Matches in SemOpenAlex for { <https://semopenalex.org/work/W2895975470> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W2895975470 abstract "In this paper, we show that by using a relatively simple neural network architecture and including edge (i.e., nonsensical) cases into a dataset we can more reliably identify factual claims than predecessor SVM models. Doping the dataset with these nonsensical example results in a more robust model overall that is resistant to being tricked into classifying sentences into a certain category based on easily met criteria. Furthermore, we show that the use of multiple word-embeddings makes little difference to the overall accuracy of the model, but particular embeddings perform differently on text that contains digits (i.e., 0-9) which can be leveraged by using multiple models to come to a conclusion on the score for a particular piece of text. Our results also show, that for our particular dataset trying to differentiate sentences into more than two categories might hurt the overall accuracy of the models, or at least not provide any substantial benefits compared to the binary classification scenario." @default.
- W2895975470 created "2018-10-26" @default.
- W2895975470 creator A5068796293 @default.
- W2895975470 creator A5084878734 @default.
- W2895975470 date "2018-07-01" @default.
- W2895975470 modified "2023-09-26" @default.
- W2895975470 title "An Empirical Study on Identifying Sentences with Salient Factual Statements" @default.
- W2895975470 cites W1503398984 @default.
- W2895975470 cites W1614298861 @default.
- W2895975470 cites W1832693441 @default.
- W2895975470 cites W2015462142 @default.
- W2895975470 cites W2153579005 @default.
- W2895975470 cites W2250539671 @default.
- W2895975470 cites W2251771443 @default.
- W2895975470 cites W2251803266 @default.
- W2895975470 cites W2296706733 @default.
- W2895975470 cites W2493916176 @default.
- W2895975470 cites W2612724701 @default.
- W2895975470 cites W2616517342 @default.
- W2895975470 cites W2751368487 @default.
- W2895975470 cites W2963044711 @default.
- W2895975470 cites W2963296402 @default.
- W2895975470 cites W2963956670 @default.
- W2895975470 cites W2964090065 @default.
- W2895975470 cites W3098090436 @default.
- W2895975470 cites W581956982 @default.
- W2895975470 doi "https://doi.org/10.1109/ijcnn.2018.8489601" @default.
- W2895975470 hasPublicationYear "2018" @default.
- W2895975470 type Work @default.
- W2895975470 sameAs 2895975470 @default.
- W2895975470 citedByCount "6" @default.
- W2895975470 countsByYear W28959754702019 @default.
- W2895975470 countsByYear W28959754702020 @default.
- W2895975470 crossrefType "proceedings-article" @default.
- W2895975470 hasAuthorship W2895975470A5068796293 @default.
- W2895975470 hasAuthorship W2895975470A5084878734 @default.
- W2895975470 hasConcept C111472728 @default.
- W2895975470 hasConcept C119857082 @default.
- W2895975470 hasConcept C12267149 @default.
- W2895975470 hasConcept C124101348 @default.
- W2895975470 hasConcept C138885662 @default.
- W2895975470 hasConcept C154945302 @default.
- W2895975470 hasConcept C162307627 @default.
- W2895975470 hasConcept C204321447 @default.
- W2895975470 hasConcept C2780586882 @default.
- W2895975470 hasConcept C2780719617 @default.
- W2895975470 hasConcept C33923547 @default.
- W2895975470 hasConcept C41008148 @default.
- W2895975470 hasConcept C41895202 @default.
- W2895975470 hasConcept C48372109 @default.
- W2895975470 hasConcept C50644808 @default.
- W2895975470 hasConcept C66905080 @default.
- W2895975470 hasConcept C90805587 @default.
- W2895975470 hasConcept C94375191 @default.
- W2895975470 hasConceptScore W2895975470C111472728 @default.
- W2895975470 hasConceptScore W2895975470C119857082 @default.
- W2895975470 hasConceptScore W2895975470C12267149 @default.
- W2895975470 hasConceptScore W2895975470C124101348 @default.
- W2895975470 hasConceptScore W2895975470C138885662 @default.
- W2895975470 hasConceptScore W2895975470C154945302 @default.
- W2895975470 hasConceptScore W2895975470C162307627 @default.
- W2895975470 hasConceptScore W2895975470C204321447 @default.
- W2895975470 hasConceptScore W2895975470C2780586882 @default.
- W2895975470 hasConceptScore W2895975470C2780719617 @default.
- W2895975470 hasConceptScore W2895975470C33923547 @default.
- W2895975470 hasConceptScore W2895975470C41008148 @default.
- W2895975470 hasConceptScore W2895975470C41895202 @default.
- W2895975470 hasConceptScore W2895975470C48372109 @default.
- W2895975470 hasConceptScore W2895975470C50644808 @default.
- W2895975470 hasConceptScore W2895975470C66905080 @default.
- W2895975470 hasConceptScore W2895975470C90805587 @default.
- W2895975470 hasConceptScore W2895975470C94375191 @default.
- W2895975470 hasLocation W28959754701 @default.
- W2895975470 hasOpenAccess W2895975470 @default.
- W2895975470 hasPrimaryLocation W28959754701 @default.
- W2895975470 hasRelatedWork W2101819884 @default.
- W2895975470 hasRelatedWork W2937631562 @default.
- W2895975470 hasRelatedWork W3004897296 @default.
- W2895975470 hasRelatedWork W3107474891 @default.
- W2895975470 hasRelatedWork W3136979370 @default.
- W2895975470 hasRelatedWork W3194539120 @default.
- W2895975470 hasRelatedWork W4205958290 @default.
- W2895975470 hasRelatedWork W4285106639 @default.
- W2895975470 hasRelatedWork W4361795583 @default.
- W2895975470 hasRelatedWork W4362499384 @default.
- W2895975470 isParatext "false" @default.
- W2895975470 isRetracted "false" @default.
- W2895975470 magId "2895975470" @default.
- W2895975470 workType "article" @default.