FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W1972567251> ?p ?o ?g. }

• W1972567251 endingPage "527" @default.
• W1972567251 startingPage "496" @default.
• W1972567251 abstract "In this article we address the issue of generating diversified translation systems from a single Statistical Machine Translation (SMT) engine for system combination. Unlike traditional approaches, we do not resort to multiple structurally different SMT systems, but instead directly learn a strong SMT system from a single translation engine in a principled way. Our approach is based on Bagging and Boosting which are two instances of the general framework of ensemble learning. The basic idea is that we first generate an ensemble of weak translation systems using a base learning algorithm, and then learn a strong translation system from the ensemble. One of the advantages of our approach is that it can work with any of current SMT systems and make them stronger almost “for free”. Beyond this, most system combination methods are directly applicable to the proposed framework for generating the final translation system from the ensemble of weak systems. We evaluate our approach on Chinese–English translation in three state-of-the-art SMT systems, including a phrase-based system, a hierarchical phrase-based system and a syntax-based system. Experimental results on the NIST MT evaluation corpora show that our approach leads to significant improvements in translation accuracy over the baselines. More interestingly, it is observed that our approach is able to improve the existing system combination systems. The biggest improvements are obtained by generating weak systems using Bagging/Boosting, and learning the strong system using a state-of-the-art system combination method." @default.
• W1972567251 created "2016-06-24" @default.
• W1972567251 creator A5012126405 @default.
• W1972567251 creator A5032686951 @default.
• W1972567251 creator A5062470278 @default.
• W1972567251 date "2013-02-01" @default.
• W1972567251 modified "2023-09-30" @default.
• W1972567251 title "Bagging and Boosting statistical machine translation systems" @default.
• W1972567251 cites W1483849869 @default.
• W1972567251 cites W1494780677 @default.
• W1972567251 cites W1529490620 @default.
• W1972567251 cites W1605688901 @default.
• W1972567251 cites W1840338487 @default.
• W1972567251 cites W1964388487 @default.
• W1972567251 cites W1975846642 @default.
• W1972567251 cites W1988790447 @default.
• W1972567251 cites W1993666847 @default.
• W1972567251 cites W2027902935 @default.
• W1972567251 cites W2032175749 @default.
• W1972567251 cites W2053463056 @default.
• W1972567251 cites W2070534370 @default.
• W1972567251 cites W2073040595 @default.
• W1972567251 cites W2073738917 @default.
• W1972567251 cites W2078861931 @default.
• W1972567251 cites W2095683820 @default.
• W1972567251 cites W2095755718 @default.
• W1972567251 cites W2100238596 @default.
• W1972567251 cites W2100805904 @default.
• W1972567251 cites W2101105183 @default.
• W1972567251 cites W2104327354 @default.
• W1972567251 cites W2111142112 @default.
• W1972567251 cites W2112900913 @default.
• W1972567251 cites W2113242816 @default.
• W1972567251 cites W2113287090 @default.
• W1972567251 cites W2115410424 @default.
• W1972567251 cites W2116957398 @default.
• W1972567251 cites W2117164663 @default.
• W1972567251 cites W2118536060 @default.
• W1972567251 cites W2118960083 @default.
• W1972567251 cites W2118972857 @default.
• W1972567251 cites W2125750666 @default.
• W1972567251 cites W2128232128 @default.
• W1972567251 cites W2132549764 @default.
• W1972567251 cites W2135293965 @default.
• W1972567251 cites W2138470801 @default.
• W1972567251 cites W2138934709 @default.
• W1972567251 cites W2141852716 @default.
• W1972567251 cites W2143008661 @default.
• W1972567251 cites W2143564602 @default.
• W1972567251 cites W2144002870 @default.
• W1972567251 cites W2144279206 @default.
• W1972567251 cites W2145033586 @default.
• W1972567251 cites W2146574666 @default.
• W1972567251 cites W2152263452 @default.
• W1972567251 cites W2152761983 @default.
• W1972567251 cites W2153653739 @default.
• W1972567251 cites W2154124206 @default.
• W1972567251 cites W2155806188 @default.
• W1972567251 cites W2157124852 @default.
• W1972567251 cites W2157875692 @default.
• W1972567251 cites W2159358338 @default.
• W1972567251 cites W2160571323 @default.
• W1972567251 cites W2165666205 @default.
• W1972567251 cites W2166197739 @default.
• W1972567251 cites W2171802951 @default.
• W1972567251 cites W2437005631 @default.
• W1972567251 cites W28412257 @default.
• W1972567251 cites W3004732066 @default.
• W1972567251 cites W3152294918 @default.
• W1972567251 cites W4212883601 @default.
• W1972567251 doi "https://doi.org/10.1016/j.artint.2012.11.005" @default.
• W1972567251 hasPublicationYear "2013" @default.
• W1972567251 type Work @default.
• W1972567251 sameAs 1972567251 @default.
• W1972567251 citedByCount "35" @default.
• W1972567251 countsByYear W19725672512013 @default.
• W1972567251 countsByYear W19725672512014 @default.
• W1972567251 countsByYear W19725672512015 @default.
• W1972567251 countsByYear W19725672512016 @default.
• W1972567251 countsByYear W19725672512017 @default.
• W1972567251 countsByYear W19725672512018 @default.
• W1972567251 countsByYear W19725672512019 @default.
• W1972567251 countsByYear W19725672512020 @default.
• W1972567251 countsByYear W19725672512021 @default.
• W1972567251 countsByYear W19725672512022 @default.
• W1972567251 countsByYear W19725672512023 @default.
• W1972567251 crossrefType "journal-article" @default.
• W1972567251 hasAuthorship W1972567251A5012126405 @default.
• W1972567251 hasAuthorship W1972567251A5032686951 @default.
• W1972567251 hasAuthorship W1972567251A5062470278 @default.
• W1972567251 hasConcept C104317684 @default.
• W1972567251 hasConcept C105580179 @default.
• W1972567251 hasConcept C111219384 @default.
• W1972567251 hasConcept C119857082 @default.
• W1972567251 hasConcept C149364088 @default.
• W1972567251 hasConcept C154945302 @default.
• W1972567251 hasConcept C185592680 @default.
• W1972567251 hasConcept C203005215 @default.

• next