Author

Satoshi Nakamura

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#natural language process... Preprint Sep 2026

Rubric-Aligned Disentangled Evaluation of Human Simultaneous Interpreting

It is shown that structured LLM prompting and scalar supervision collapse rubric dimensions, yielding near-zero correlation with human ratings and strong cross-dimension coupling, are effective for segment-level SI evaluation.

Zi-Yu Zhang, Satoshi Nakamura · 0 citations