The CUED HiFST System for the WMT10 Translation Shared Task
نویسندگان
چکیده
This paper describes the Cambridge University Engineering Department submission to the Fifth Workshop on Statistical Machine Translation. We report results for the French-English and Spanish-English shared translation tasks in both directions. The CUED system is based on HiFST, a hierarchical phrase-based decoder implemented using weighted finite-state transducers. In the French-English task, we investigate the use of context-dependent alignment models. We also show that lattice minimum Bayes-risk decoding is an effective framework for multi-source translation, leading to large gains in BLEU score.
منابع مشابه
CUED Submission for the WMT10 Translation Shared Task
This paper describes the Cambridge University Engineering Department (CUED) system for the ACL 2010 fifth workshop on statistical machine translation (WMT10). We participated in the FrenchEnglish and Spanish-English translation shared tasks in both directions. The CUED system is a hierarchical phrase-based system that uses finite-state transducers and lattice rescoring. In the French-English ta...
متن کاملThe HiFST System for the EuroParl Spanish-to-English Task
In this paper we present results for the Europarl Spanish-to-English translation task. We use HiFST, a novel hierarchical phrase-based translation system implemented with finite-state technology that creates target lattices rather than k-best lists.
متن کاملFurther Experiments with Shallow Hybrid MT Systems
We describe our hybrid machine translation system which has been developed for and used in the WMT10 shared task. We compute translations from a rulebased MT system and combine the resulting translation “templates” with partial phrases from a state-of-the-art phrasebased, statistical MT engine. Phrase substitution is guided by several decision factors, a continuation of previous work within our...
متن کاملEl Sistema HiFST Aplicado a la Tarea de Castellano-Inglés del Europarl
In this paper we present results for the Europarl Spanish-to-English translation task. We use HiFST, a novel hierarchical phrase-based translation system implemented with finite-state technology that creates target lattices rather than k-best lists.
متن کاملFindings of the 2010 Joint Workshop on Statistical Machine Translation and Metrics for Machine Translation
This paper presents the results of the WMT10 and MetricsMATR10 shared tasks,1 which included a translation task, a system combination task, and an evaluation task. We conducted a large-scale manual evaluation of 104 machine translation systems and 41 system combination entries. We used the ranking of these systems to measure how strongly automatic metrics correlate with human judgments of trans...
متن کامل