Matches in SemOpenAlex for { <https://semopenalex.org/work/W2116180041> ?p ?o ?g. }
- W2116180041 abstract "Speech summarization, facilitating users to better browse through and understand speech information (especially, spoken documents), has become an active area of intensive research recently. Many of the existing machine-learning approaches to speech summarization cast important sentence selection as a two-class classification problem and have shown empirical success for a wide array of summarization tasks. One common deficiency of these approaches is that the corresponding learning criteria are loosely related to the final evaluation metric. To cater for this problem, we present a novel probabilistic framework to learn the summarization models, building on top of the Bayes decision theory. Two effective training criteria, viz. maximum relevance estimation (MRE) and minimum ranking loss estimation (MRLE), deduced from such a framework are introduced to characterize the pair-wise preference relationships between spoken sentences. Experiments on a broadcast news speech summarization task exhibit the performance merits of our summarization methods when compared to existing methods." @default.
- W2116180041 created "2016-06-24" @default.
- W2116180041 creator A5000009544 @default.
- W2116180041 creator A5033839875 @default.
- W2116180041 creator A5053222355 @default.
- W2116180041 date "2012-03-01" @default.
- W2116180041 modified "2023-09-25" @default.
- W2116180041 title "Constructing effective ranking models for speech summarization" @default.
- W2116180041 cites W1505175215 @default.
- W2116180041 cites W1577877742 @default.
- W2116180041 cites W179757531 @default.
- W2116180041 cites W1877570817 @default.
- W2116180041 cites W1988520084 @default.
- W2116180041 cites W1993666847 @default.
- W2116180041 cites W2036223361 @default.
- W2116180041 cites W2097321121 @default.
- W2116180041 cites W2107326178 @default.
- W2116180041 cites W2117390600 @default.
- W2116180041 cites W2120128255 @default.
- W2116180041 cites W2131381130 @default.
- W2116180041 cites W2136657878 @default.
- W2116180041 cites W2140365917 @default.
- W2116180041 cites W2141540671 @default.
- W2116180041 cites W2146574666 @default.
- W2116180041 cites W2151844545 @default.
- W2116180041 cites W2158025800 @default.
- W2116180041 cites W2293771131 @default.
- W2116180041 cites W2913074841 @default.
- W2116180041 cites W2974222084 @default.
- W2116180041 doi "https://doi.org/10.1109/icassp.2012.6289056" @default.
- W2116180041 hasPublicationYear "2012" @default.
- W2116180041 type Work @default.
- W2116180041 sameAs 2116180041 @default.
- W2116180041 citedByCount "2" @default.
- W2116180041 countsByYear W21161800412014 @default.
- W2116180041 countsByYear W21161800412016 @default.
- W2116180041 crossrefType "proceedings-article" @default.
- W2116180041 hasAuthorship W2116180041A5000009544 @default.
- W2116180041 hasAuthorship W2116180041A5033839875 @default.
- W2116180041 hasAuthorship W2116180041A5053222355 @default.
- W2116180041 hasConcept C119857082 @default.
- W2116180041 hasConcept C134714966 @default.
- W2116180041 hasConcept C154945302 @default.
- W2116180041 hasConcept C158154518 @default.
- W2116180041 hasConcept C162324750 @default.
- W2116180041 hasConcept C170858558 @default.
- W2116180041 hasConcept C176217482 @default.
- W2116180041 hasConcept C17744445 @default.
- W2116180041 hasConcept C187736073 @default.
- W2116180041 hasConcept C189430467 @default.
- W2116180041 hasConcept C199539241 @default.
- W2116180041 hasConcept C204321447 @default.
- W2116180041 hasConcept C21547014 @default.
- W2116180041 hasConcept C2777530160 @default.
- W2116180041 hasConcept C2780451532 @default.
- W2116180041 hasConcept C41008148 @default.
- W2116180041 hasConcept C49937458 @default.
- W2116180041 hasConcept C81917197 @default.
- W2116180041 hasConceptScore W2116180041C119857082 @default.
- W2116180041 hasConceptScore W2116180041C134714966 @default.
- W2116180041 hasConceptScore W2116180041C154945302 @default.
- W2116180041 hasConceptScore W2116180041C158154518 @default.
- W2116180041 hasConceptScore W2116180041C162324750 @default.
- W2116180041 hasConceptScore W2116180041C170858558 @default.
- W2116180041 hasConceptScore W2116180041C176217482 @default.
- W2116180041 hasConceptScore W2116180041C17744445 @default.
- W2116180041 hasConceptScore W2116180041C187736073 @default.
- W2116180041 hasConceptScore W2116180041C189430467 @default.
- W2116180041 hasConceptScore W2116180041C199539241 @default.
- W2116180041 hasConceptScore W2116180041C204321447 @default.
- W2116180041 hasConceptScore W2116180041C21547014 @default.
- W2116180041 hasConceptScore W2116180041C2777530160 @default.
- W2116180041 hasConceptScore W2116180041C2780451532 @default.
- W2116180041 hasConceptScore W2116180041C41008148 @default.
- W2116180041 hasConceptScore W2116180041C49937458 @default.
- W2116180041 hasConceptScore W2116180041C81917197 @default.
- W2116180041 hasLocation W21161800411 @default.
- W2116180041 hasOpenAccess W2116180041 @default.
- W2116180041 hasPrimaryLocation W21161800411 @default.
- W2116180041 hasRelatedWork W1541909693 @default.
- W2116180041 hasRelatedWork W1567001743 @default.
- W2116180041 hasRelatedWork W179757531 @default.
- W2116180041 hasRelatedWork W1879936196 @default.
- W2116180041 hasRelatedWork W1966158391 @default.
- W2116180041 hasRelatedWork W1969700396 @default.
- W2116180041 hasRelatedWork W1984364982 @default.
- W2116180041 hasRelatedWork W2033083972 @default.
- W2116180041 hasRelatedWork W2093119036 @default.
- W2116180041 hasRelatedWork W2098283414 @default.
- W2116180041 hasRelatedWork W2099039485 @default.
- W2116180041 hasRelatedWork W2103404183 @default.
- W2116180041 hasRelatedWork W2105382461 @default.
- W2116180041 hasRelatedWork W2109297205 @default.
- W2116180041 hasRelatedWork W2122111711 @default.
- W2116180041 hasRelatedWork W2141514700 @default.
- W2116180041 hasRelatedWork W2153466749 @default.
- W2116180041 hasRelatedWork W2158495349 @default.
- W2116180041 hasRelatedWork W2298163492 @default.
- W2116180041 hasRelatedWork W2606131017 @default.
- W2116180041 isParatext "false" @default.