Paper: Synchronous Tree Adjoining Machine Translation

ACL ID D09-1076
Title Synchronous Tree Adjoining Machine Translation
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2009

Tree Adjoining Grammars have well-known advantages, but are typically considered too difficult for practical systems. We demon- strate that, when done right, adjoining im- proves translation quality without becoming computationally intractable. Using adjoining to modeloptionalityallows generaltranslation patterns to be learned without the clutter of endless variations of optional material. The appropriatemodifiers can later be spliced in as needed. In this paper, we describe a novel method for learning a type of Synchronous Tree Ad- joining Grammar and associated probabilities from aligned tree/string training data. We in- troduce a method of converting these gram- mars to a weakly equivalent tree transducer for decoding. Finally, we show that adjoining results in an end-to-end improvement...