Forms Wanted: Training SMT on Monolingual Data
نویسندگان
چکیده
We propose and evaluate a simple technique of “reverse self-training” for statistical machine translation. The technique allows to extend target-side vocabulary of the MT system using target-side monolingual data and it is especially aimed at translation to morphologically rich languages.
منابع مشابه
Investigations on large-scale lightly-supervised training for statistical machine translation
Sentence-aligned bilingual texts are a crucial resource to build statistical machine translation (SMT) systems. In this paper we propose to apply lightly-supervised training to produce additional parallel data. The idea is to translate large amounts of monolingual data (up to 275M words) with an SMT system, and to use those as additional training data. Results are reported for the translation f...
متن کاملRe-training Monolingual Parser Bilingually for Syntactic SMT
The training of most syntactic SMT approaches involves two essential components, word alignment and monolingual parser. In the current state of the art these two components are mutually independent, thus causing problems like lack of rule generalization, and violation of syntactic correspondence in translation rules. In this paper, we propose two ways of re-training monolingual parser with the ...
متن کاملChained System: A Linear Combination of Different Types of Statistical Machine Translation Systems
The paper explores a way to learn post-editing fixes of raw MT outputs automatically by combining two different types of statistical machine translation (SMT) systems in a linear fashion. Our proposed system (which we call a chained system) consists of two SMT systems: (i) a syntax-based SMT system and (ii) a phrase-based SMT system (Koehn, 2004). We first translate source sentences of the bite...
متن کاملMonolingual Data Optimisation for Bootstrapping SMT Engines
Content localisation via machine translation (MT) is a sine qua non, especially for international online business. While most applications utilise rule-based solutions due to the lack of suitable in-domain parallel corpora for statistical MT (SMT) training, in this paper we investigate the possibility of applying SMT where huge amounts of monolingual content only are available. We describe a ca...
متن کاملImproving word alignment for low resource languages using English monolingual SRL
We introduce a new statistical machine translation approach specifically geared to learning translation from low resource languages, that exploits monolingual English semantic parsing to bias inversion transduction grammar (ITG) induction. We show that in contrast to conventional statistical machine translation (SMT) training methods, which rely heavily on phrase memorization, our approach focu...
متن کامل