FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2597682004> ?p ?o ?g. }

• W2597682004 abstract "Semantic event extraction has been applied in many natural language processing(NLP) tasks like summarization and text mining. However, not many researches havebeen carried out to automate multiple event extraction and representation. This hasresulted in the limitation of semantically annotated corpus to PropBank, FrameNet andVerbNet for event extraction. These corpus collections can be expanded by havingother semantically annotated event corpus added into it. Many event extraction modelslike EVENT, SEM and LODE have been proposed but these researches stopped at thecollection of events. Extending research beyond this collection of event to investigatethe interpretation and abstraction of event-based knowledge has not been exploitedmuch. Furthermore, there is a lack of research for key event indexing to identify therelative importance of multiple events in a complex sentence. This indexing canaugment successful extracted event-based knowledge as weight.The main objective of this research is to propose a framework that can automatethe extraction of semantically relevant key events based on thematic hierarchy anddiscourse-level dependencies to determine their relationships and relative importance.This has led to the exploration and formulation of designs to: i) capture and annotatemultiple semantic events in a semantic representation format. ii) define a linguisticallyinjected model (Linguistic Window Model) to interpret multiple events in a complexsentence. iii) define new weights for graph-based text (based on Linguistic WindowModel) for key event indexing.This research has proposed a new method, EveSem, a NLP tools pipeline toautomate the extraction and annotation of semantic events. This tool has performedmarginally better than TIPSemB-1.0. EveSem is then extended to invent a LinguisticWindow Model which has a linguistic structure that is found to enhance the F1-scorewhen compared to ACE data for event extraction. The thematic hierarchy and discourse-level dependencies properties of the linguistic structure have been found togreatly improve the recall over ACE data for trigger identification as well. Based onthe thematic hierarchy, new weights are defined to construct weighted graph-based textwhich has shown to improve the indexing of relative importance of key event incomplex sentences.The results showed that the NLP tools pipeline has successfully extracted andrepresented multiple events in XML tags. The small collection of XML annotatedcorpus for semantic events can be added to the collection of event lexical databases.Furthermore, this approach is domain generic and is portable to be implemented inother languages provided the language has the available NLP tools. The LinguisticWindow Model is able to extract event with improve F1-score over ACE task. Thismodel has the advantage over bag of word (BOW) model for key event indexing sinceit takes into consideration the context of word co-occurrence and semantic associationbetween words based on the linguistic structure of the model. As a conclusion, theobjectives of this research have been successfully achieved. The research hasaddressed the gaps identified in this thesis by: (a) automatically generated a collectionof multiple semantic event using a generic approach through NLP tools as a pipeline,(b) identifying relative importance of key semantic events based on linguisticproperties of the sentence." @default.
• W2597682004 created "2017-04-07" @default.
• W2597682004 creator A5003182284 @default.
• W2597682004 date "2015-01-01" @default.
• W2597682004 modified "2023-09-23" @default.
• W2597682004 title "Semantic event extraction in unstructured text based on prominence and discourse-level dependencies" @default.
• W2597682004 hasPublicationYear "2015" @default.
• W2597682004 type Work @default.
• W2597682004 sameAs 2597682004 @default.
• W2597682004 citedByCount "0" @default.
• W2597682004 crossrefType "dissertation" @default.
• W2597682004 hasAuthorship W2597682004A5003182284 @default.
• W2597682004 hasConcept C121332964 @default.
• W2597682004 hasConcept C154945302 @default.
• W2597682004 hasConcept C170858558 @default.
• W2597682004 hasConcept C185754541 @default.
• W2597682004 hasConcept C186644900 @default.
• W2597682004 hasConcept C195807954 @default.
• W2597682004 hasConcept C204321447 @default.
• W2597682004 hasConcept C23123220 @default.
• W2597682004 hasConcept C26517878 @default.
• W2597682004 hasConcept C2776321320 @default.
• W2597682004 hasConcept C2777530160 @default.
• W2597682004 hasConcept C2779662365 @default.
• W2597682004 hasConcept C38652104 @default.
• W2597682004 hasConcept C41008148 @default.
• W2597682004 hasConcept C62520636 @default.
• W2597682004 hasConcept C75165309 @default.
• W2597682004 hasConceptScore W2597682004C121332964 @default.
• W2597682004 hasConceptScore W2597682004C154945302 @default.
• W2597682004 hasConceptScore W2597682004C170858558 @default.
• W2597682004 hasConceptScore W2597682004C185754541 @default.
• W2597682004 hasConceptScore W2597682004C186644900 @default.
• W2597682004 hasConceptScore W2597682004C195807954 @default.
• W2597682004 hasConceptScore W2597682004C204321447 @default.
• W2597682004 hasConceptScore W2597682004C23123220 @default.
• W2597682004 hasConceptScore W2597682004C26517878 @default.
• W2597682004 hasConceptScore W2597682004C2776321320 @default.
• W2597682004 hasConceptScore W2597682004C2777530160 @default.
• W2597682004 hasConceptScore W2597682004C2779662365 @default.
• W2597682004 hasConceptScore W2597682004C38652104 @default.
• W2597682004 hasConceptScore W2597682004C41008148 @default.
• W2597682004 hasConceptScore W2597682004C62520636 @default.
• W2597682004 hasConceptScore W2597682004C75165309 @default.
• W2597682004 hasLocation W25976820041 @default.
• W2597682004 hasOpenAccess W2597682004 @default.
• W2597682004 hasPrimaryLocation W25976820041 @default.
• W2597682004 hasRelatedWork W14498012 @default.
• W2597682004 hasRelatedWork W150863218 @default.
• W2597682004 hasRelatedWork W172136173 @default.
• W2597682004 hasRelatedWork W2019701229 @default.
• W2597682004 hasRelatedWork W2020487656 @default.
• W2597682004 hasRelatedWork W2055685316 @default.
• W2597682004 hasRelatedWork W2099724779 @default.
• W2597682004 hasRelatedWork W2133554837 @default.
• W2597682004 hasRelatedWork W2293457016 @default.
• W2597682004 hasRelatedWork W2309491054 @default.
• W2597682004 hasRelatedWork W2396252828 @default.
• W2597682004 hasRelatedWork W2407026183 @default.
• W2597682004 hasRelatedWork W2511641841 @default.
• W2597682004 hasRelatedWork W2517141889 @default.
• W2597682004 hasRelatedWork W2560182576 @default.
• W2597682004 hasRelatedWork W2577673625 @default.
• W2597682004 hasRelatedWork W2581702097 @default.
• W2597682004 hasRelatedWork W2919426963 @default.
• W2597682004 hasRelatedWork W3166716275 @default.
• W2597682004 hasRelatedWork W897062481 @default.
• W2597682004 isParatext "false" @default.
• W2597682004 isRetracted "false" @default.
• W2597682004 magId "2597682004" @default.
• W2597682004 workType "dissertation" @default.