Matches in SemOpenAlex for { <https://semopenalex.org/work/W4320233408> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W4320233408 abstract "Data-to-text generation systems aim to generate text descriptions based on input data (often represented in the tabular form). A typical system uses huge training samples for learning the correspondence between tables and texts. However, large training sets are expensive to obtain, limiting the applicability of these approaches in real-world scenarios. In this work, we focus on few-shot data-to-text generation. We observe that, while fine-tuned pretrained language models may generate plausible sentences, they suffer from the low semantic coverage problem in the few-shot setting. In other words, important input slots tend to be missing in the generated text. To this end, we propose a search-and-learning approach that leverages pretrained language models but inserts the missing slots to improve the semantic coverage. We further fine-tune our system based on the search results to smooth out the search noise, yielding better-quality text and improving inference efficiency to a large extent. Experiments show that our model achieves high performance on E2E and WikiBio datasets. Especially, we cover 98.35% of input slots on E2E, largely alleviating the low coverage problem." @default.
- W4320233408 created "2023-02-13" @default.
- W4320233408 creator A5024821632 @default.
- W4320233408 creator A5067342034 @default.
- W4320233408 creator A5073903451 @default.
- W4320233408 creator A5083628707 @default.
- W4320233408 date "2021-12-05" @default.
- W4320233408 modified "2023-09-23" @default.
- W4320233408 title "Search and Learn: Improving Semantic Coverage for Data-to-Text Generation" @default.
- W4320233408 doi "https://doi.org/10.48550/arxiv.2112.02770" @default.
- W4320233408 hasPublicationYear "2021" @default.
- W4320233408 type Work @default.
- W4320233408 citedByCount "0" @default.
- W4320233408 crossrefType "posted-content" @default.
- W4320233408 hasAuthorship W4320233408A5024821632 @default.
- W4320233408 hasAuthorship W4320233408A5067342034 @default.
- W4320233408 hasAuthorship W4320233408A5073903451 @default.
- W4320233408 hasAuthorship W4320233408A5083628707 @default.
- W4320233408 hasBestOaLocation W43202334081 @default.
- W4320233408 hasConcept C111472728 @default.
- W4320233408 hasConcept C119857082 @default.
- W4320233408 hasConcept C120665830 @default.
- W4320233408 hasConcept C121332964 @default.
- W4320233408 hasConcept C127413603 @default.
- W4320233408 hasConcept C137293760 @default.
- W4320233408 hasConcept C138885662 @default.
- W4320233408 hasConcept C154945302 @default.
- W4320233408 hasConcept C188198153 @default.
- W4320233408 hasConcept C192209626 @default.
- W4320233408 hasConcept C204321447 @default.
- W4320233408 hasConcept C23123220 @default.
- W4320233408 hasConcept C2776214188 @default.
- W4320233408 hasConcept C2779530757 @default.
- W4320233408 hasConcept C2780428219 @default.
- W4320233408 hasConcept C41008148 @default.
- W4320233408 hasConcept C51632099 @default.
- W4320233408 hasConcept C78519656 @default.
- W4320233408 hasConceptScore W4320233408C111472728 @default.
- W4320233408 hasConceptScore W4320233408C119857082 @default.
- W4320233408 hasConceptScore W4320233408C120665830 @default.
- W4320233408 hasConceptScore W4320233408C121332964 @default.
- W4320233408 hasConceptScore W4320233408C127413603 @default.
- W4320233408 hasConceptScore W4320233408C137293760 @default.
- W4320233408 hasConceptScore W4320233408C138885662 @default.
- W4320233408 hasConceptScore W4320233408C154945302 @default.
- W4320233408 hasConceptScore W4320233408C188198153 @default.
- W4320233408 hasConceptScore W4320233408C192209626 @default.
- W4320233408 hasConceptScore W4320233408C204321447 @default.
- W4320233408 hasConceptScore W4320233408C23123220 @default.
- W4320233408 hasConceptScore W4320233408C2776214188 @default.
- W4320233408 hasConceptScore W4320233408C2779530757 @default.
- W4320233408 hasConceptScore W4320233408C2780428219 @default.
- W4320233408 hasConceptScore W4320233408C41008148 @default.
- W4320233408 hasConceptScore W4320233408C51632099 @default.
- W4320233408 hasConceptScore W4320233408C78519656 @default.
- W4320233408 hasLocation W43202334081 @default.
- W4320233408 hasOpenAccess W4320233408 @default.
- W4320233408 hasPrimaryLocation W43202334081 @default.
- W4320233408 hasRelatedWork W142374489 @default.
- W4320233408 hasRelatedWork W1488266984 @default.
- W4320233408 hasRelatedWork W1563618553 @default.
- W4320233408 hasRelatedWork W2148757832 @default.
- W4320233408 hasRelatedWork W2359001871 @default.
- W4320233408 hasRelatedWork W2511279186 @default.
- W4320233408 hasRelatedWork W2916492174 @default.
- W4320233408 hasRelatedWork W3008086364 @default.
- W4320233408 hasRelatedWork W3107474891 @default.
- W4320233408 hasRelatedWork W563404 @default.
- W4320233408 isParatext "false" @default.
- W4320233408 isRetracted "false" @default.
- W4320233408 workType "article" @default.