Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385644172> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W4385644172 abstract "Script Event Prediction (SEP) aims to predict the subsequent event for a given event chain from a candidate list. Prior research has achieved great success by integrating external knowledge to enhance the semantics, but it is laborious to acquisite the appropriate knowledge resources and retrieve the script-related knowledge. In this paper, we regard public pre-trained language models as knowledge bases and automatically mine the script-related knowledge via prompt-learning. Still, the scenario-diversity and label-ambiguity in scripts make it uncertain to construct the most functional prompt and label token in prompt learning, i.e., prompt-uncertainty and verbalizer-uncertainty. Considering the innate ability of Gaussian distribution to express uncertainty, we deploy the prompt tokens and label tokens as random variables following Gaussian distributions, where a prompt estimator and a verbalizer estimator are proposed to estimate their probabilistic representations instead of deterministic representations. We take the lead to explore prompt-learning in SEP and provide a fresh perspective to enrich the script semantics. Our method is evaluated on the most widely used benchmark and a newly proposed large-scale one. Experiments show that our method, which benefits from knowledge evoked from pre-trained language models, outperforms prior baselines by 1.46% and 1.05% on two benchmarks, respectively." @default.
- W4385644172 created "2023-08-08" @default.
- W4385644172 creator A5028351629 @default.
- W4385644172 creator A5041369287 @default.
- W4385644172 creator A5043360958 @default.
- W4385644172 creator A5066857796 @default.
- W4385644172 creator A5080665569 @default.
- W4385644172 creator A5080686378 @default.
- W4385644172 date "2023-08-03" @default.
- W4385644172 modified "2023-09-22" @default.
- W4385644172 title "Prompt2Gaussia: Uncertain Prompt-learning for Script Event Prediction" @default.
- W4385644172 doi "https://doi.org/10.48550/arxiv.2308.02103" @default.
- W4385644172 hasPublicationYear "2023" @default.
- W4385644172 type Work @default.
- W4385644172 citedByCount "0" @default.
- W4385644172 crossrefType "posted-content" @default.
- W4385644172 hasAuthorship W4385644172A5028351629 @default.
- W4385644172 hasAuthorship W4385644172A5041369287 @default.
- W4385644172 hasAuthorship W4385644172A5043360958 @default.
- W4385644172 hasAuthorship W4385644172A5066857796 @default.
- W4385644172 hasAuthorship W4385644172A5080665569 @default.
- W4385644172 hasAuthorship W4385644172A5080686378 @default.
- W4385644172 hasBestOaLocation W43856441721 @default.
- W4385644172 hasConcept C105795698 @default.
- W4385644172 hasConcept C111919701 @default.
- W4385644172 hasConcept C119857082 @default.
- W4385644172 hasConcept C121332964 @default.
- W4385644172 hasConcept C13280743 @default.
- W4385644172 hasConcept C154945302 @default.
- W4385644172 hasConcept C162324750 @default.
- W4385644172 hasConcept C184337299 @default.
- W4385644172 hasConcept C185429906 @default.
- W4385644172 hasConcept C185798385 @default.
- W4385644172 hasConcept C187736073 @default.
- W4385644172 hasConcept C199360897 @default.
- W4385644172 hasConcept C204321447 @default.
- W4385644172 hasConcept C205649164 @default.
- W4385644172 hasConcept C2776214188 @default.
- W4385644172 hasConcept C2779662365 @default.
- W4385644172 hasConcept C2780451532 @default.
- W4385644172 hasConcept C2780522230 @default.
- W4385644172 hasConcept C33923547 @default.
- W4385644172 hasConcept C41008148 @default.
- W4385644172 hasConcept C49937458 @default.
- W4385644172 hasConcept C61423126 @default.
- W4385644172 hasConcept C62520636 @default.
- W4385644172 hasConceptScore W4385644172C105795698 @default.
- W4385644172 hasConceptScore W4385644172C111919701 @default.
- W4385644172 hasConceptScore W4385644172C119857082 @default.
- W4385644172 hasConceptScore W4385644172C121332964 @default.
- W4385644172 hasConceptScore W4385644172C13280743 @default.
- W4385644172 hasConceptScore W4385644172C154945302 @default.
- W4385644172 hasConceptScore W4385644172C162324750 @default.
- W4385644172 hasConceptScore W4385644172C184337299 @default.
- W4385644172 hasConceptScore W4385644172C185429906 @default.
- W4385644172 hasConceptScore W4385644172C185798385 @default.
- W4385644172 hasConceptScore W4385644172C187736073 @default.
- W4385644172 hasConceptScore W4385644172C199360897 @default.
- W4385644172 hasConceptScore W4385644172C204321447 @default.
- W4385644172 hasConceptScore W4385644172C205649164 @default.
- W4385644172 hasConceptScore W4385644172C2776214188 @default.
- W4385644172 hasConceptScore W4385644172C2779662365 @default.
- W4385644172 hasConceptScore W4385644172C2780451532 @default.
- W4385644172 hasConceptScore W4385644172C2780522230 @default.
- W4385644172 hasConceptScore W4385644172C33923547 @default.
- W4385644172 hasConceptScore W4385644172C41008148 @default.
- W4385644172 hasConceptScore W4385644172C49937458 @default.
- W4385644172 hasConceptScore W4385644172C61423126 @default.
- W4385644172 hasConceptScore W4385644172C62520636 @default.
- W4385644172 hasLocation W43856441721 @default.
- W4385644172 hasOpenAccess W4385644172 @default.
- W4385644172 hasPrimaryLocation W43856441721 @default.
- W4385644172 hasRelatedWork W1485630101 @default.
- W4385644172 hasRelatedWork W201699256 @default.
- W4385644172 hasRelatedWork W2086733238 @default.
- W4385644172 hasRelatedWork W2498017833 @default.
- W4385644172 hasRelatedWork W2739306978 @default.
- W4385644172 hasRelatedWork W2740945385 @default.
- W4385644172 hasRelatedWork W2787190016 @default.
- W4385644172 hasRelatedWork W2961085424 @default.
- W4385644172 hasRelatedWork W2983785000 @default.
- W4385644172 hasRelatedWork W4290792893 @default.
- W4385644172 isParatext "false" @default.
- W4385644172 isRetracted "false" @default.
- W4385644172 workType "article" @default.