Matches in SemOpenAlex for { <https://semopenalex.org/work/W2896904757> ?p ?o ?g. }
- W2896904757 abstract "Semantic analysis of text corpora is of broad utility, including for data from conversations, on-line chats, brainstorming sessions, comments on blogs, etc. – all of which are potentially interesting sources of information and ideas. In the present paper, we look at data from a large group brainstorming experiment that generated thousands of mostly brief statements. The ultimate goal is to detect which statements are semantically atypical within the overall corpus. In contexts such as spam detection or detection of on-line intrusions, autoencoders have been used successfully to separate typical from atypical data, and we consider this approach in the present paper. Texts are embedded in a semantic space obtained through topic analysis, and an autoencoder network is used to reconstruct each embedded text. The results show that, while difficulty of reconstruction is related to quantitative measures of atypicality in the embedding vector space, it is not well correlated with novelty assignments made by a human rater. However, this is not the case when the data is first clustered in the embedding space: The reconstruction error for each data cluster indicates that some clusters represent more novel data than others, and that the inverse size of the cluster and the mean reconstruction error of the texts in the cluster capture this well. In particular, autoencoders that enforce dimensionality reduction improve discrimination. The results also show that, in the reconstruction process, the autoencoder implicitly discovers the same clusters in the data that are discovered explicitly by an optimized k-means approach." @default.
- W2896904757 created "2018-10-26" @default.
- W2896904757 creator A5005741308 @default.
- W2896904757 creator A5017660782 @default.
- W2896904757 creator A5020533881 @default.
- W2896904757 creator A5033722814 @default.
- W2896904757 creator A5036905489 @default.
- W2896904757 creator A5051655206 @default.
- W2896904757 creator A5076484761 @default.
- W2896904757 date "2018-07-01" @default.
- W2896904757 modified "2023-09-26" @default.
- W2896904757 title "Using Semantic Clustering And Autoencoders For Detecting Novelty In Corpora Of Short Texts" @default.
- W2896904757 cites W1490430947 @default.
- W2896904757 cites W1533861849 @default.
- W2896904757 cites W1536258620 @default.
- W2896904757 cites W1876967670 @default.
- W2896904757 cites W1972262362 @default.
- W2896904757 cites W1979625382 @default.
- W2896904757 cites W1980974094 @default.
- W2896904757 cites W1987971958 @default.
- W2896904757 cites W1990277796 @default.
- W2896904757 cites W2027634772 @default.
- W2896904757 cites W2036763306 @default.
- W2896904757 cites W2053155195 @default.
- W2896904757 cites W2072644219 @default.
- W2896904757 cites W2086438570 @default.
- W2896904757 cites W2095038093 @default.
- W2896904757 cites W2106154564 @default.
- W2896904757 cites W2124208340 @default.
- W2896904757 cites W2125656037 @default.
- W2896904757 cites W2130764762 @default.
- W2896904757 cites W2144343387 @default.
- W2896904757 cites W2168068255 @default.
- W2896904757 cites W2482371029 @default.
- W2896904757 cites W2742557696 @default.
- W2896904757 cites W2913932916 @default.
- W2896904757 cites W2938829626 @default.
- W2896904757 cites W2964261549 @default.
- W2896904757 cites W2160631673 @default.
- W2896904757 cites W3021775139 @default.
- W2896904757 doi "https://doi.org/10.1109/ijcnn.2018.8489431" @default.
- W2896904757 hasPublicationYear "2018" @default.
- W2896904757 type Work @default.
- W2896904757 sameAs 2896904757 @default.
- W2896904757 citedByCount "4" @default.
- W2896904757 countsByYear W28969047572019 @default.
- W2896904757 countsByYear W28969047572020 @default.
- W2896904757 countsByYear W28969047572021 @default.
- W2896904757 crossrefType "proceedings-article" @default.
- W2896904757 hasAuthorship W2896904757A5005741308 @default.
- W2896904757 hasAuthorship W2896904757A5017660782 @default.
- W2896904757 hasAuthorship W2896904757A5020533881 @default.
- W2896904757 hasAuthorship W2896904757A5033722814 @default.
- W2896904757 hasAuthorship W2896904757A5036905489 @default.
- W2896904757 hasAuthorship W2896904757A5051655206 @default.
- W2896904757 hasAuthorship W2896904757A5076484761 @default.
- W2896904757 hasConcept C101738243 @default.
- W2896904757 hasConcept C108583219 @default.
- W2896904757 hasConcept C111919701 @default.
- W2896904757 hasConcept C119857082 @default.
- W2896904757 hasConcept C138885662 @default.
- W2896904757 hasConcept C153180895 @default.
- W2896904757 hasConcept C154945302 @default.
- W2896904757 hasConcept C204321447 @default.
- W2896904757 hasConcept C27206212 @default.
- W2896904757 hasConcept C2778572836 @default.
- W2896904757 hasConcept C2778738651 @default.
- W2896904757 hasConcept C41008148 @default.
- W2896904757 hasConcept C41608201 @default.
- W2896904757 hasConcept C70518039 @default.
- W2896904757 hasConcept C73555534 @default.
- W2896904757 hasConceptScore W2896904757C101738243 @default.
- W2896904757 hasConceptScore W2896904757C108583219 @default.
- W2896904757 hasConceptScore W2896904757C111919701 @default.
- W2896904757 hasConceptScore W2896904757C119857082 @default.
- W2896904757 hasConceptScore W2896904757C138885662 @default.
- W2896904757 hasConceptScore W2896904757C153180895 @default.
- W2896904757 hasConceptScore W2896904757C154945302 @default.
- W2896904757 hasConceptScore W2896904757C204321447 @default.
- W2896904757 hasConceptScore W2896904757C27206212 @default.
- W2896904757 hasConceptScore W2896904757C2778572836 @default.
- W2896904757 hasConceptScore W2896904757C2778738651 @default.
- W2896904757 hasConceptScore W2896904757C41008148 @default.
- W2896904757 hasConceptScore W2896904757C41608201 @default.
- W2896904757 hasConceptScore W2896904757C70518039 @default.
- W2896904757 hasConceptScore W2896904757C73555534 @default.
- W2896904757 hasLocation W28969047571 @default.
- W2896904757 hasOpenAccess W2896904757 @default.
- W2896904757 hasPrimaryLocation W28969047571 @default.
- W2896904757 hasRelatedWork W2601105035 @default.
- W2896904757 hasRelatedWork W2772780115 @default.
- W2896904757 hasRelatedWork W2922841016 @default.
- W2896904757 hasRelatedWork W2963031333 @default.
- W2896904757 hasRelatedWork W2971734402 @default.
- W2896904757 hasRelatedWork W3005796368 @default.
- W2896904757 hasRelatedWork W3017161237 @default.
- W2896904757 hasRelatedWork W3178127657 @default.
- W2896904757 hasRelatedWork W4211210873 @default.
- W2896904757 hasRelatedWork W4214895820 @default.
- W2896904757 isParatext "false" @default.