Paper: Locally Training the Log-Linear Model for SMT

ACL ID D12-1037
Title Locally Training the Log-Linear Model for SMT
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2012

In statistical machine translation, minimum error rate training (MERT) is a standard method for tuning a single weight with regard to a given development data. However, due to the diversity and uneven distribution of source sentences, there are two problems suffered by this method. First, its performance is highly dependent on the choice of a development set, which may lead to an unstable performance for testing. Second, translations become in- consistent at the sentence level since tuning is performed globally on a document level. In this paper, we propose a novel local training method to address these two problems. Un- like a global training method, such as MERT, in which a single weight is learned and used for all the input sentences, we perform training and testing in one step by learn...