A tree does not make a well-formed sentence: Improving syntactic string-to-tree statistical machine translation with more linguistic knowledge. (July 2015)

• Record Type: Journal Article
• Authors: Sennrich, Rico; Williams, Philip; Huck, Matthias
• Is Part Of: Computer speech & language. Volume 32(2015)
• Page Start: 27
• Page End: 45
• Publication Date: 2015-07
• Subjects: Statistical machine translation -- Syntactic translation models -- String-to-tree models -- Morphology; Speech processing systems -- Periodicals; Automatic speech recognition -- Periodicals; Computers -- Periodicals; Linguistics -- Periodicals; Speech-Language Pathology -- Periodicals; Traitement automatique de la parole -- Périodiques; Reconnaissance automatique de la parole -- Périodiques; Automatic speech recognition; Speech processing systems; Electronic journals; Periodicals; 006.454
• DOI: 10.1016/j.csl.2014.09.002
• Languages: English
• ISSNs: 0885-2308

Abstract

Abstract : Highlights: String-to-tree SMT systems aim to produce grammatically well-formed translation. Modelling assumptions of synchronous grammars can result in ungrammatical output. Grammar overgeneralisations can be reduced by parser choice and modifications. Overgeneralisation errors can be prevented with rule-based lingustic constraints. Abstract: 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.