Year: 2008
Type: conference-paper
Abstract: Current re-ranking algorithms for machine translation rely on log-linear models, which have the potential problem of underfitting the training data. We present BoostedMERT, a novel boosting algorithm that uses Minimum Error Rate Training (MERT) as a weak learner and builds a re-ranker far more expressive than log-linear models. BoostedMERT is easy to implement, inherits the efficient optimization properties of MERT, and can quickly boost the BLEU score on N-best re-ranking tasks. In this paper, we describe the general algorithm and present preliminary results on the IWSLT 2007 Arabic-English task.
Authors: Kevin Duh, Katrin Kirchhoff
Institution: University of Washington
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
Funder: National Science Foundation
OpenAlex ID: W2118960083