Search Results for author:
Found 2 papers, 0 papers with code
Finding Replicable Human Evaluations via Stable Ranking Probability
Reliable human evaluation is critical to the development of successful natural language generation models, but achieving it is notoriously difficult.
Multilingual Document-Level Translation Enables Zero-Shot Transfer From Sentences to Documents
Using simple concatenation-based DocNMT, we explore the effect of 3 factors on the transfer: the number of teacher languages with document level data, the balance between document and sentence level data at training, and the data condition of parallel documents (genuine vs. backtranslated).
Cannot find the paper you are looking for? You can
Submit a new open access paper.
