Rule Selection with Soft Syntactic Features for String-to-Tree Statistical Machine Translation

Abstract

In syntax-based machine translation, rule selection is the task of choosing the correct target side of a translation rule among rules with the same source side. We define a discriminative rule selection model for systems that have syntactic annotation on the target language side (stringto-tree). This is a new and clean way to integrate soft source syntactic constraints into string-to-tree systems as features of the rule selection model. We release our implementation as part of Moses.

The QT21/HimL Combined Machine Translation System

“…During decoding, the rule selection model is called at each rule application with syntactic context information as feature templates. The features are the same as used by Braune et al (2015) in their string-to-tree system, including both lexical and soft source syntax features. The translation model features comprise the standard hierarchical features (Chiang, 2005) with an additional feature for the rule selection model (Braune et al, 2016).…”

LMU Munich's Neural Machine Translation Systems for News Articles and Health Information Texts

“…2 A unique characteristic of the LMU English→German NMT systems is a linguistically informed, cascaded word segmentation technique that we developed and applied to the German target language side of the training data. Amongst other aspects, SMT research at LMU is focusing on investigating linguistically informed methods that improve machine translation into target languages which exhibit a more complex morphosyntax than English (Huck et al, 2017b;Tamchyna et al, 2016a;Ramm and Fraser, 2016;Weller-Di Marco et al, 2016;Braune et al, 2015;Cap et al, 2014a;Fraser et al, 2012). We are taking advantage of our group's longstanding experience regarding handling of complex morphosyntax in SMT, now enriching NMT with novel techniques that specifically tackle target-side morphosyntax.…”