Identifying MT Errors for Higher-Quality Target Language Writing

Identifying MT Errors for Higher-Quality Target Language Writing

Kayo Tsuji
DOI: 10.4018/IJTIAL.335899
Article PDF Download
Open access articles are freely available for download

Abstract

Second language education has arrived at a phase of proposing effective uses of neural machine translation (NMT). Previous research has explored various aspects of post-editing and suggested that it is crucial to manually edit NMT output to produce better target language (TL) texts. The purpose of this study was to identify NMT errors in output text, so that Japanese TL (English) learners can recognize what to be aware of. The study targeted the NMT output from Japanese-written academic reports, pre-edited by 73 Japanese students with intermediate TL proficiency. The data was analysed and primarily lexical and grammatical issues were detected and systematically classified. Results showed that the use of inappropriate TL vocabulary was the most frequent error, followed by misuse or lack of determiners. Some could be avoided in a pre-editing phase by carefully choosing precise source-language (SL) vocabulary or reducing SL ambiguity, while others required a deeper understanding of TL syntactic rules or the nuance of TL vocabulary. TL Learners need to raise their awareness of these NMT errors for effective post-editing.
Article Preview
Top

2. Previous Research

Post-editing1 has received attention from a variety of perspectives. Researchers have identified the merits of post-editing (Alsalem, 2019; Escartín et al., 2017; Fredholm, 2019; Green et al., 2013), explored the post-editing process (Jia et al., 2019), along with user experiences of post-editing (Harto et al., 2022). They have also analysed how TL proficiency affects the post-editing process (Chung, 2020) and the differences between post-editing by native and non-native TL speakers (Sánchez-Gijón and Torres-Hostench, 2014). In relation to education, research has investigated whether MT can be used as a pedagogical support tool (Lee and Briggs, 2020), the effect of post-edit training on TT quality (Báez, 2018; Zhang and Torres-Hostench, 2022), as well as the development of post-editing rules (Turganbayeva et al., 2022). The results of this research provide several influential principles for successful post-editing.

Complete Article List

Search this Journal:
Reset
Volume 6: 1 Issue (2024)
Volume 5: 1 Issue (2023)
Volume 4: 2 Issues (2022)
Volume 3: 2 Issues (2021)
Volume 2: 2 Issues (2020)
Volume 1: 2 Issues (2019)
View Complete Journal Contents Listing