Paper: Learning Non-linear Features for Machine Translation Using Gradient Boosting Machines

ACL ID P13-2072
Title Learning Non-linear Features for Machine Translation Using Gradient Boosting Machines
Venue Annual Meeting of the Association of Computational Linguistics
Session Short Paper
Year 2013
Authors

In this paper we show how to auto- matically induce non-linear features for machine translation. The new features are selected to approximately maximize a BLEU-related objective and decompose on the level of local phrases, which guar- antees that the asymptotic complexity of machine translation decoding does not in- crease. We achieve this by applying gra- dient boosting machines (Friedman, 2000) to learn newweak learners (features) in the form of regression trees, using a differen- tiable loss function related to BLEU. Our results indicate that small gains in perfor- mance can be achieved using this method but we do not see the dramatic gains ob- served using feature induction for other important machine learning tasks.