The forest-based Tree Sequence to String SMT System for CWMT-
نویسندگان
چکیده
This paper reports IR’s SMT System for CWMT-2009 MT evaluation. In the CWMT-2009 MT evaluation, we use our forest-based tree sequence to string translation system to participate in the ChineseEnglish single system evaluation track. In this paper, we give an overall introduction of our translation system and then report the experiment details including how we pre-process the training data, system configuration and post-processing procedures.
منابع مشابه
The ICT system description for IWSLT 2008
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; Huan...
متن کاملForest-based Tree Sequence to String Translation Model
This paper proposes a forest-based tree sequence to string translation model for syntaxbased statistical machine translation, which automatically learns tree sequence to string translation rules from word-aligned sourceside-parsed bilingual texts. The proposed model leverages on the strengths of both tree sequence-based and forest-based translation models. Therefore, it can not only utilize for...
متن کاملTransformation and Decomposition for Efficiently Implementing and Improving Dependency-to-String Model In Moses
Dependency structure provides grammatical relations between words, which have shown to be effective in Statistical Machine Translation (SMT). In this paper, we present an open source module in Moses which implements a dependency-to-string model. We propose a method to transform the input dependency tree into a corresponding constituent tree for reusing the tree-based decoder in Moses. In our ex...
متن کاملNTT - NAIST SMT Systems for IWSLT 2013
This paper presents NTT-NAIST SMT systems for EnglishGerman and German-English MT tasks of the IWSLT 2013 evaluation campaign. The systems are based on generalized minimum Bayes risk system combination of three SMT systems: forest-to-string, hierarchical phrase-based, phrasebased with pre-ordering. Individual SMT systems include data selection for domain adaptation, rescoring using recurrent ne...
متن کاملForest Stand Types Classification Using Tree-Based Algorithms and SPOT-HRG Data
Forest types mapping, is one of the most necessary elements in the forest management and silviculture treatments. Traditional methods such as field surveys are almost time-consuming and cost-intensive. Improvements in remote sensing data sources and classification –estimation methods are preparing new opportunities for obtaining more accurate forest biophysical attributes maps. This research co...
متن کامل