Matches in SemOpenAlex for { <https://semopenalex.org/work/W4379258810> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W4379258810 abstract "The generation of explanation graphs is a significant task that aims to produce explanation graphs in response to user input, revealing the internal reasoning process. This task is challenging due to the significant discrepancy between unstructured user queries and structured explanation graphs. Current research commonly fine-tunes a text-based pre-trained language model on a small downstream dataset that is annotated with labeled graphs. However, due to the limited scale of available datasets, this approach may prove to be insufficient in bridging the gap between natural language text and structured graphs. In this paper, to alleviate the above limitations, we propose a novel pre-trained framework EG3P(for Explanation Graph Generation via Generative Pre-training over synthetic graphs) for the explanation graph generation task. Specifically, we first propose a text-to-graph generative task to pre-train the model with the goal of bridging the text-graph gap. Additionally, we propose an automatic corpus synthesis strategy for synthesizing a large scale of high-quality corpus, reducing the reliance on costly manual annotation methods. Experimental results on ExplaGraphs show the effectiveness of EG3P that our model surpasses all baseline systems with remarkable margins. Besides, further analysis demonstrates that EG3P is able to generate better explanation graphs on actual reasoning tasks such as CommonsenseQA and OpenbookQA." @default.
- W4379258810 created "2023-06-04" @default.
- W4379258810 creator A5000005088 @default.
- W4379258810 creator A5009504821 @default.
- W4379258810 creator A5054331961 @default.
- W4379258810 creator A5079818805 @default.
- W4379258810 date "2023-06-01" @default.
- W4379258810 modified "2023-09-26" @default.
- W4379258810 title "Explanation Graph Generation via Generative Pre-training over Synthetic Graphs" @default.
- W4379258810 doi "https://doi.org/10.48550/arxiv.2306.00652" @default.
- W4379258810 hasPublicationYear "2023" @default.
- W4379258810 type Work @default.
- W4379258810 citedByCount "0" @default.
- W4379258810 crossrefType "posted-content" @default.
- W4379258810 hasAuthorship W4379258810A5000005088 @default.
- W4379258810 hasAuthorship W4379258810A5009504821 @default.
- W4379258810 hasAuthorship W4379258810A5054331961 @default.
- W4379258810 hasAuthorship W4379258810A5079818805 @default.
- W4379258810 hasBestOaLocation W43792588101 @default.
- W4379258810 hasConcept C119857082 @default.
- W4379258810 hasConcept C132525143 @default.
- W4379258810 hasConcept C154945302 @default.
- W4379258810 hasConcept C162324750 @default.
- W4379258810 hasConcept C167966045 @default.
- W4379258810 hasConcept C174348530 @default.
- W4379258810 hasConcept C187736073 @default.
- W4379258810 hasConcept C195324797 @default.
- W4379258810 hasConcept C204321447 @default.
- W4379258810 hasConcept C2776187449 @default.
- W4379258810 hasConcept C2776321320 @default.
- W4379258810 hasConcept C2780451532 @default.
- W4379258810 hasConcept C2985684807 @default.
- W4379258810 hasConcept C2987255567 @default.
- W4379258810 hasConcept C31258907 @default.
- W4379258810 hasConcept C39890363 @default.
- W4379258810 hasConcept C41008148 @default.
- W4379258810 hasConcept C80444323 @default.
- W4379258810 hasConceptScore W4379258810C119857082 @default.
- W4379258810 hasConceptScore W4379258810C132525143 @default.
- W4379258810 hasConceptScore W4379258810C154945302 @default.
- W4379258810 hasConceptScore W4379258810C162324750 @default.
- W4379258810 hasConceptScore W4379258810C167966045 @default.
- W4379258810 hasConceptScore W4379258810C174348530 @default.
- W4379258810 hasConceptScore W4379258810C187736073 @default.
- W4379258810 hasConceptScore W4379258810C195324797 @default.
- W4379258810 hasConceptScore W4379258810C204321447 @default.
- W4379258810 hasConceptScore W4379258810C2776187449 @default.
- W4379258810 hasConceptScore W4379258810C2776321320 @default.
- W4379258810 hasConceptScore W4379258810C2780451532 @default.
- W4379258810 hasConceptScore W4379258810C2985684807 @default.
- W4379258810 hasConceptScore W4379258810C2987255567 @default.
- W4379258810 hasConceptScore W4379258810C31258907 @default.
- W4379258810 hasConceptScore W4379258810C39890363 @default.
- W4379258810 hasConceptScore W4379258810C41008148 @default.
- W4379258810 hasConceptScore W4379258810C80444323 @default.
- W4379258810 hasLocation W43792588101 @default.
- W4379258810 hasOpenAccess W4379258810 @default.
- W4379258810 hasPrimaryLocation W43792588101 @default.
- W4379258810 hasRelatedWork W2739751068 @default.
- W4379258810 hasRelatedWork W2884815824 @default.
- W4379258810 hasRelatedWork W2985263817 @default.
- W4379258810 hasRelatedWork W3043226534 @default.
- W4379258810 hasRelatedWork W3088348751 @default.
- W4379258810 hasRelatedWork W3154973012 @default.
- W4379258810 hasRelatedWork W3198859314 @default.
- W4379258810 hasRelatedWork W4205602488 @default.
- W4379258810 hasRelatedWork W4213074484 @default.
- W4379258810 hasRelatedWork W4287712122 @default.
- W4379258810 isParatext "false" @default.
- W4379258810 isRetracted "false" @default.
- W4379258810 workType "article" @default.