Understanding Pre-Editing for Black-Box Neural Machine Translation
This study provides a deeper understanding of pre-editing for practitioners and researchers working with black-box NMT systems, addressing a gap in understanding how pre-editing works.
This paper investigates human pre-editing practices for black-box neural machine translation (NMT) by collecting 6,652 instances across various settings. The study found that enhancing explicitness and syntactic structure is more crucial for translation quality than brevity, and while NMT impact is unpredictable, some tendencies exist based on editing operation types.
Pre-editing is the process of modifying the source text (ST) so that it can be translated by machine translation (MT) in a better quality. Despite the unpredictability of black-box neural MT (NMT), pre-editing has been deployed in various practical MT use cases. Although many studies have demonstrated the effectiveness of pre-editing methods for particular settings, thus far, a deep understanding of what pre-editing is and how it works for black-box NMT is lacking. To elicit such understanding, we extensively investigated human pre-editing practices. We first implemented a protocol to incrementally record the minimum edits for each ST and collected 6,652 instances of pre-editing across three translation directions, two MT systems, and four text domains. We then analysed the instances from three perspectives: the characteristics of the pre-edited ST, the diversity of pre-editing operations, and the impact of the pre-editing operations on NMT outputs. Our findings include the following: (1) enhancing the explicitness of the meaning of an ST and its syntactic structure is more important for obtaining better translations than making the ST shorter and simpler, and (2) although the impact of pre-editing on NMT is generally unpredictable, there are some tendencies of changes in the NMT outputs depending on the editing operation types.