Tuning as Linear Regression

Marzieh Bazrafshan, Tagyoung Chung, Daniel Gildea · 2012

We propose a tuning method for statistical machine translation, based on the pairwise ranking approach. Hopkins and May (2011) presented a method that uses a binary classifier. In this work, we use linear regression and show that our approach is as effective as using a binary classifier and converges faster. 1

Read the paper · More papers on PaperTik