Predictive translation memory
Spence Green, Jason Chuang, Jeffrey Heer et al. · ACM Symposium on User Interface Software and Technology (UIST) · 2014
The standard approach to computer-aided language translation is post-editing: a machine generates a single translation that a human translator corrects. Recent studies have shown this simple technique to be surprisingly effective, yet it underutilizes the complementary strengths of precision-oriented humans and recall-oriented machines. We present Predictive Translation Memory, an interactive, mixed-initiative system for human language translation. Translators build translations incrementally by considering machine suggestions that update according to the user's current partial translation. In a large-scale study, we find that professional translators are slightly slower in the interactive mode yet produce slightly higher quality translations despite significant prior experience with the baseline post-editing condition. Our analysis identifies significant predictors of time and quality, and also characterizes interactive aid usage. Subjects entered over 99% of characters via interactive aids, a significantly higher fraction than that shown in previous work.
Cited by 52 works. doi:10.1145/2642918.2647408
Authors
References
- Lecture Notes in Computer Science 1205
- BLEU
- The Stanford CoreNLP Natural Language Processing Toolkit
- Random effects structure for confirmatory hypothesis testing: Keep it maximal
- Statistical machine translation
- AI in CAI: An Artificial-Intelligence Approach to Computer-Assisted Instruction
- Good applications for crummy machine translation
- Principles of mixed-initiative user interfaces
- Alignment by agreement
- Re-evaluating the Role of Bleu in Machine Translation Research