT tasks; (ii) creating effective parallel corpora for resource constrained languages; and (iii) leveraging the enhanced semantic knowledge captured by word-level embeddings to perform character-level tasks.

A product and process analysis of post-editor corrections on neural, statistical and rule-based machine translation output

This paper presents a comparison of post-editing (PE) changes performed on English-to-Finnish neural (NMT), rule-based (RBMT) and statistical machine translation (SMT) output, combining a product-based and a process-based approach. A total of 33 translation students acted as participants in a PE experiment providing both post-edited texts and edit process data. Our product-based analysis of the post-edited texts shows statistically significant differences in the distribution of edit types between machine translation systems. Deletions were the most common edit type for the RBMT, insertions for the SMT, and word form changes as well as word substitutions for the NMT system. The results also show significant differences in the correctness and necessity of the edits, particularly in the form of a large number of unnecessary edits in the RBMT output. Problems related to certain verb forms and ambiguity were observed for NMT and SMT, while RBMT was more likely to handle them correctly. Process-based comparison of effort indicators shows a slight increase of keystrokes per word for NMT output, and a slight decrease in average pause length for NMT compared to RBMT and SMT in specific text blocks. A statistically significant difference was observed in the number of visits per sub-segment, which is lower for NMT than for RBMT and SMT. The results suggest that although different types of edits were needed to outputs from NMT, RBMT and SMT systems, the difference is not necessarily reflected in process-based effort indicators.

Conceptual environmental impact assessment of a novel self-sustained sanitation system incorporating a quantitative microbial risk assessment approach

In many developing countries, including South Africa, water scarcity has resulted in poor sanitation practices. The majority of the sanitation infrastructures in those regions fail to meet basic hygienic standards. This along with the lack of proper sewage/wastewater infrastructure creates significant environmental and public health concerns. A self-sustained, waterless “Nano Membrane Toilet” (NMT) design was proposed as a result of the “Reinvent the Toilet Challenge” funded by the Bill and Melinda Gates Foundation. A “cradle-to-grave” life cycle assessment (LCA) approach was adopted to study the use of NMT in comparison with conventional pour flush toilet (PFT) and urine-diverting dry toilet (UDDT). All three scenarios were applied in the context of South Africa. In addition, a Quantitative Microbial Risk Assessment (QMRA) was used to reflect the impact of the pathogen risk on human health. LCA study showed that UDDT had the best environmental performance, followed by NMT and PFT systems for all impact categories investigated including human health, resource and ecosystem. This was mainly due to the environmental credits associated with the use of urine and compost as fertilizers. However, with the incorporation of the pathogen impact into the human health impact category, the NMT had a significant better performance than the PFT and UDDT systems, which exhibited an impact category value 4E + 04 and 4E + 03 times higher, respectively. Sensitivity analysis identified that the use of ash as fertilizer, electricity generation and the reduction of NOx emissions were the key areas that influenced significantly the environmental performance of the NMT system.

Visualizing Neural Machine Translation Attention and Confidence

Abstract In this article, we describe a tool for visualizing the output and attention weights of neural machine translation systems and for estimating confidence about the output based on the attention. Our aim is to help researchers and developers better understand the behaviour of their NMT systems without the need for any reference translations. Our tool includes command line and web-based interfaces that allow to systematically evaluate translation outputs from various engines and experiments. We also present a web demo of our tool with examples of good and bad translations: http://ej.uz/nmt-attention.