When we automatically acquire translation knowledge from a bilingual corpus, redundant rules are generated due to translation variety. To overcome this problem, we propose bilingual corpus cleaning based on translation literality. Word-level correspondence and phrase-level correspondence are applied as the criteria of literality. Using these criteria, a bilingual corpus was cleaned, and transla...

Speech translation tasks usually are different from text-based machine translation tasks, and the training data for speech translation tasks are usually very limited. Therefore, domain adaptation is crucial to achieve robust performance across different conditions in speech translation. In this paper, we study the problem of adapting a general-domain, writing-textstyle machine translation syste...

Different approaches in machine translation achieve similar translation quality with a variety of translations in the output. Recently it has been shown, that it is possible to leverage the individual strengths of various systems and improve the overall translation quality by combining translation outputs. In this paper we present a method of hypothesis selection which is relatively simple comp...

When we automatically acquire translation knowledge from a bilingual corpus, redundant rules are generated due to translation variety. To overcome this problem, we propose bilingual corpus cleaning based on translation literality. Word-level correspondence and phrase-level correspondence are applied as the criteria of literality. Using these criteria, a bilingual corpus was cleaned, and transla...

VOLUME 10, NUMBER 1, 1997 THE LINCOLN LABORATORY JOURNAL 35 T    operates worldwide in a variety of international environments that require language translation. Translators who can interpret military terminology are a scarce commodity in countries such as the Republic of Korea (R.O.K.), and U.S. military leaders there support the development of bilingual machine translati...

Abstract At ATR Spoken Language Translation Research Laboratories, we are building a broad-coverage bilingual corpus to study corpus-based speech translation technologies for the real world. There are three important points to consider in designing and constructing a corpus for future speech translation research. The first is to have a variety of speech samples, with a wide range of pronunciati...

Translation is not merely a mater of linguistics. The major goal the present paper to investigate relationship between ‘culture’ and ‘translation’. To this end, researcher drew on corpus from English Persian languages. findings indicated that although different languages, like Persian, employ linguistic forms, variety cannot be considered as real challenge. Since during process translation, sou...

Translation is a tool of knowledge transferring an original language to another language. In other words, it the process converting written word from one into in way that culturally and linguistically appropriate so can be understood. There are, however, challenges translation which include knowing about variety features such as structure differs between languages. The combination meaning words...