The ICT system description for IWSLT 2008
نویسندگان
چکیده
1.1 Silenus Silenus (Mi et al., 2008; Mi and Huang, 2008) is a forest-based tree-to-string SMT system. A packed parse forest is a compact representation of all derivations (i.e., parse trees) for a given sentence under a context-free grammar. A tree-to-string rule describes the correspondence between a source parse tree and a target string. Unlike previous tree-to-string (Liu et al., 2006; Huang et al., 2006) or string-to-tree models (Galley et al., 2006; Marcu et al., 2006), we extract tree-to-string rules from aligned forest-string pairs. In decoding, the input is a source forest rather than a source tree. Figure 1 demonstrates a pair of linked source forest and target string. Table 1 shows some tree-to-string rules learned from the example forest-string pair in Figure 1.
منابع مشابه
The QMUL system description for IWSLT 2008
The QMUL system to the IWSLT 2008 evaluation campaign is a phrase-based statistical MT system implemented in C++. The decoder employs a multi-stack architecture, and uses a beam to manage the search space. We participated in both BTEC Arabic → English and Chinese → English tracks, as well as the PIVOT task. In our first submission to IWSLT, we are particularly interested in seeing how our SMT s...
متن کاملThe ICT statistical machine translation systems for IWSLT 2007
In this paper, we give an overview of the ICT statistical machine translation systems for the evaluation campaign of the International Workshop on Spoken Language Translation (IWSLT) 2007. In this year’s evaluation, we participated in the Chinese-English transcript translation task, and developed three systems based on different techniques: a formally syntax-based system Bruin, an extended phra...
متن کاملThe ICT statistical machine translation systems for the IWSLT 2009
This paper describes the ICT Statistical Machine Translation systems that used in the evaluation campaign of the International Workshop on Spoken Language Translation (IWSLT) 2009. For this year’s evaluation, we participated in the Challenge Task (Chinese-English and English-Chinese) and BTEC Task (Chinese-English). And we mainly focus on one new method to improve single system’s translation qu...
متن کاملThe MIT-LL/AFRL IWSLT-2008 MT system
This paper describes the MIT-LL/AFRL statistical MT system and the improvements that were developed during the IWSLT 2008 evaluation campaign. As part of these efforts, we experimented with a number of extensions to the standard phrase-based model that improve performance for both text and speech-based translation on Chinese and Arabic translation tasks. We discuss the architecture of the MIT-L...
متن کاملThe LIUM Arabic/English statistical machine translation system for IWSLT 2008
This paper describes the system developed by the LIUM laboratory for the 2008 IWSLT evaluation. We only participated in the Arabic/English BTEC task. We developed a statistical phrase-based system using the Moses toolkit and SYSTRAN’s rule-based translation system to perform a morphological decomposition of the Arabic words. A continuous space language model was deployed to improve the modeling...
متن کامل