FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2336583208> ?p ?o ?g. }

• W2336583208 abstract "Since sub-sentential alignment is critically important to the translation quality of an ExampleBased Machine Translation (EBMT) system, which operates by finding and combining phrase-level matches against the training examples, we developed a new alignment algorithm for the purpose of improving the EBMT system’s performance. This new Symmetric Probabilistic Alignment (SPA) algorithm treats the source and target languages in a symmetric fashion. We describe our basic algorithm and its primary extensions that enable use of surrounding context, and of positional preference information, compare its alignment accuracy with IBM Model 4, and report on experiments in which either IBM Model 4 or SPA alignments are substituted for the aligner currently built into the EBMT system. Both Model 4 and SPA are significantly better than the internal aligner. Then we extend SPA to exploit external alignment information from Moses and to output non-contiguous target phrases. We also alter SPA so that the weights for its feature scores are tuned using minimum error rate training. Our experiments show that exploiting external alignment information and non-contiguous alignment are helpful for SPA in the EBMT system. Even with these improvements, however, SPA still could not properly deal with systematic translation for insertion or deletion words between two distant languages. Therefore, we attempt to alleviate this problem by using syntactic chunks as translation units. To do so, we developed a new chunk alignment algorithm that exploits word alignment information to align chunks. Then we integrated a chunk-based translation component based on the chunk alignment into the EBMT system that uses SPA for phrasal alignment. We show that the chunk alignment performs significantly better than the baseline system that aligns two chunks if any word pair of the two chunks has word alignment link. We also demonstrate that the system with chunk-based translation is significantly better than the baseline EBMT system with SPA in translation quality." @default.
• W2336583208 created "2016-06-24" @default.
• W2336583208 creator A5080895296 @default.
• W2336583208 date "2011-01-01" @default.
• W2336583208 modified "2023-09-24" @default.
• W2336583208 title "Chunk alignment for Corpus-Based Machine Translation" @default.
• W2336583208 cites W1480519300 @default.
• W2336583208 cites W1489834179 @default.
• W2336583208 cites W1521937871 @default.
• W2336583208 cites W1522263329 @default.
• W2336583208 cites W1528268292 @default.
• W2336583208 cites W1551705512 @default.
• W2336583208 cites W173608067 @default.
• W2336583208 cites W1973923101 @default.
• W2336583208 cites W1978082594 @default.
• W2336583208 cites W1983201496 @default.
• W2336583208 cites W1987869189 @default.
• W2336583208 cites W2002532287 @default.
• W2336583208 cites W2002785199 @default.
• W2336583208 cites W2006969979 @default.
• W2336583208 cites W2011008859 @default.
• W2336583208 cites W2038698865 @default.
• W2336583208 cites W2048390999 @default.
• W2336583208 cites W2062766658 @default.
• W2336583208 cites W2063381274 @default.
• W2336583208 cites W2065459442 @default.
• W2336583208 cites W2082754765 @default.
• W2336583208 cites W2083017767 @default.
• W2336583208 cites W2097125878 @default.
• W2336583208 cites W2097606805 @default.
• W2336583208 cites W2097790277 @default.
• W2336583208 cites W2099111195 @default.
• W2336583208 cites W2101105183 @default.
• W2336583208 cites W2106068492 @default.
• W2336583208 cites W2108540317 @default.
• W2336583208 cites W2113541941 @default.
• W2336583208 cites W2117745860 @default.
• W2336583208 cites W2119168550 @default.
• W2336583208 cites W2119224513 @default.
• W2336583208 cites W2120513984 @default.
• W2336583208 cites W2121479142 @default.
• W2336583208 cites W2123156796 @default.
• W2336583208 cites W2123301721 @default.
• W2336583208 cites W2123962305 @default.
• W2336583208 cites W2124807415 @default.
• W2336583208 cites W2129765547 @default.
• W2336583208 cites W2131988669 @default.
• W2336583208 cites W2135399222 @default.
• W2336583208 cites W2138753018 @default.
• W2336583208 cites W2138787466 @default.
• W2336583208 cites W2144211451 @default.
• W2336583208 cites W2146459952 @default.
• W2336583208 cites W2146574666 @default.
• W2336583208 cites W2149555425 @default.
• W2336583208 cites W2152263452 @default.
• W2336583208 cites W2155958522 @default.
• W2336583208 cites W2156985047 @default.
• W2336583208 cites W2158388102 @default.
• W2336583208 cites W2161792612 @default.
• W2336583208 cites W2165109801 @default.
• W2336583208 cites W2167072947 @default.
• W2336583208 cites W222053410 @default.
• W2336583208 cites W3197037075 @default.
• W2336583208 cites W3204570878 @default.
• W2336583208 cites W72275503 @default.
• W2336583208 cites W131115700 @default.
• W2336583208 hasPublicationYear "2011" @default.
• W2336583208 type Work @default.
• W2336583208 sameAs 2336583208 @default.
• W2336583208 citedByCount "0" @default.
• W2336583208 crossrefType "book-chapter" @default.
• W2336583208 hasAuthorship W2336583208A5080895296 @default.
• W2336583208 hasConcept C104317684 @default.
• W2336583208 hasConcept C105580179 @default.
• W2336583208 hasConcept C138885662 @default.
• W2336583208 hasConcept C149364088 @default.
• W2336583208 hasConcept C151730666 @default.
• W2336583208 hasConcept C154945302 @default.
• W2336583208 hasConcept C165696696 @default.
• W2336583208 hasConcept C171250308 @default.
• W2336583208 hasConcept C185592680 @default.
• W2336583208 hasConcept C192562407 @default.
• W2336583208 hasConcept C203005215 @default.
• W2336583208 hasConcept C204321447 @default.
• W2336583208 hasConcept C2776224158 @default.
• W2336583208 hasConcept C2776401178 @default.
• W2336583208 hasConcept C2779343474 @default.
• W2336583208 hasConcept C38652104 @default.
• W2336583208 hasConcept C41008148 @default.
• W2336583208 hasConcept C41895202 @default.
• W2336583208 hasConcept C49937458 @default.
• W2336583208 hasConcept C53893814 @default.
• W2336583208 hasConcept C55493867 @default.
• W2336583208 hasConcept C70388272 @default.
• W2336583208 hasConcept C86803240 @default.
• W2336583208 hasConcept C90805587 @default.
• W2336583208 hasConceptScore W2336583208C104317684 @default.
• W2336583208 hasConceptScore W2336583208C105580179 @default.
• W2336583208 hasConceptScore W2336583208C138885662 @default.
• W2336583208 hasConceptScore W2336583208C149364088 @default.

• next