The CMU-Avenue French-English Translation System
نویسندگان
چکیده
This paper describes the French-English translation system developed by the Avenue research group at Carnegie Mellon University for the Seventh Workshop on Statistical Machine Translation (NAACL WMT12). We present a method for training data selection, a description of our hierarchical phrase-based translation system, and a discussion of the impact of data size on best practice for system building.
منابع مشابه
CMU Multi - Engine Machine Translation for WMT 2010 Kenneth
This paper describes our submission, cmu-heafield-combo, to the WMT 2010 machine translation system combination task. Using constrained resources, we participated in all nine language pairs, namely translating English to and from Czech, French, German, and Spanish as well as combining English translations from multiple languages. Combination proceeds by aligning all pairs of system outputs then...
متن کاملCMU Multi-Engine Machine Translation for WMT 2010
This paper describes our submission, cmu-heafield-combo, to the WMT 2010 machine translation system combination task. Using constrained resources, we participated in all nine language pairs, namely translating English to and from Czech, French, German, and Spanish as well as combining English translations from multiple languages. Combination proceeds by aligning all pairs of system outputs then...
متن کاملAbcdeffabbbed Dbfabffdbb Eb!b"#$$ Abcdebbafca Aacceae Cccc !a !acaa!ee" #$c!%ee&'(e%!'(#)* Ddd&&e&&f
This report describes the machine translation system tuning experiments leading to CMU system submissions to the WMT 2011 French-English and Haitian-English translation tracks. For each language track, we tune a standard phrase-based SMT system to a variety of metrics including BLEU, TER, and several variations of METEOR. We select a balanced Tuning version of METEOR that performs well across t...
متن کاملThe CMU Machine Translation Systems at WMT 2013: Syntax, Synthetic Translation Options, and Pseudo-References
We describe the CMU systems submitted to the 2013 WMT shared task in machine translation. We participated in three language pairs, French–English, Russian– English, and English–Russian. Our particular innovations include: a labelcoarsening scheme for syntactic tree-totree translation and the use of specialized modules to create “synthetic translation options” that can both generalize beyond wha...
متن کاملModels of Translation Competitions
What do we want to learn from a translation competition and how do we learn it with confidence? We argue that a disproportionate focus on ranking competition participants has led to lots of different rankings, but little insight about which rankings we should trust. In response, we provide the first framework that allows an empirical comparison of different analyses of competition results. We t...
متن کامل