We report results from a domain adaptation task for statistical machine translation (SMT) using cache-based adaptive language and translation models. We apply an exponential decay factor and integrate the cache models in a standard phrasebased SMT decoder. Without the need for any domain-specific resources we obtain a 2.6% relative improvement on average in BLEU scores using our dynamic adaptat...

An English-to-Turkish Interlingual MT System p. 83 Rapid Prototyping of Domain-Specific Machine Translation Systems p. 95 Time-Constrained Machine Translation p. 103 An Evaluation of the Multi-Engine MT Architecture p. 113 An Ontology-Based Approach to Parsing Turkish Sentences p. 124 Monolingual Translator Workstation p. 136 Fast Document Translation for Cross-Language Information Retrieval p....

The paper describes suitable sources for creating Czech-Slovak parallel corpora, including our procedure of creating plain text parallel corpora from various data sources. We attempt to address the pros and cons of various types of data sources, especially when they are used in machine translation. Some results of machine translation from Czech to Slovak based on the acquired corpora are also g...

The construction, identification, and use of a recombinant DNA clone containing a growth hormone structural gene sequence is described. A cDNA copy of partially purified pregrowth hormone mRNA from cultured rat pituitary tumor (GC) cells was employed in the construction of a hybrid plasmid, designated pBR322-GH1. The cloned DNA sequence was positively identified by a hybridization-translation p...

THE Machine Translation Laboratory of the Georgetown University Institute of Languages and Linguistics has been working for some years on RussianEnglish machine translation. Different approaches to the problem, varying from essentially empirical code-matching techniques to techniques involving complete linguistic analysis, have been investigated and evaluated here. The procedure which was final...

this study was conducted to identify and compare the strategies applied by two native farsi translators in rendering the culture specific items (csis) of a literary text titled savushun in their english translations. in this study, csis refer to the materials, social customs, religious concepts, and traditions available in one language and culture but nonexistent in the other language and cultu...

One of the necessary tasks of a machine translation system is lexical transfer. In some cases there is a one-to-one mapping from source language word to target language word. What theoretical model is followed when there is a one-to-many mapping? Unfortunately, none of the linguistic models that have been used in machine translation include a lexical transfer component. In the absence of a theo...

VERBMOBIL is a speech-to-speech translation system for spoken dialogues between two speakers. The application scenario is appointment scheduling for business meetings, with spoken dialogues between two speakers. Both dialogue participants have at least a passive knowledge of English which serves as intermediate language. The transfer directions are German to English and Japanese to English. A s...

State of the art statistical machine translation systems are typically trained by symmetrizing word alignments in two translation directions. We introduce a new method that improves word alignment results, based on self learning using the initial symmetrized word alignments results. The method involves aligning words and symmetrizing alignments, generating labeled training data, and construct a...

setting standards for translation assessment has usually been problematic for authorities, theoreticians, and most commonly instructors. it is often difficult to tell the difference between translation evaluation, criticism, and assessment due to hardships of bridging the gap between theory and practice. the aim of this study was to create a rubric against which translations could be assessed. ...