Consensus Training for Consensus Decoding in Machine Translation

We propose a novel objective function for discriminatively tuning log-linear machine translation models. Our objective explicitly optimizes the BLEU score of expected n-gram counts, the same quantities that arise in forestbased consensus and minimum Bayes risk decoding methods. Our continuous objective can be optimized using simple gradient ascent. However, computing critical quantities in the gradient necessitates a novel dynamic program, which we also present here. Assuming BLEU as an evaluation measure, our objective function has two principle advantages over standard max BLEU tuning. First, it specifically optimizes model weights for downstream consensus decoding procedures. An unexpected second benefit is that it reduces overfitting, which can improve test set BLEU scores when using standard Viterbi decoding.