Matches in SemOpenAlex for { <https://semopenalex.org/work/W3210220160> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W3210220160 endingPage "116064" @default.
- W3210220160 startingPage "116064" @default.
- W3210220160 abstract "Summaries are expected to relay the most amount of information in the least amount of words. Summary assessment tools such as Rouge, METEOR, and BLEU fail to explain the factual consistency of summaries with source documents and also disregard the synonymy between expressions. Information-coverage is a measure of the amount of important information retained in the summary. We propose ICE and ICE-T metrics that employ pre-trained word embeddings, Part-Of-Speech or POS-based keyword extraction, cosine-similarity, source length, and target length, for gauging the information-coverage in automatically shaped abstracts. We propose five POS-based keyword sampling techniques (NN, NN-VB, NN-JJ, NN-VB-JJ, and NN-VB-JJ-CD) for efficient retrieval of predominant information from the source text. Experiments show that: (1) ICE very strongly correlates with human-judgments w.r.t NN-VB-JJ-CD sampling (Pearson (0.989), Spearman rank (0.987) and Kendall rank (0.919)); and NN-VB-JJ sampling (Pearson (0.978), Spearman rank (0.979) and Kendall rank (0.899)) (2) ICE-T strongly correlates with human-judgments w.r.t NN-VB-JJ-CD sampling (Pearson (0.904), Spearman rank (0.846) and Kendall rank (0.702)); and NN-VB-JJ sampling (Pearson (0.877) and Spearman rank (0.832)). ICE and ICE-T are reliable information-coverage estimation tools as they equate eminently with human evaluations compared to Rouge (Rouge-1, Rouge-2, Rouge-L, Rouge-WE), and BLEU." @default.
- W3210220160 created "2021-11-08" @default.
- W3210220160 creator A5040171024 @default.
- W3210220160 creator A5055575612 @default.
- W3210220160 creator A5060052491 @default.
- W3210220160 date "2022-03-01" @default.
- W3210220160 modified "2023-09-27" @default.
- W3210220160 title "ICE: Information coverage estimate for automatic evaluation abstractive summaries" @default.
- W3210220160 cites W1826672328 @default.
- W3210220160 cites W1970842529 @default.
- W3210220160 cites W1983018376 @default.
- W3210220160 cites W2004450254 @default.
- W3210220160 cites W2007407316 @default.
- W3210220160 cites W2012179416 @default.
- W3210220160 cites W2026498605 @default.
- W3210220160 cites W2044070623 @default.
- W3210220160 cites W2059126410 @default.
- W3210220160 cites W2064418625 @default.
- W3210220160 cites W2101105183 @default.
- W3210220160 cites W2141848945 @default.
- W3210220160 cites W2147192413 @default.
- W3210220160 cites W2250539671 @default.
- W3210220160 cites W2522025693 @default.
- W3210220160 cites W2562609730 @default.
- W3210220160 cites W2755111576 @default.
- W3210220160 cites W2805583911 @default.
- W3210220160 cites W2883616768 @default.
- W3210220160 cites W2890013547 @default.
- W3210220160 cites W2904790185 @default.
- W3210220160 cites W2949611393 @default.
- W3210220160 cites W2962965405 @default.
- W3210220160 cites W2962985882 @default.
- W3210220160 cites W2963419157 @default.
- W3210220160 cites W2963850840 @default.
- W3210220160 cites W2963926728 @default.
- W3210220160 cites W2964813902 @default.
- W3210220160 cites W3138773240 @default.
- W3210220160 doi "https://doi.org/10.1016/j.eswa.2021.116064" @default.
- W3210220160 hasPublicationYear "2022" @default.
- W3210220160 type Work @default.
- W3210220160 sameAs 3210220160 @default.
- W3210220160 citedByCount "0" @default.
- W3210220160 crossrefType "journal-article" @default.
- W3210220160 hasAuthorship W3210220160A5040171024 @default.
- W3210220160 hasAuthorship W3210220160A5055575612 @default.
- W3210220160 hasAuthorship W3210220160A5060052491 @default.
- W3210220160 hasConcept C124101348 @default.
- W3210220160 hasConcept C154945302 @default.
- W3210220160 hasConcept C204321447 @default.
- W3210220160 hasConcept C23123220 @default.
- W3210220160 hasConcept C41008148 @default.
- W3210220160 hasConceptScore W3210220160C124101348 @default.
- W3210220160 hasConceptScore W3210220160C154945302 @default.
- W3210220160 hasConceptScore W3210220160C204321447 @default.
- W3210220160 hasConceptScore W3210220160C23123220 @default.
- W3210220160 hasConceptScore W3210220160C41008148 @default.
- W3210220160 hasLocation W32102201601 @default.
- W3210220160 hasOpenAccess W3210220160 @default.
- W3210220160 hasPrimaryLocation W32102201601 @default.
- W3210220160 hasRelatedWork W2119135658 @default.
- W3210220160 hasRelatedWork W2119214692 @default.
- W3210220160 hasRelatedWork W2357241418 @default.
- W3210220160 hasRelatedWork W2366644548 @default.
- W3210220160 hasRelatedWork W2368651715 @default.
- W3210220160 hasRelatedWork W2376314740 @default.
- W3210220160 hasRelatedWork W2384888906 @default.
- W3210220160 hasRelatedWork W2611614995 @default.
- W3210220160 hasRelatedWork W2789919619 @default.
- W3210220160 hasRelatedWork W3107474891 @default.
- W3210220160 hasVolume "189" @default.
- W3210220160 isParatext "false" @default.
- W3210220160 isRetracted "false" @default.
- W3210220160 magId "3210220160" @default.
- W3210220160 workType "article" @default.