A tree does not make a well-formed sentence: Improving syntactic string-to-tree statistical machine translation with more linguistic knowledge

作者：Sennrich Rico^*; Williams Philip; Huck Matthias

来源：Computer Speech and Language, 2015, 32(1): 27-45.

DOI：10.1016/j.csl.2014.09.002

• Statistical machine translation
• Syntactic translation models
• String-to-tree models
• Morphology

Synchronous context-free grammars (SCFGs) can be learned from parallel texts that are annotated with target-side syntax, and can produce translations by building target-side syntactic trees from source strings. Ideally, producing syntactic trees would entail that the translation is grammatically well-formed, but in reality, this is often not the case. Focusing on translation into German, we discuss various ways in which string-to-tree translation models over- or undergeneralise. We show how these problems can be addressed by choosing a suitable parser and modifying its output, by introducing linguistic constraints that enforce morphological agreement and constrain subcategorisation, and by modelling the productive generation of German compounds.

• 出版日期2015-7