Matches in SemOpenAlex for { <https://semopenalex.org/work/W2130614777> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W2130614777 abstract "To enable downstream language processing,automatic speech recognition output must be segmented into its individual sentences. Previous sentence segmentation systems have typically been very local,using low-level prosodic and lexical features to independently decide whether or not to segment at each word boundary position. In this work,we leverage global syntactic information from a syntactic parser, which is better able to capture long distance dependencies. While some previous work has included syntactic features, ours is the first to do so in a tractable, lattice-based way, which is crucial for scaling up to long-sentence contexts. Specifically, an initial hypothesis lattice is constructed using local features. Candidate sentences are then assigned syntactic language model scores. These global syntactic scores are combined with local low-level scores in a log-linear model. The resulting system significantly outperforms the most popular long-span model for sentence segmentation (the hidden event language model) on both reference text and automatic speech recognizer output from news broadcasts." @default.
- W2130614777 created "2016-06-24" @default.
- W2130614777 creator A5004921249 @default.
- W2130614777 creator A5062886906 @default.
- W2130614777 creator A5068709817 @default.
- W2130614777 creator A5071505335 @default.
- W2130614777 date "2008-12-01" @default.
- W2130614777 modified "2023-09-26" @default.
- W2130614777 title "Efficient sentence segmentation using syntactic features" @default.
- W2130614777 cites W1504308419 @default.
- W2130614777 cites W1551104980 @default.
- W2130614777 cites W189129698 @default.
- W2130614777 cites W204933015 @default.
- W2130614777 cites W2097584131 @default.
- W2130614777 cites W2158188757 @default.
- W2130614777 cites W2161653775 @default.
- W2130614777 cites W3313028 @default.
- W2130614777 cites W94670513 @default.
- W2130614777 doi "https://doi.org/10.1109/slt.2008.4777844" @default.
- W2130614777 hasPublicationYear "2008" @default.
- W2130614777 type Work @default.
- W2130614777 sameAs 2130614777 @default.
- W2130614777 citedByCount "20" @default.
- W2130614777 countsByYear W21306147772012 @default.
- W2130614777 countsByYear W21306147772013 @default.
- W2130614777 countsByYear W21306147772014 @default.
- W2130614777 countsByYear W21306147772016 @default.
- W2130614777 countsByYear W21306147772017 @default.
- W2130614777 countsByYear W21306147772019 @default.
- W2130614777 countsByYear W21306147772020 @default.
- W2130614777 countsByYear W21306147772021 @default.
- W2130614777 crossrefType "proceedings-article" @default.
- W2130614777 hasAuthorship W2130614777A5004921249 @default.
- W2130614777 hasAuthorship W2130614777A5062886906 @default.
- W2130614777 hasAuthorship W2130614777A5068709817 @default.
- W2130614777 hasAuthorship W2130614777A5071505335 @default.
- W2130614777 hasConcept C137293760 @default.
- W2130614777 hasConcept C153083717 @default.
- W2130614777 hasConcept C154945302 @default.
- W2130614777 hasConcept C186644900 @default.
- W2130614777 hasConcept C204321447 @default.
- W2130614777 hasConcept C2777530160 @default.
- W2130614777 hasConcept C28490314 @default.
- W2130614777 hasConcept C41008148 @default.
- W2130614777 hasConcept C89600930 @default.
- W2130614777 hasConcept C98501671 @default.
- W2130614777 hasConceptScore W2130614777C137293760 @default.
- W2130614777 hasConceptScore W2130614777C153083717 @default.
- W2130614777 hasConceptScore W2130614777C154945302 @default.
- W2130614777 hasConceptScore W2130614777C186644900 @default.
- W2130614777 hasConceptScore W2130614777C204321447 @default.
- W2130614777 hasConceptScore W2130614777C2777530160 @default.
- W2130614777 hasConceptScore W2130614777C28490314 @default.
- W2130614777 hasConceptScore W2130614777C41008148 @default.
- W2130614777 hasConceptScore W2130614777C89600930 @default.
- W2130614777 hasConceptScore W2130614777C98501671 @default.
- W2130614777 hasLocation W21306147771 @default.
- W2130614777 hasOpenAccess W2130614777 @default.
- W2130614777 hasPrimaryLocation W21306147771 @default.
- W2130614777 hasRelatedWork W1504308419 @default.
- W2130614777 hasRelatedWork W1567281825 @default.
- W2130614777 hasRelatedWork W1864243922 @default.
- W2130614777 hasRelatedWork W1865731626 @default.
- W2130614777 hasRelatedWork W189129698 @default.
- W2130614777 hasRelatedWork W1911521811 @default.
- W2130614777 hasRelatedWork W1972873790 @default.
- W2130614777 hasRelatedWork W1976448505 @default.
- W2130614777 hasRelatedWork W2069059998 @default.
- W2130614777 hasRelatedWork W2097584131 @default.
- W2130614777 hasRelatedWork W2122730850 @default.
- W2130614777 hasRelatedWork W2124246394 @default.
- W2130614777 hasRelatedWork W2147350917 @default.
- W2130614777 hasRelatedWork W2168892890 @default.
- W2130614777 hasRelatedWork W2170582114 @default.
- W2130614777 hasRelatedWork W2426479676 @default.
- W2130614777 hasRelatedWork W28144983 @default.
- W2130614777 hasRelatedWork W90695545 @default.
- W2130614777 hasRelatedWork W94670513 @default.
- W2130614777 hasRelatedWork W2413854561 @default.
- W2130614777 isParatext "false" @default.
- W2130614777 isRetracted "false" @default.
- W2130614777 magId "2130614777" @default.
- W2130614777 workType "article" @default.