Abstract
By examining and comparing the linguistic patterns in a self-built corpus of Chinese-English translations produced by WeChat Translate, the latest online machine translation app from the most popular social media platform (WeChat) in China, this study explores such questions as whether or not and to what extent simplification and normalization (hypothesized Translation Universals) exhibit themselves in these translations. The results show that, whereas simplification cannot be substantiated, the tendency of normalization to occur in the WeChat translations can be confirmed. The research finds that these results are caused by the operating mechanism of machine translation (MT) systems. Certain salient words tend to prime WeChat's MT system to repetitively resort to typical language patterns, which leads to a significant overuse of lexical chunks. It is hoped that the present study can shed new light on the development of MT systems and encourage more corpus-based product-oriented research on MT.
| Original language | English |
|---|---|
| Pages (from-to) | 31-58 |
| Number of pages | 28 |
| Journal | International Journal of Corpus Linguistics |
| Volume | 27 |
| Issue number | 1 |
| Early online date | 14 Feb 2022 |
| DOIs | |
| Publication status | Published - 22 Mar 2022 |
Keywords
- machine translation
- normalization
- simplification
- Translation Universals
- WeChat Translate
ASJC Scopus subject areas
- Language and Linguistics
- Linguistics and Language