Paper: Variational Decoding for Statistical Machine Translation

ACL ID P09-1067
Title Variational Decoding for Statistical Machine Translation
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2009
Authors

Statistical models in machine translation exhibit spurious ambiguity. That is, the probability of an output string is split among many distinct derivations (e.g., trees or segmentations). In principle, the goodness of a string is measured by the total probability of its many derivations. However, finding the best string (e.g., dur- ing decoding) is then computationally in- tractable. Therefore, most systems use a simple Viterbi approximation that mea- sures the goodness of a string using only its most probable derivation. Instead, we develop a variational approximation, which considers all the derivations but still allows tractable decoding. Our particular variational distributions are parameterized as n-gram models. We also analytically show that interpolating thesen-gram mod- els for dif...