Drem: The AFRL Submission to the WMT15 Tuning Task

نویسندگان

  • Grant Erdmann
  • Jeremy Gwinnup
چکیده

We define a new algorithm, named “Drem”, for tuning the weighted linear model in a statistical machine translation system. Drem has two major innovations. First, it uses scaled derivative-free trust-region optimization rather than other methods’ line search or (sub)gradient approximations. Second, it interpolates the decoder output, using information about which decodes produced which translations.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

The AFRL-MITLL WMT15 System: There's More than One Way to Decode It!

This paper describes the AFRL-MITLL statistical MT systems and the improvements that were developed during the WMT15 evaluation campaign. As part of these efforts we experimented with a number of extensions to the standard phrasebased model that improve performance on the Russian to English translation task creating three submission systems with different decoding strategies. Out of vocabulary ...

متن کامل

BEER 1.1: ILLC UvA submission to metrics and tuning task

We describe the submissions of ILLC UvA to the metrics and tuning tasks on WMT15. Both submissions are based on the BEER evaluation metric originally presented on WMT14 (Stanojević and Sima’an, 2014a). The main changes introduced this year are: (i) extending the learning-to-rank trained sentence level metric to the corpus level (but still decomposable to sentence level), (ii) incorporating synt...

متن کامل

CUNI in WMT15: Chimera Strikes Again

This paper describes our WMT15 system submission for the translation task, a hybrid system for English-to-Czech translation. We repeat the successful setup from the previous two years.

متن کامل

Results of the WMT15 Tuning Shared Task

This paper presents the results of the WMT15 Tuning Shared Task. We provided the participants of this task with a complete machine translation system and asked them to tune its internal parameters (feature weights). The tuned systems were used to translate the test set and the outputs were manually ranked for translation quality. We received 4 submissions in the English-Czech and 6 in the Czech...

متن کامل

Sheffield Systems for the Finnish-English WMT Translation Task

This paper provides an overview of the Sheffield University submission to the WMT15 Translation Task for the FinnishEnglish language pair. The submitted translations were created from a system built using the CDEC decoder. Finnish is a morphologically rich language with elements such as nouns and verbs carrying a large number of inflectional types. Consequently, our improvements are based on mo...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2015