Paper: Rule Markov Models for Fast Tree-to-String Translation

ACL ID P11-1086
Title Rule Markov Models for Fast Tree-to-String Translation
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2011

Most statistical machine translation systems rely on composed rules (rules that can be formed out of smaller rules in the grammar). Though this practice improves translation by weakening independence assumptions in the translation model, it nevertheless results in huge, redundant grammars, making both train- ing and decoding inefficient. Here, we take the opposite approach, where we only use min- imal rules (those that cannot be formed out of other rules), and instead rely on a rule Markov model of the derivation history to capture dependencies between minimal rules. Large-scale experiments on a state-of-the-art tree-to-string translation system show that our approach leads to a slimmer model, a faster decoder, yet the same translation quality (mea- sured using Bleu) as composed rules.