FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4286632012> ?p ?o ?g. }

• W4286632012 endingPage "886" @default.
• W4286632012 startingPage "849" @default.
• W4286632012 abstract "Abstract Dependency-based approaches to syntactic analysis assume that syntactic structure can be analyzed in terms of binary asymmetric dependency relations holding between elementary syntactic units. Computational models for dependency parsing almost universally assume that an elementary syntactic unit is a word, while the influential theory of Lucien Tesnière instead posits a more abstract notion of nucleus, which may be realized as one or more words. In this article, we investigate the effect of enriching computational parsing models with a concept of nucleus inspired by Tesnière. We begin by reviewing how the concept of nucleus can be defined in the framework of Universal Dependencies, which has become the de facto standard for training and evaluating supervised dependency parsers, and explaining how composition functions can be used to make neural transition-based dependency parsers aware of the nuclei thus defined. We then perform an extensive experimental study, using data from 20 languages to assess the impact of nucleus composition across languages with different typological characteristics, and utilizing a variety of analytical tools including ablation, linear mixed-effects models, diagnostic classifiers, and dimensionality reduction. The analysis reveals that nucleus composition gives small but consistent improvements in parsing accuracy for most languages, and that the improvement mainly concerns the analysis of main predicates, nominal dependents, clausal dependents, and coordination structures. Significant factors explaining the rate of improvement across languages include entropy in coordination structures and frequency of certain function words, in particular determiners. Analysis using dimensionality reduction and diagnostic classifiers suggests that nucleus composition increases the similarity of vectors representing nuclei of the same syntactic type." @default.
• W4286632012 created "2022-07-23" @default.
• W4286632012 creator A5001572213 @default.
• W4286632012 creator A5030452648 @default.
• W4286632012 creator A5052998031 @default.
• W4286632012 creator A5077063699 @default.
• W4286632012 date "2022-01-01" @default.
• W4286632012 modified "2023-10-14" @default.
• W4286632012 title "Nucleus Composition in Transition-based Dependency Parsing" @default.
• W4286632012 cites W116785612 @default.
• W4286632012 cites W1951724000 @default.
• W4286632012 cites W1983819420 @default.
• W4286632012 cites W2010835028 @default.
• W4286632012 cites W2030904529 @default.
• W4286632012 cites W2058951422 @default.
• W4286632012 cites W2097125878 @default.
• W4286632012 cites W2105847779 @default.
• W4286632012 cites W2131395877 @default.
• W4286632012 cites W2134036914 @default.
• W4286632012 cites W2157260183 @default.
• W4286632012 cites W2301095666 @default.
• W4286632012 cites W2740285126 @default.
• W4286632012 cites W2915977242 @default.
• W4286632012 cites W2952307023 @default.
• W4286632012 cites W2952757700 @default.
• W4286632012 cites W2963135511 @default.
• W4286632012 cites W2963430224 @default.
• W4286632012 cites W3094030321 @default.
• W4286632012 cites W3103817024 @default.
• W4286632012 doi "https://doi.org/10.1162/coli_a_00450" @default.
• W4286632012 hasPublicationYear "2022" @default.
• W4286632012 type Work @default.
• W4286632012 citedByCount "1" @default.
• W4286632012 countsByYear W42866320122023 @default.
• W4286632012 crossrefType "journal-article" @default.
• W4286632012 hasAuthorship W4286632012A5001572213 @default.
• W4286632012 hasAuthorship W4286632012A5030452648 @default.
• W4286632012 hasAuthorship W4286632012A5052998031 @default.
• W4286632012 hasAuthorship W4286632012A5077063699 @default.
• W4286632012 hasBestOaLocation W42866320121 @default.
• W4286632012 hasConcept C111030470 @default.
• W4286632012 hasConcept C154945302 @default.
• W4286632012 hasConcept C164883195 @default.
• W4286632012 hasConcept C186644900 @default.
• W4286632012 hasConcept C19768560 @default.
• W4286632012 hasConcept C204321447 @default.
• W4286632012 hasConcept C41008148 @default.
• W4286632012 hasConceptScore W4286632012C111030470 @default.
• W4286632012 hasConceptScore W4286632012C154945302 @default.
• W4286632012 hasConceptScore W4286632012C164883195 @default.
• W4286632012 hasConceptScore W4286632012C186644900 @default.
• W4286632012 hasConceptScore W4286632012C19768560 @default.
• W4286632012 hasConceptScore W4286632012C204321447 @default.
• W4286632012 hasConceptScore W4286632012C41008148 @default.
• W4286632012 hasIssue "4" @default.
• W4286632012 hasLocation W42866320121 @default.
• W4286632012 hasLocation W42866320122 @default.
• W4286632012 hasOpenAccess W4286632012 @default.
• W4286632012 hasPrimaryLocation W42866320121 @default.
• W4286632012 hasRelatedWork W2020540721 @default.
• W4286632012 hasRelatedWork W2101720163 @default.
• W4286632012 hasRelatedWork W2242177611 @default.
• W4286632012 hasRelatedWork W2251868338 @default.
• W4286632012 hasRelatedWork W2351267244 @default.
• W4286632012 hasRelatedWork W2381769141 @default.
• W4286632012 hasRelatedWork W2498686385 @default.
• W4286632012 hasRelatedWork W2888625260 @default.
• W4286632012 hasRelatedWork W65617392 @default.
• W4286632012 hasRelatedWork W83176488 @default.
• W4286632012 hasVolume "48" @default.
• W4286632012 isParatext "false" @default.
• W4286632012 isRetracted "false" @default.
• W4286632012 workType "article" @default.