Matches in SemOpenAlex for { <https://semopenalex.org/work/W1987486061> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W1987486061 endingPage "224" @default.
- W1987486061 startingPage "193" @default.
- W1987486061 abstract "The availability of large scale data sets of manually annotated predicate-argument structures has recently favored the use of machine learning approaches to the design of automated semantic role labeling (SRL) systems. The main research in this area relates to the design choices for feature representation and for effective decompositions of the task in different learning models. Regarding the former choice, structural properties of full syntactic parses are largely employed as they represent ways to encode different principles suggested by the linking theory between syntax and semantics. The latter choice relates to several learning schemes over global views of the parses. For example, re-ranking stages operating over alternative predicate-argument sequences of the same sentence have shown to be very effective. In this article, we propose several kernel functions to model parse tree properties in kernel-based machines, for example, perceptrons or support vector machines. In particular, we define different kinds of tree kernels as general approaches to feature engineering in SRL. Moreover, we extensively experiment with such kernels to investigate their contribution to individual stages of an SRL architecture both in isolation and in combination with other traditional manually coded features. The results for boundary recognition, classification, and re-ranking stages provide systematic evidence about the significant impact of tree kernels on the overall accuracy, especially when the amount of training data is small. As a conclusive result, tree kernels allow for a general and easily portable feature engineering method which is applicable to a large family of natural language processing tasks." @default.
- W1987486061 created "2016-06-24" @default.
- W1987486061 creator A5019835473 @default.
- W1987486061 creator A5056376686 @default.
- W1987486061 creator A5083592532 @default.
- W1987486061 date "2008-06-01" @default.
- W1987486061 modified "2023-09-26" @default.
- W1987486061 title "Tree Kernels for Semantic Role Labeling" @default.
- W1987486061 cites W1981082061 @default.
- W1987486061 cites W2138043057 @default.
- W1987486061 cites W2151170651 @default.
- W1987486061 cites W2158847908 @default.
- W1987486061 doi "https://doi.org/10.1162/coli.2008.34.2.193" @default.
- W1987486061 hasPublicationYear "2008" @default.
- W1987486061 type Work @default.
- W1987486061 sameAs 1987486061 @default.
- W1987486061 citedByCount "151" @default.
- W1987486061 countsByYear W19874860612012 @default.
- W1987486061 countsByYear W19874860612013 @default.
- W1987486061 countsByYear W19874860612014 @default.
- W1987486061 countsByYear W19874860612015 @default.
- W1987486061 countsByYear W19874860612016 @default.
- W1987486061 countsByYear W19874860612017 @default.
- W1987486061 countsByYear W19874860612018 @default.
- W1987486061 countsByYear W19874860612019 @default.
- W1987486061 countsByYear W19874860612020 @default.
- W1987486061 countsByYear W19874860612021 @default.
- W1987486061 crossrefType "journal-article" @default.
- W1987486061 hasAuthorship W1987486061A5019835473 @default.
- W1987486061 hasAuthorship W1987486061A5056376686 @default.
- W1987486061 hasAuthorship W1987486061A5083592532 @default.
- W1987486061 hasBestOaLocation W19874860611 @default.
- W1987486061 hasConcept C113174947 @default.
- W1987486061 hasConcept C119857082 @default.
- W1987486061 hasConcept C122280245 @default.
- W1987486061 hasConcept C12267149 @default.
- W1987486061 hasConcept C134306372 @default.
- W1987486061 hasConcept C140146324 @default.
- W1987486061 hasConcept C140417398 @default.
- W1987486061 hasConcept C154945302 @default.
- W1987486061 hasConcept C199360897 @default.
- W1987486061 hasConcept C204321447 @default.
- W1987486061 hasConcept C2777530160 @default.
- W1987486061 hasConcept C33923547 @default.
- W1987486061 hasConcept C41008148 @default.
- W1987486061 hasConcept C60048249 @default.
- W1987486061 hasConcept C67277372 @default.
- W1987486061 hasConcept C75866337 @default.
- W1987486061 hasConcept C95623464 @default.
- W1987486061 hasConceptScore W1987486061C113174947 @default.
- W1987486061 hasConceptScore W1987486061C119857082 @default.
- W1987486061 hasConceptScore W1987486061C122280245 @default.
- W1987486061 hasConceptScore W1987486061C12267149 @default.
- W1987486061 hasConceptScore W1987486061C134306372 @default.
- W1987486061 hasConceptScore W1987486061C140146324 @default.
- W1987486061 hasConceptScore W1987486061C140417398 @default.
- W1987486061 hasConceptScore W1987486061C154945302 @default.
- W1987486061 hasConceptScore W1987486061C199360897 @default.
- W1987486061 hasConceptScore W1987486061C204321447 @default.
- W1987486061 hasConceptScore W1987486061C2777530160 @default.
- W1987486061 hasConceptScore W1987486061C33923547 @default.
- W1987486061 hasConceptScore W1987486061C41008148 @default.
- W1987486061 hasConceptScore W1987486061C60048249 @default.
- W1987486061 hasConceptScore W1987486061C67277372 @default.
- W1987486061 hasConceptScore W1987486061C75866337 @default.
- W1987486061 hasConceptScore W1987486061C95623464 @default.
- W1987486061 hasIssue "2" @default.
- W1987486061 hasLocation W19874860611 @default.
- W1987486061 hasLocation W19874860612 @default.
- W1987486061 hasLocation W19874860613 @default.
- W1987486061 hasOpenAccess W1987486061 @default.
- W1987486061 hasPrimaryLocation W19874860611 @default.
- W1987486061 hasRelatedWork W129174880 @default.
- W1987486061 hasRelatedWork W2010456335 @default.
- W1987486061 hasRelatedWork W2011392257 @default.
- W1987486061 hasRelatedWork W2084774044 @default.
- W1987486061 hasRelatedWork W2349991099 @default.
- W1987486061 hasRelatedWork W2882669297 @default.
- W1987486061 hasRelatedWork W2887717948 @default.
- W1987486061 hasRelatedWork W2890446476 @default.
- W1987486061 hasRelatedWork W3186232876 @default.
- W1987486061 hasRelatedWork W4288089236 @default.
- W1987486061 hasVolume "34" @default.
- W1987486061 isParatext "false" @default.
- W1987486061 isRetracted "false" @default.
- W1987486061 magId "1987486061" @default.
- W1987486061 workType "article" @default.