Matches in SemOpenAlex for { <https://semopenalex.org/work/W2117617819> ?p ?o ?g. }
- W2117617819 endingPage "965" @default.
- W2117617819 startingPage "957" @default.
- W2117617819 abstract "This paper presents efficient algorithms for expected similarity maximization, which coincides with minimum Bayes decoding for a similarity-based loss function. Our algorithms are designed for similarity functions that are sequence kernels in a general class of positive definite symmetric kernels. We discuss both a general algorithm and a more efficient algorithm applicable in a common unambiguous scenario. We also describe the application of our algorithms to machine translation and report the results of experiments with several translation data sets which demonstrate a substantial speed-up. In particular, our results show a speed-up by two orders of magnitude with respect to the original method of Tromble et al. (2008) and by a factor of 3 or more even with respect to an approximate algorithm specifically designed for that task. These results open the path for the exploration of more appropriate or optimal kernels for the specific tasks considered." @default.
- W2117617819 created "2016-06-24" @default.
- W2117617819 creator A5014137885 @default.
- W2117617819 creator A5018646392 @default.
- W2117617819 creator A5030888546 @default.
- W2117617819 creator A5058849006 @default.
- W2117617819 creator A5065338569 @default.
- W2117617819 date "2010-06-02" @default.
- W2117617819 modified "2023-09-24" @default.
- W2117617819 title "Expected Sequence Similarity Maximization" @default.
- W2117617819 cites W1480643256 @default.
- W2117617819 cites W1513168562 @default.
- W2117617819 cites W1578332044 @default.
- W2117617819 cites W1582482241 @default.
- W2117617819 cites W1629199664 @default.
- W2117617819 cites W179694669 @default.
- W2117617819 cites W1993666847 @default.
- W2117617819 cites W2020816856 @default.
- W2117617819 cites W2099964107 @default.
- W2117617819 cites W2100000146 @default.
- W2117617819 cites W2100238596 @default.
- W2117617819 cites W2101105183 @default.
- W2117617819 cites W2118439278 @default.
- W2117617819 cites W2119168550 @default.
- W2117617819 cites W2136657878 @default.
- W2117617819 cites W2138414624 @default.
- W2117617819 cites W2159358338 @default.
- W2117617819 cites W2160392347 @default.
- W2117617819 cites W2161195767 @default.
- W2117617819 cites W222053410 @default.
- W2117617819 hasPublicationYear "2010" @default.
- W2117617819 type Work @default.
- W2117617819 sameAs 2117617819 @default.
- W2117617819 citedByCount "2" @default.
- W2117617819 countsByYear W21176178192015 @default.
- W2117617819 crossrefType "proceedings-article" @default.
- W2117617819 hasAuthorship W2117617819A5014137885 @default.
- W2117617819 hasAuthorship W2117617819A5018646392 @default.
- W2117617819 hasAuthorship W2117617819A5030888546 @default.
- W2117617819 hasAuthorship W2117617819A5058849006 @default.
- W2117617819 hasAuthorship W2117617819A5065338569 @default.
- W2117617819 hasConcept C103278499 @default.
- W2117617819 hasConcept C104317684 @default.
- W2117617819 hasConcept C105580179 @default.
- W2117617819 hasConcept C11413529 @default.
- W2117617819 hasConcept C115961682 @default.
- W2117617819 hasConcept C126255220 @default.
- W2117617819 hasConcept C14036430 @default.
- W2117617819 hasConcept C149364088 @default.
- W2117617819 hasConcept C154945302 @default.
- W2117617819 hasConcept C185592680 @default.
- W2117617819 hasConcept C199360897 @default.
- W2117617819 hasConcept C203005215 @default.
- W2117617819 hasConcept C2776330181 @default.
- W2117617819 hasConcept C2777735758 @default.
- W2117617819 hasConcept C2778112365 @default.
- W2117617819 hasConcept C33923547 @default.
- W2117617819 hasConcept C41008148 @default.
- W2117617819 hasConcept C54355233 @default.
- W2117617819 hasConcept C55493867 @default.
- W2117617819 hasConcept C57273362 @default.
- W2117617819 hasConcept C78458016 @default.
- W2117617819 hasConcept C86803240 @default.
- W2117617819 hasConceptScore W2117617819C103278499 @default.
- W2117617819 hasConceptScore W2117617819C104317684 @default.
- W2117617819 hasConceptScore W2117617819C105580179 @default.
- W2117617819 hasConceptScore W2117617819C11413529 @default.
- W2117617819 hasConceptScore W2117617819C115961682 @default.
- W2117617819 hasConceptScore W2117617819C126255220 @default.
- W2117617819 hasConceptScore W2117617819C14036430 @default.
- W2117617819 hasConceptScore W2117617819C149364088 @default.
- W2117617819 hasConceptScore W2117617819C154945302 @default.
- W2117617819 hasConceptScore W2117617819C185592680 @default.
- W2117617819 hasConceptScore W2117617819C199360897 @default.
- W2117617819 hasConceptScore W2117617819C203005215 @default.
- W2117617819 hasConceptScore W2117617819C2776330181 @default.
- W2117617819 hasConceptScore W2117617819C2777735758 @default.
- W2117617819 hasConceptScore W2117617819C2778112365 @default.
- W2117617819 hasConceptScore W2117617819C33923547 @default.
- W2117617819 hasConceptScore W2117617819C41008148 @default.
- W2117617819 hasConceptScore W2117617819C54355233 @default.
- W2117617819 hasConceptScore W2117617819C55493867 @default.
- W2117617819 hasConceptScore W2117617819C57273362 @default.
- W2117617819 hasConceptScore W2117617819C78458016 @default.
- W2117617819 hasConceptScore W2117617819C86803240 @default.
- W2117617819 hasLocation W21176178191 @default.
- W2117617819 hasOpenAccess W2117617819 @default.
- W2117617819 hasPrimaryLocation W21176178191 @default.
- W2117617819 hasRelatedWork W116427867 @default.
- W2117617819 hasRelatedWork W1480181449 @default.
- W2117617819 hasRelatedWork W1529507376 @default.
- W2117617819 hasRelatedWork W1590323350 @default.
- W2117617819 hasRelatedWork W1849431564 @default.
- W2117617819 hasRelatedWork W1965260463 @default.
- W2117617819 hasRelatedWork W1977709968 @default.
- W2117617819 hasRelatedWork W1988054014 @default.
- W2117617819 hasRelatedWork W2065225164 @default.
- W2117617819 hasRelatedWork W2095981367 @default.