Matches in SemOpenAlex for { <https://semopenalex.org/work/W3103025252> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W3103025252 abstract "Since the amount of information on the internet is growing rapidly, it is not easy for a user to find relevant information for his/her query. To tackle this issue, much attention has been paid to Automatic Document Summarization. The key point in any successful document summarizer is a good document representation. The traditional approaches based on word overlapping mostly fail to produce that kind of representation. Word embedding, distributed representation of words, has shown an excellent performance that allows words to match on semantic level. Naively concatenating word embeddings makes the common word dominant which in turn diminish the representation quality. In this paper, we employ word embeddings to improve the weighting schemes for calculating the input matrix of Latent Semantic Analysis method. Two embedding-based weighting schemes are proposed and then combined to calculate the values of this matrix. The new weighting schemes are modified versions of the augment weight and the entropy frequency. The new schemes combine the strength of the traditional weighting schemes and word embedding. The proposed approach is experimentally evaluated on three well-known English datasets, DUC 2002, DUC 2004 and Multilingual 2015 Single-document Summarization for English. The proposed model performs comprehensively better compared to the state-of-the-art methods, by at least 1% ROUGE points, leading to a conclusion that it provides a better document representation and a better document summary as a result." @default.
- W3103025252 created "2020-11-23" @default.
- W3103025252 date "2019-01-31" @default.
- W3103025252 modified "2023-10-14" @default.
- W3103025252 title "Latent Semantic Analysis Approach for Document Summarization Based on Word Embeddings" @default.
- W3103025252 cites W1532325895 @default.
- W3103025252 cites W1986154307 @default.
- W3103025252 cites W2028742638 @default.
- W3103025252 cites W2110480283 @default.
- W3103025252 cites W2131876387 @default.
- W3103025252 cites W2250361277 @default.
- W3103025252 cites W2250539671 @default.
- W3103025252 cites W2251683517 @default.
- W3103025252 cites W2307381258 @default.
- W3103025252 cites W2328886022 @default.
- W3103025252 cites W2329305226 @default.
- W3103025252 cites W2530979053 @default.
- W3103025252 cites W2560654344 @default.
- W3103025252 cites W2566220624 @default.
- W3103025252 cites W2574535369 @default.
- W3103025252 cites W2612675303 @default.
- W3103025252 cites W2740656274 @default.
- W3103025252 cites W2800965800 @default.
- W3103025252 cites W2950577311 @default.
- W3103025252 cites W2952913664 @default.
- W3103025252 cites W2963499246 @default.
- W3103025252 cites W912777836 @default.
- W3103025252 cites W2612753051 @default.
- W3103025252 doi "https://doi.org/10.3837/tiis.2019.01.015" @default.
- W3103025252 hasPublicationYear "2019" @default.
- W3103025252 type Work @default.
- W3103025252 sameAs 3103025252 @default.
- W3103025252 citedByCount "2" @default.
- W3103025252 countsByYear W31030252522019 @default.
- W3103025252 countsByYear W31030252522023 @default.
- W3103025252 crossrefType "journal-article" @default.
- W3103025252 hasBestOaLocation W31030252521 @default.
- W3103025252 hasConcept C126838900 @default.
- W3103025252 hasConcept C138885662 @default.
- W3103025252 hasConcept C154945302 @default.
- W3103025252 hasConcept C170133592 @default.
- W3103025252 hasConcept C170858558 @default.
- W3103025252 hasConcept C17744445 @default.
- W3103025252 hasConcept C183115368 @default.
- W3103025252 hasConcept C184337299 @default.
- W3103025252 hasConcept C199360897 @default.
- W3103025252 hasConcept C199539241 @default.
- W3103025252 hasConcept C204321447 @default.
- W3103025252 hasConcept C23123220 @default.
- W3103025252 hasConcept C2776359362 @default.
- W3103025252 hasConcept C2777462759 @default.
- W3103025252 hasConcept C41008148 @default.
- W3103025252 hasConcept C41608201 @default.
- W3103025252 hasConcept C41895202 @default.
- W3103025252 hasConcept C71924100 @default.
- W3103025252 hasConcept C90805587 @default.
- W3103025252 hasConcept C94625758 @default.
- W3103025252 hasConceptScore W3103025252C126838900 @default.
- W3103025252 hasConceptScore W3103025252C138885662 @default.
- W3103025252 hasConceptScore W3103025252C154945302 @default.
- W3103025252 hasConceptScore W3103025252C170133592 @default.
- W3103025252 hasConceptScore W3103025252C170858558 @default.
- W3103025252 hasConceptScore W3103025252C17744445 @default.
- W3103025252 hasConceptScore W3103025252C183115368 @default.
- W3103025252 hasConceptScore W3103025252C184337299 @default.
- W3103025252 hasConceptScore W3103025252C199360897 @default.
- W3103025252 hasConceptScore W3103025252C199539241 @default.
- W3103025252 hasConceptScore W3103025252C204321447 @default.
- W3103025252 hasConceptScore W3103025252C23123220 @default.
- W3103025252 hasConceptScore W3103025252C2776359362 @default.
- W3103025252 hasConceptScore W3103025252C2777462759 @default.
- W3103025252 hasConceptScore W3103025252C41008148 @default.
- W3103025252 hasConceptScore W3103025252C41608201 @default.
- W3103025252 hasConceptScore W3103025252C41895202 @default.
- W3103025252 hasConceptScore W3103025252C71924100 @default.
- W3103025252 hasConceptScore W3103025252C90805587 @default.
- W3103025252 hasConceptScore W3103025252C94625758 @default.
- W3103025252 hasLocation W31030252521 @default.
- W3103025252 hasLocation W31030252522 @default.
- W3103025252 hasOpenAccess W3103025252 @default.
- W3103025252 hasPrimaryLocation W31030252521 @default.
- W3103025252 hasRelatedWork W1230873221 @default.
- W3103025252 hasRelatedWork W2760463480 @default.
- W3103025252 hasRelatedWork W2790133820 @default.
- W3103025252 hasRelatedWork W2899016443 @default.
- W3103025252 hasRelatedWork W2953316075 @default.
- W3103025252 hasRelatedWork W2953413383 @default.
- W3103025252 hasRelatedWork W2996012216 @default.
- W3103025252 hasRelatedWork W3103025252 @default.
- W3103025252 hasRelatedWork W4205618730 @default.
- W3103025252 hasRelatedWork W4246455502 @default.
- W3103025252 isParatext "false" @default.
- W3103025252 isRetracted "false" @default.
- W3103025252 magId "3103025252" @default.
- W3103025252 workType "article" @default.