Access Restriction

Author Haddow, Barry ♦ Arun, Abhishek
Source CiteSeerX
Content type Text
File Format PDF
Language English
Subject Domain (in DDC) Computer science, information & general works ♦ Data processing & computer science
Subject Keyword Medium Sized System ♦ Output Sentence ♦ Chosen Gain Function ♦ Discriminative Training ♦ Gain Function ♦ Alternative Algorithm ♦ Phrase-based Machine Translation ♦ Model Weight ♦ 20-30 Feature ♦ Phrasebased Mt System ♦ Stability Problem ♦ Document Level Feature ♦ Beat Mert ♦ Samplerank Training ♦ Samplerank Proceeds ♦ Statistical Machine Translation System ♦ Algorithm Suffers
Description In WMT
Statistical machine translation systems are normally optimised for a chosen gain function (metric) by using MERT to find the best model weights. This algorithm suffers from stability problems and cannot scale beyond 20-30 features. We present an alternative algorithm for discriminative training of phrasebased MT systems, SampleRank, which scales to hundreds of features, equals or beats MERT on both small and medium sized systems, and permits the use of sentence or document level features. SampleRank proceeds by repeatedly updating the model weights to ensure that the ranking of output sentences induced by the model is the same as that induced by the gain function. 1
Educational Role Student ♦ Teacher
Age Range above 22 year
Educational Use Research
Education Level UG and PG ♦ Career/Technical Study
Learning Resource Type Article
Publisher Date 2011-01-01