Adjoining Tree-to-String Translation

We introduce synchronous tree adjoining grammars (TAG) into tree-to-string translation, which converts a source tree to a target string. Without reconstructing TAG derivations explicitly, our rule extraction algorithm directly learns tree-to-string rules from aligned Treebank-style trees. As tree-to-string translation casts decoding as a tree parsing problem rather than parsing, the decoder still runs fast when adjoining is included. Less than 2 times slower, the adjoining tree-tostring system improves translation quality by +0.7 BLEU over the baseline system only allowing for tree substitution on NIST ChineseEnglish test sets.

• Type: Journal
• Year: 2011
• Where: ACL
• Authors: Yang Liu, Qun Liu, Yajuan Lü
• Keywords: ACL 2011, Baseline System, Computational Linguistics, Target String, Translation Quality