Some Weaknesses of Modern Machine Translation (by Example of Google Translate Web Service)
Some weaknesses of machine translation carried out by means of neural networks (“neural translation”) are considered. The relevance of this topic is determined by the significant popularity of the relevant web services among translators, teachers, researchers, students and others who are interested...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | Russian |
| Published: |
Tsentr nauchnykh i obrazovatelnykh proektov
2018-10-01
|
| Series: | Научный диалог |
| Subjects: | |
| Online Access: | https://www.nauka-dialog.ru/jour/article/view/929 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849223797382578176 |
|---|---|
| author | I. S. Samokhin N. L. Sokolova M. G. Sergeyeva |
| author_facet | I. S. Samokhin N. L. Sokolova M. G. Sergeyeva |
| author_sort | I. S. Samokhin |
| collection | DOAJ |
| description | Some weaknesses of machine translation carried out by means of neural networks (“neural translation”) are considered. The relevance of this topic is determined by the significant popularity of the relevant web services among translators, teachers, researchers, students and others who are interested in the introductory or urgent transcoding of the text from one language to another. The results of the experiment are presented: well-known web service “Google Translate” was offered to translate into English several dozens of Russian-language terms and concepts related to philology and pedagogy. Recommendations are given to correct some errors and inaccuracies made by the web service. The authors come to the conclusion that the use of neural translation has led to a significant improvement in the quality of services provided by the web service “Google Translate.” It is noted that this service still makes mistakes (semantic and stylistic) when translating the following categories of vocabulary: compound terms and concepts; lexical units and phrases that do not have clear equivalents in the English language; two words with the same English equivalent; abbreviations; author’s occasionalisms. It is reported that, according to the authors, such errors are made by other popular web services (“Yandex.Translator,” “Translate.ru” etc.) |
| format | Article |
| id | doaj-art-067726ce4c764a3f9746e7737e0d8fbc |
| institution | Kabale University |
| issn | 2225-756X 2227-1295 |
| language | Russian |
| publishDate | 2018-10-01 |
| publisher | Tsentr nauchnykh i obrazovatelnykh proektov |
| record_format | Article |
| series | Научный диалог |
| spelling | doaj-art-067726ce4c764a3f9746e7737e0d8fbc2025-08-25T18:13:17ZrusTsentr nauchnykh i obrazovatelnykh proektovНаучный диалог2225-756X2227-12952018-10-0101014815710.24224/2227-1295-2018-10-148-157925Some Weaknesses of Modern Machine Translation (by Example of Google Translate Web Service)I. S. Samokhin0N. L. Sokolova1M. G. Sergeyeva2Peoples’ Friendship University of RussiaPeoples’ Friendship University of RussiaPeoples’ Friendship University of RussiaSome weaknesses of machine translation carried out by means of neural networks (“neural translation”) are considered. The relevance of this topic is determined by the significant popularity of the relevant web services among translators, teachers, researchers, students and others who are interested in the introductory or urgent transcoding of the text from one language to another. The results of the experiment are presented: well-known web service “Google Translate” was offered to translate into English several dozens of Russian-language terms and concepts related to philology and pedagogy. Recommendations are given to correct some errors and inaccuracies made by the web service. The authors come to the conclusion that the use of neural translation has led to a significant improvement in the quality of services provided by the web service “Google Translate.” It is noted that this service still makes mistakes (semantic and stylistic) when translating the following categories of vocabulary: compound terms and concepts; lexical units and phrases that do not have clear equivalents in the English language; two words with the same English equivalent; abbreviations; author’s occasionalisms. It is reported that, according to the authors, such errors are made by other popular web services (“Yandex.Translator,” “Translate.ru” etc.)https://www.nauka-dialog.ru/jour/article/view/929google translatemachine translationweb servicegoogle translateneural translationtranslation services |
| spellingShingle | I. S. Samokhin N. L. Sokolova M. G. Sergeyeva Some Weaknesses of Modern Machine Translation (by Example of Google Translate Web Service) Научный диалог google translate machine translation web service google translate neural translation translation services |
| title | Some Weaknesses of Modern Machine Translation (by Example of Google Translate Web Service) |
| title_full | Some Weaknesses of Modern Machine Translation (by Example of Google Translate Web Service) |
| title_fullStr | Some Weaknesses of Modern Machine Translation (by Example of Google Translate Web Service) |
| title_full_unstemmed | Some Weaknesses of Modern Machine Translation (by Example of Google Translate Web Service) |
| title_short | Some Weaknesses of Modern Machine Translation (by Example of Google Translate Web Service) |
| title_sort | some weaknesses of modern machine translation by example of google translate web service |
| topic | google translate machine translation web service google translate neural translation translation services |
| url | https://www.nauka-dialog.ru/jour/article/view/929 |
| work_keys_str_mv | AT issamokhin someweaknessesofmodernmachinetranslationbyexampleofgoogletranslatewebservice AT nlsokolova someweaknessesofmodernmachinetranslationbyexampleofgoogletranslatewebservice AT mgsergeyeva someweaknessesofmodernmachinetranslationbyexampleofgoogletranslatewebservice |