The ITC-irst statistical machine translation system for IWSLT-2004
نویسندگان
چکیده
Focus of this paper is the system for statistical machine translation developed at ITC-irst. It has been employed in the evaluation campaign of the International Workshop on Spoken Language Translation 2004 in all the three data set conditions of the Chinese-English track. Both the statistical model underlying the system and the system architecture are presented. Moreover, details are given on how the submitted runs have been produced.
منابع مشابه
The ITC-irst SMT system for IWSLT-2005
This paper describes the statistical machine translation system developed at ITC-irst for the evaluation campaign of the International Workshop on Spoken Language Translation 2005. The system exploits two search passes: the first pass is performed by a beam-search decoder which generates an n-best list of translations, the second by a simple re-scoring algorithm. The two passes apply log-linear...
متن کاملThe ITC-irst SMT system for IWSLT 2006
This paper reports on the participation of ITC-irst to the evaluation campaign of the International Workshop on Spoken Language Translation 2006. Our two-pass system is the evolution of the one we employed for the 2005 campaign: in the first pass, an N-best list of translations is generated for each source sentence by means of a beam-search decoder; in the second pass, N-best lists are rescored...
متن کاملThe JHU workshop 2006 IWSLT system
Wade Shen† MIT Lincoln Laboratory 244 Wood St. Lexington, MA 02420, USA [email protected] Richard Zens Lehrstuhl für Informatik 6 Computer Science Department RWTH Aachen University D-52056 Aachen, Germany [email protected] Nicola Bertoldi, Marcello Federico ITC-irst Centro per la Ricerca Scientifica e Tecnologica I-38050 Povo (Trento), Italy {federico|bertoldi}@itc.it Abstract This paper de...
متن کاملExperimenting with phrase-based statistical translation within the IWSLT 2004 Chinese-to-English shared translation task
This paper describes the system we built for the Chinese to English track of the IWSLT 2004 evaluation campaign. A one month effort was devoted to this exercise, starting from scratch and making use as much as possible of freely available packages. We show that a decent phrase-based translation engine can be built within this short time frame.
متن کاملITC-irst at CLEF 2002: Using N-best Query Translations for CLIR
This paper reports on the participation of ITC-irst in the Italian monolingual retrieval track and in the bilingual English-Italian track of the Cross Language Evaluation Forum (CLEF) 2002. A crosslanguage information retrieval systems is proposed which integrates retrieval and translation scores over the set of N-best translations of the source query. Translations are computed by a statistical...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2004