Modeling Inflection and Word-Formation in SMT
نویسندگان
چکیده
The current state-of-the-art in statistical machine translation (SMT) suffers from issues of sparsity and inadequate modeling power when translating into morphologically rich languages. We model both inflection and word-formation for the task of translating into German. We translate from English words to an underspecified German representation and then use linearchain CRFs to predict the fully specified German representation. We show that improved modeling of inflection and wordformation leads to improved SMT.
منابع مشابه
Applying Morphology Generation Models to Machine Translation
We improve the quality of statistical machine translation (SMT) by applying models that predict word forms from their stems using extensive morphological and syntactic information from both the source and target languages. Our inflection generation models are trained independently of the SMT system. We investigate different ways of combining the inflection prediction component with the SMT syst...
متن کاملA Distributed Inflection Model for Translating into Morphologically Rich Languages
Lexical sparsity is a major challenge for machine translation into morphologically rich languages. We address this problem by modeling sequences of fine-grained morphological tags in a bilingual context. To overcome the issue of ambiguous word analyses, we introduce soft tags, which are under-specified representations retaining all possible morphological attributes of a word. In order to learn ...
متن کاملA Hybrid Machine Translation System Based on a Monotone Decoder
In this paper, a hybrid Machine Translation (MT) system is proposed by combining the result of a rule-based machine translation (RBMT) system with a statistical approach. The RBMT uses a set of linguistic rules for translation, which leads to better translation results in terms of word ordering and syntactic structure. On the other hand, SMT works better in lexical choice. Therefore, in our sys...
متن کاملWord Sense Disambiguation for Statistical Machine Translation
While much effort has been put in designing and evaluating Word Sense Disambiguation (WSD) models for translation in the WSD community, standard Statistical Machine Translation (SMT) systems have achieved remarkable improvements in translation quality without modeling WSD explicitly. However, inspecting SMT output suggests that SMT needs better semantic modeling to accurately translate meaning....
متن کاملCombining Bilingual Terminology Mining and Morphological Modeling for Domain Adaptation in SMT
Translating in technical domains is a wellknown problem in SMT, as the lack of parallel documents causes significant problems of sparsity. We discuss and compare different strategies for enriching SMT systems built on general domain data with bilingual terminology mined from comparable corpora. In particular, we focus on the targetlanguage inflection of the terminology data and present a pipeli...
متن کامل