Matches in SemOpenAlex for { <https://semopenalex.org/work/W4293146026> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W4293146026 endingPage "103744" @default.
- W4293146026 startingPage "103744" @default.
- W4293146026 abstract "Commonsense knowledge acquisition is one of the fundamental issues in realizing human-level AI. However, commonsense knowledge is difficult to obtain because it is a human consensus and rarely explicitly appears in texts or other data. In this paper, we focus on the automatic acquisition of a typical kind of implicit verb-oriented commonsense knowledge (e.g., “person eats food”), which is the concept-level knowledge of verb phrases. For this purpose, we propose a taxonomy-guided induction method to mine verb-oriented commonsense knowledge from verb phrases with the help of a probabilistic taxonomy. First, we design an entropy-based triplet filter to cope with noisy verb phrases. Then, we propose a joint model based on the minimum description length principle and a neural language model to generate verb-oriented commonsense knowledge. Besides, we introduce two strategies to accelerate the computation, including the simulated annealing-based approximate solution and the verb phrase clustering method. Finally, we conduct extensive experiments to prove that our solution is more effective than competitors in mining verb-oriented commonsense knowledge. We construct a commonsense knowledge base called VoCSK, containing 259 verbs and 18,406 verb-oriented commonsense knowledge. To verify the usefulness of VoCSK, we utilize the knowledge in this KB to improve the model performance on two downstream applications." @default.
- W4293146026 created "2022-08-27" @default.
- W4293146026 creator A5011544360 @default.
- W4293146026 creator A5030104017 @default.
- W4293146026 creator A5053557669 @default.
- W4293146026 creator A5055838753 @default.
- W4293146026 creator A5057931637 @default.
- W4293146026 creator A5075507821 @default.
- W4293146026 creator A5081537657 @default.
- W4293146026 creator A5090455375 @default.
- W4293146026 date "2022-09-01" @default.
- W4293146026 modified "2023-09-27" @default.
- W4293146026 title "VoCSK: Verb-oriented commonsense knowledge mining with taxonomy-guided induction" @default.
- W4293146026 cites W1539587635 @default.
- W4293146026 cites W1552847225 @default.
- W4293146026 cites W1975879668 @default.
- W4293146026 cites W2016089260 @default.
- W4293146026 cites W2024060531 @default.
- W4293146026 cites W2054658115 @default.
- W4293146026 cites W2080133951 @default.
- W4293146026 cites W2081580037 @default.
- W4293146026 cites W2088212442 @default.
- W4293146026 cites W2092552912 @default.
- W4293146026 cites W2099964107 @default.
- W4293146026 cites W2102098892 @default.
- W4293146026 cites W2107658650 @default.
- W4293146026 cites W2151170651 @default.
- W4293146026 cites W2158847908 @default.
- W4293146026 cites W2548036585 @default.
- W4293146026 cites W2792026792 @default.
- W4293146026 doi "https://doi.org/10.1016/j.artint.2022.103744" @default.
- W4293146026 hasPublicationYear "2022" @default.
- W4293146026 type Work @default.
- W4293146026 citedByCount "1" @default.
- W4293146026 countsByYear W42931460262023 @default.
- W4293146026 crossrefType "journal-article" @default.
- W4293146026 hasAuthorship W4293146026A5011544360 @default.
- W4293146026 hasAuthorship W4293146026A5030104017 @default.
- W4293146026 hasAuthorship W4293146026A5053557669 @default.
- W4293146026 hasAuthorship W4293146026A5055838753 @default.
- W4293146026 hasAuthorship W4293146026A5057931637 @default.
- W4293146026 hasAuthorship W4293146026A5075507821 @default.
- W4293146026 hasAuthorship W4293146026A5081537657 @default.
- W4293146026 hasAuthorship W4293146026A5090455375 @default.
- W4293146026 hasConcept C120567893 @default.
- W4293146026 hasConcept C154945302 @default.
- W4293146026 hasConcept C204321447 @default.
- W4293146026 hasConcept C2776397901 @default.
- W4293146026 hasConcept C30542707 @default.
- W4293146026 hasConcept C41008148 @default.
- W4293146026 hasConceptScore W4293146026C120567893 @default.
- W4293146026 hasConceptScore W4293146026C154945302 @default.
- W4293146026 hasConceptScore W4293146026C204321447 @default.
- W4293146026 hasConceptScore W4293146026C2776397901 @default.
- W4293146026 hasConceptScore W4293146026C30542707 @default.
- W4293146026 hasConceptScore W4293146026C41008148 @default.
- W4293146026 hasFunder F4320321885 @default.
- W4293146026 hasFunder F4320335777 @default.
- W4293146026 hasFunder F4320336652 @default.
- W4293146026 hasLocation W42931460261 @default.
- W4293146026 hasOpenAccess W4293146026 @default.
- W4293146026 hasPrimaryLocation W42931460261 @default.
- W4293146026 hasRelatedWork W1512718085 @default.
- W4293146026 hasRelatedWork W1569841287 @default.
- W4293146026 hasRelatedWork W2293457016 @default.
- W4293146026 hasRelatedWork W2351428524 @default.
- W4293146026 hasRelatedWork W2359001871 @default.
- W4293146026 hasRelatedWork W2369308426 @default.
- W4293146026 hasRelatedWork W2789919619 @default.
- W4293146026 hasRelatedWork W3169305685 @default.
- W4293146026 hasRelatedWork W1551406738 @default.
- W4293146026 hasRelatedWork W2610387714 @default.
- W4293146026 hasVolume "310" @default.
- W4293146026 isParatext "false" @default.
- W4293146026 isRetracted "false" @default.
- W4293146026 workType "article" @default.