Search Results for author: Stephen Mussman

Found 1 papers, 1 papers with code

The price of debiasing automatic metrics in natural language evaluation

1 code implementation6 Jul 2018 Arun Tejasvi Chaganty, Stephen Mussman, Percy Liang

For evaluating generation systems, automatic metrics such as BLEU cost nothing to run but have been shown to correlate poorly with human judgment, leading to systematic bias against certain model improvements.

Question Answering

Cannot find the paper you are looking for? You can Submit a new open access paper.