Video Recordings

Simultaneous interpreting is more than just real-time translation—it requires processes like summarization, simplification, generalization, and paraphrasing. While these strategies help interpreters manage cognitive load, they also typically enhance audience comprehension. In this talk, I will present findings from a dataset of student interpreting, discussing the challenges of annotation, key characteristics of the data, and notable linguistic patterns. I will also outline our progress toward automatic alignment methods and their potential applications. Beyond dataset analysis, I’ll explore broader questions: Can we improve the automatic evaluation of simultaneous interpreting? How can these insights help train better interpreters and refine machine translation systems?