Access Restriction

Author Nießen, Sonja ♦ Ney, Hermann
Source CiteSeerX
Content type Text
File Format PDF
Language English
Subject Domain (in DDC) Computer science, information & general works ♦ Data processing & computer science
Subject Keyword Question Inversion ♦ Statistical Machine Translation ♦ Bilingual Corpus ♦ Linguistic Knowledge ♦ Language Pair German ♦ Target Language ♦ Different Language ♦ Detachable German Verb Prefix ♦ Sentence Structure ♦ Translation Direction ♦ So-called Alignment Model ♦ Previous Publication ♦ Explicit Introduction ♦ Word Order ♦ Morpho-syntactic Analysis ♦ German-english Corpus ♦ Syntactic Information ♦ Systematic Experiment
Description In the framework of statistical machine translation (SMT), correspondences between the words in the source and the target language are learned from bilingual corpora on the basis of so-called alignment models. Among other things these are meant to capture the differences in word order in different languages. In this paper we show that SMT can take advantage of the explicit introduction of some linguistic knowledge about the sentence structure in the languages under consideration. In contrast to previous publications dealing with the incorporation of morphological and syntactic information into SMT, we focus on two aspects of reordering for the language pair German and English, namely question inversion and detachable German verb prefixes. The results of systematic experiments are reported and demonstrate the applicability of the approach to both translation directions on a German-English corpus.
In Proc. MT Summit VIII
Educational Role Student ♦ Teacher
Age Range above 22 year
Educational Use Research
Education Level UG and PG ♦ Career/Technical Study
Learning Resource Type Article
Publisher Department Lehrstuhl Für Informatik Vi