FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W1662350148> ?p ?o ?g. }

• W1662350148 endingPage "85" @default.
• W1662350148 startingPage "35" @default.
• W1662350148 abstract "Previous approaches of analyzing spontaneously spoken language often have been based on encoding syntactic and semantic knowledge manually and symbolically. While there has been some progress using statistical or connectionist language models, many current spoken-language systems still use a relatively brittle, hand-coded symbolic grammar or symbolic semantic component.In contrast, we describe a so-called screening approach for learning robust processing of spontaneously spoken language. A screening approach is a flat analysis which uses shallow sequences of category representations for analyzing an utterance at various syntactic, semantic and dialog levels. Rather than using a deeply structured symbolic analysis, we use a flat connectionist analysis. This screening approach aims at supporting speech and language processing by using (1) data-driven learning and (2) robustness of connectionist networks. In order to test this approach, we have developed the screen system which is based on this new robust, learned and flat analysis.In this paper, we focus on a detailed description of screen's architecture, the flat syntactic and semantic analysis, the interaction with a speech recognizer, and a detailed evaluation analysis of the robustness under the influence of noisy or incomplete input. The main result of this paper is that flat representations allow more robust processing of spontaneous spoken language than deeply structured representations. In particular, we show how the fault-tolerance and learning capability of connectionist networks can support a flat analysis for providing more robust spoken-language processing within an overall hybrid symbolic/connectionist framework." @default.
• W1662350148 created "2016-06-24" @default.
• W1662350148 creator A5033486668 @default.
• W1662350148 creator A5086179302 @default.
• W1662350148 date "1997-01-01" @default.
• W1662350148 modified "2023-09-26" @default.
• W1662350148 title "SCREEN: learning a flat syntactic and semantic spoken language analysis using artificial neural networks" @default.
• W1662350148 cites W1044396125 @default.
• W1662350148 cites W1519770193 @default.
• W1662350148 cites W1566301929 @default.
• W1662350148 cites W1591234214 @default.
• W1662350148 cites W1603751719 @default.
• W1662350148 cites W1620964569 @default.
• W1662350148 cites W1758863888 @default.
• W1662350148 cites W1934481294 @default.
• W1662350148 cites W1979500821 @default.
• W1662350148 cites W1985419798 @default.
• W1662350148 cites W1994851566 @default.
• W1662350148 cites W2002324068 @default.
• W1662350148 cites W2006077098 @default.
• W1662350148 cites W2014435183 @default.
• W1662350148 cites W2022083899 @default.
• W1662350148 cites W2049488882 @default.
• W1662350148 cites W2054776541 @default.
• W1662350148 cites W2073683349 @default.
• W1662350148 cites W2093476462 @default.
• W1662350148 cites W2097013558 @default.
• W1662350148 cites W2110485445 @default.
• W1662350148 cites W2113941657 @default.
• W1662350148 cites W2114083375 @default.
• W1662350148 cites W2143868493 @default.
• W1662350148 cites W2150884987 @default.
• W1662350148 cites W2153271982 @default.
• W1662350148 cites W2154007344 @default.
• W1662350148 cites W2158789241 @default.
• W1662350148 cites W2164211417 @default.
• W1662350148 cites W2164949130 @default.
• W1662350148 cites W2164977118 @default.
• W1662350148 cites W2569248448 @default.
• W1662350148 cites W2766736793 @default.
• W1662350148 cites W284628447 @default.
• W1662350148 cites W626462138 @default.
• W1662350148 cites W89965911 @default.
• W1662350148 cites W1780577378 @default.
• W1662350148 doi "https://doi.org/10.22028/d291-25253" @default.
• W1662350148 hasPublicationYear "1997" @default.
• W1662350148 type Work @default.
• W1662350148 sameAs 1662350148 @default.
• W1662350148 citedByCount "22" @default.
• W1662350148 countsByYear W16623501482017 @default.
• W1662350148 crossrefType "journal-article" @default.
• W1662350148 hasAuthorship W1662350148A5033486668 @default.
• W1662350148 hasAuthorship W1662350148A5086179302 @default.
• W1662350148 hasConcept C104317684 @default.
• W1662350148 hasConcept C137293760 @default.
• W1662350148 hasConcept C154945302 @default.
• W1662350148 hasConcept C185592680 @default.
• W1662350148 hasConcept C204321447 @default.
• W1662350148 hasConcept C2775852435 @default.
• W1662350148 hasConcept C2776230583 @default.
• W1662350148 hasConcept C28490314 @default.
• W1662350148 hasConcept C41008148 @default.
• W1662350148 hasConcept C50644808 @default.
• W1662350148 hasConcept C55493867 @default.
• W1662350148 hasConcept C63479239 @default.
• W1662350148 hasConcept C8521452 @default.
• W1662350148 hasConceptScore W1662350148C104317684 @default.
• W1662350148 hasConceptScore W1662350148C137293760 @default.
• W1662350148 hasConceptScore W1662350148C154945302 @default.
• W1662350148 hasConceptScore W1662350148C185592680 @default.
• W1662350148 hasConceptScore W1662350148C204321447 @default.
• W1662350148 hasConceptScore W1662350148C2775852435 @default.
• W1662350148 hasConceptScore W1662350148C2776230583 @default.
• W1662350148 hasConceptScore W1662350148C28490314 @default.
• W1662350148 hasConceptScore W1662350148C41008148 @default.
• W1662350148 hasConceptScore W1662350148C50644808 @default.
• W1662350148 hasConceptScore W1662350148C55493867 @default.
• W1662350148 hasConceptScore W1662350148C63479239 @default.
• W1662350148 hasConceptScore W1662350148C8521452 @default.
• W1662350148 hasIssue "1" @default.
• W1662350148 hasLocation W16623501481 @default.
• W1662350148 hasOpenAccess W1662350148 @default.
• W1662350148 hasPrimaryLocation W16623501481 @default.
• W1662350148 hasRelatedWork W1500977665 @default.
• W1662350148 hasRelatedWork W1519770193 @default.
• W1662350148 hasRelatedWork W1863987242 @default.
• W1662350148 hasRelatedWork W1971844566 @default.
• W1662350148 hasRelatedWork W2002089154 @default.
• W1662350148 hasRelatedWork W2002324068 @default.
• W1662350148 hasRelatedWork W2036631620 @default.
• W1662350148 hasRelatedWork W2073257493 @default.
• W1662350148 hasRelatedWork W2087946919 @default.
• W1662350148 hasRelatedWork W2106474089 @default.
• W1662350148 hasRelatedWork W2110485445 @default.
• W1662350148 hasRelatedWork W2138708605 @default.
• W1662350148 hasRelatedWork W2244401980 @default.
• W1662350148 hasRelatedWork W2476701415 @default.
• W1662350148 hasRelatedWork W2766736793 @default.

• next