Combination of Machine Translation Systems via Hypothesis Selection from Combined N-Best Lists
نویسندگان
چکیده
Different approaches in machine translation achieve similar translation quality with a variety of translations in the output. Recently it has been shown, that it is possible to leverage the individual strengths of various systems and improve the overall translation quality by combining translation outputs. In this paper we present a method of hypothesis selection which is relatively simple compared to system combination methods which construct a synthesis of the input hypotheses. Our method uses information from n-best lists from several MT systems and features on the sentence level which are independent from the MT systems involved to improve the translation quality.
منابع مشابه
CMU System Combination via Hypothesis Selection for WMT'10
This paper describes the CMU entry for the system combination shared task at WMT’10. Our combination method is hypothesis selection, which uses information from n-best lists from the input MT systems, where available. The sentence level features used are independent from the MT systems involved. Compared to the baseline we added source-to-target word alignment based features and trained system ...
متن کاملCMU System Combination for WMT'09
This paper describes the CMU entry for the system combination shared task at WMT’09. Our combination method is hypothesis selection, which uses information from n-best lists from several MT systems. The sentence level features are independent from the MT systems involved. To compensate for various n-best list sizes in the workshop shared task including firstbest-only entries, we normalize one o...
متن کاملThe NICT translation system for IWSLT 2010
This paper describes NICT’s participation in the IWSLT 2010 evaluation campaign for the DIALOG translation (Chinese-English) and the BTEC (French-English) translation shared-tasks. For the DIALOG translation, the main challenge to this task is applying context information during translation. Context information can be used to decide on word choice and also to replace missing information during ...
متن کاملReordering via N-Best Lists for Spanish-Basque Translation
In Statistical Machine Translation (SMT), one of the main problems they are confronted with is the problem stemming from the different word order that different languages imply. Most works addressing this issue centre their effort in pairs of languages involving Arabic, Japanese or Chinese because of their utmost different origin with respect to western languages. However, Basque is also a lang...
متن کاملNon-linear n-best List Reranking with Few Features
In Machine Translation, it is customary to compute the model score of a predicted hypothesis as a linear combination of multiple features, where each feature assesses a particular facet of the hypothesis. The choice of a linear combination is usually justified by the possibility of efficient inference (decoding); yet, the appropriateness of this simple combination scheme to the task at hand is ...
متن کامل