Matches in SemOpenAlex for { <https://semopenalex.org/work/W2767609139> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W2767609139 abstract "Information Extraction by Text Segmentation (IETS) aims at segmenting text inputs to extract implicit data values contained in them.The state-of-art IETS approaches mainly rely on machine learning techniques, either supervised or unsupervised.However, while the supervised approaches require a large labelled training data, the performance of the unsupervised ones could be unstable on different data sets.To overcome their weaknesses, this paper introduces CNN-IETS, a novel unsupervised probabilistic approach that takes the advantages of pre-existing data and a Convolution Neural Network (CNN)-based probabilistic classification model. While using the CNN model can ease the burden of selecting high-quality features in associating text segments with attributes of a given domain, the pre-existing data as a domain knowledge base can provide training data with a comprehensive list of features for building the CNN model.Given an input text, we do initial segmentation (according to the occurrences of these words in the knowledge base) to generate text segments for CNN classification with probabilities. Then, based on the probabilistic CNN classification results, we work on finding the most probable labelling way to the whole input text.As a complementary, a bidirectional sequencing model learned on-demand from test data is finally deployed to do further adjustment to some problematic labelled segments.Our experimental study conducted on several real data collections shows that CNN-IETS improves the extraction quality of state-of-art approaches by more than 10%." @default.
- W2767609139 created "2017-11-17" @default.
- W2767609139 creator A5014867897 @default.
- W2767609139 creator A5032517198 @default.
- W2767609139 creator A5034285792 @default.
- W2767609139 creator A5065529268 @default.
- W2767609139 creator A5070439966 @default.
- W2767609139 creator A5073103596 @default.
- W2767609139 creator A5082789137 @default.
- W2767609139 date "2017-11-06" @default.
- W2767609139 modified "2023-10-17" @default.
- W2767609139 title "CNN-IETS" @default.
- W2767609139 cites W1794858913 @default.
- W2767609139 cites W1832693441 @default.
- W2767609139 cites W1976258225 @default.
- W2767609139 cites W1981791873 @default.
- W2767609139 cites W1992994083 @default.
- W2767609139 cites W2032584215 @default.
- W2767609139 cites W2093752301 @default.
- W2767609139 cites W2102153716 @default.
- W2767609139 cites W2108126629 @default.
- W2767609139 cites W2117130368 @default.
- W2767609139 cites W2124410446 @default.
- W2767609139 cites W2127395777 @default.
- W2767609139 cites W236085609 @default.
- W2767609139 cites W2964036454 @default.
- W2767609139 cites W3004248957 @default.
- W2767609139 cites W2099430417 @default.
- W2767609139 doi "https://doi.org/10.1145/3132847.3132962" @default.
- W2767609139 hasPublicationYear "2017" @default.
- W2767609139 type Work @default.
- W2767609139 sameAs 2767609139 @default.
- W2767609139 citedByCount "6" @default.
- W2767609139 countsByYear W27676091392018 @default.
- W2767609139 countsByYear W27676091392019 @default.
- W2767609139 countsByYear W27676091392020 @default.
- W2767609139 countsByYear W27676091392022 @default.
- W2767609139 crossrefType "proceedings-article" @default.
- W2767609139 hasAuthorship W2767609139A5014867897 @default.
- W2767609139 hasAuthorship W2767609139A5032517198 @default.
- W2767609139 hasAuthorship W2767609139A5034285792 @default.
- W2767609139 hasAuthorship W2767609139A5065529268 @default.
- W2767609139 hasAuthorship W2767609139A5070439966 @default.
- W2767609139 hasAuthorship W2767609139A5073103596 @default.
- W2767609139 hasAuthorship W2767609139A5082789137 @default.
- W2767609139 hasConcept C119857082 @default.
- W2767609139 hasConcept C124101348 @default.
- W2767609139 hasConcept C134306372 @default.
- W2767609139 hasConcept C153180895 @default.
- W2767609139 hasConcept C154945302 @default.
- W2767609139 hasConcept C207685749 @default.
- W2767609139 hasConcept C2776145971 @default.
- W2767609139 hasConcept C33923547 @default.
- W2767609139 hasConcept C36503486 @default.
- W2767609139 hasConcept C41008148 @default.
- W2767609139 hasConcept C45347329 @default.
- W2767609139 hasConcept C49937458 @default.
- W2767609139 hasConcept C50644808 @default.
- W2767609139 hasConcept C8038995 @default.
- W2767609139 hasConcept C81363708 @default.
- W2767609139 hasConcept C89600930 @default.
- W2767609139 hasConceptScore W2767609139C119857082 @default.
- W2767609139 hasConceptScore W2767609139C124101348 @default.
- W2767609139 hasConceptScore W2767609139C134306372 @default.
- W2767609139 hasConceptScore W2767609139C153180895 @default.
- W2767609139 hasConceptScore W2767609139C154945302 @default.
- W2767609139 hasConceptScore W2767609139C207685749 @default.
- W2767609139 hasConceptScore W2767609139C2776145971 @default.
- W2767609139 hasConceptScore W2767609139C33923547 @default.
- W2767609139 hasConceptScore W2767609139C36503486 @default.
- W2767609139 hasConceptScore W2767609139C41008148 @default.
- W2767609139 hasConceptScore W2767609139C45347329 @default.
- W2767609139 hasConceptScore W2767609139C49937458 @default.
- W2767609139 hasConceptScore W2767609139C50644808 @default.
- W2767609139 hasConceptScore W2767609139C8038995 @default.
- W2767609139 hasConceptScore W2767609139C81363708 @default.
- W2767609139 hasConceptScore W2767609139C89600930 @default.
- W2767609139 hasFunder F4320321001 @default.
- W2767609139 hasLocation W27676091391 @default.
- W2767609139 hasOpenAccess W2767609139 @default.
- W2767609139 hasPrimaryLocation W27676091391 @default.
- W2767609139 hasRelatedWork W2769435486 @default.
- W2767609139 hasRelatedWork W3093612317 @default.
- W2767609139 hasRelatedWork W3102253946 @default.
- W2767609139 hasRelatedWork W3196155444 @default.
- W2767609139 hasRelatedWork W3214651656 @default.
- W2767609139 hasRelatedWork W4200528772 @default.
- W2767609139 hasRelatedWork W4285201151 @default.
- W2767609139 hasRelatedWork W4287776258 @default.
- W2767609139 hasRelatedWork W4308191152 @default.
- W2767609139 hasRelatedWork W4312417841 @default.
- W2767609139 isParatext "false" @default.
- W2767609139 isRetracted "false" @default.
- W2767609139 magId "2767609139" @default.
- W2767609139 workType "article" @default.