Matches in SemOpenAlex for { <https://semopenalex.org/work/W4320342468> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W4320342468 abstract "Pre-trained language models (PLM) have achieved remarkable advancement in table-to-text generation tasks. However, the lack of labeled domain-specific knowledge and the topology gap between tabular data and text make it difficult for PLMs to yield faithful text. Low-resource generation likewise faces unique challenges in this domain. Inspired by how humans descript tabular data with prior knowledge, we suggest a new framework: PromptMize, which targets table-to-text generation under few-shot settings. The design of our framework consists of two aspects: a prompt planner and a knowledge adapter. The prompt planner aims to generate a prompt signal that provides instance guidance for PLMs to bridge the topology gap between tabular data and text. Moreover, the knowledge adapter memorizes domain-specific knowledge from the unlabelled corpus to supply essential information during generation. Extensive experiments and analyses are investigated on three open domain few-shot NLG datasets: human, song, and book. Compared with previous state-of-the-art approaches, our model achieves remarkable performance in generating quality as judged by human and automatic evaluations." @default.
- W4320342468 created "2023-02-13" @default.
- W4320342468 creator A5024900991 @default.
- W4320342468 creator A5034043503 @default.
- W4320342468 creator A5034483183 @default.
- W4320342468 creator A5036143549 @default.
- W4320342468 creator A5044559284 @default.
- W4320342468 creator A5067200755 @default.
- W4320342468 creator A5080757739 @default.
- W4320342468 creator A5082388465 @default.
- W4320342468 date "2023-02-08" @default.
- W4320342468 modified "2023-10-16" @default.
- W4320342468 title "Few-Shot Table-to-Text Generation with Prompt Planning and Knowledge Memorization" @default.
- W4320342468 doi "https://doi.org/10.48550/arxiv.2302.04415" @default.
- W4320342468 hasPublicationYear "2023" @default.
- W4320342468 type Work @default.
- W4320342468 citedByCount "0" @default.
- W4320342468 crossrefType "posted-content" @default.
- W4320342468 hasAuthorship W4320342468A5024900991 @default.
- W4320342468 hasAuthorship W4320342468A5034043503 @default.
- W4320342468 hasAuthorship W4320342468A5034483183 @default.
- W4320342468 hasAuthorship W4320342468A5036143549 @default.
- W4320342468 hasAuthorship W4320342468A5044559284 @default.
- W4320342468 hasAuthorship W4320342468A5067200755 @default.
- W4320342468 hasAuthorship W4320342468A5080757739 @default.
- W4320342468 hasAuthorship W4320342468A5082388465 @default.
- W4320342468 hasBestOaLocation W43203424681 @default.
- W4320342468 hasConcept C100776233 @default.
- W4320342468 hasConcept C111919701 @default.
- W4320342468 hasConcept C124101348 @default.
- W4320342468 hasConcept C126322002 @default.
- W4320342468 hasConcept C134306372 @default.
- W4320342468 hasConcept C145420912 @default.
- W4320342468 hasConcept C154945302 @default.
- W4320342468 hasConcept C177284502 @default.
- W4320342468 hasConcept C204321447 @default.
- W4320342468 hasConcept C2776999362 @default.
- W4320342468 hasConcept C2985684807 @default.
- W4320342468 hasConcept C30038468 @default.
- W4320342468 hasConcept C33923547 @default.
- W4320342468 hasConcept C36503486 @default.
- W4320342468 hasConcept C41008148 @default.
- W4320342468 hasConcept C45235069 @default.
- W4320342468 hasConcept C71924100 @default.
- W4320342468 hasConceptScore W4320342468C100776233 @default.
- W4320342468 hasConceptScore W4320342468C111919701 @default.
- W4320342468 hasConceptScore W4320342468C124101348 @default.
- W4320342468 hasConceptScore W4320342468C126322002 @default.
- W4320342468 hasConceptScore W4320342468C134306372 @default.
- W4320342468 hasConceptScore W4320342468C145420912 @default.
- W4320342468 hasConceptScore W4320342468C154945302 @default.
- W4320342468 hasConceptScore W4320342468C177284502 @default.
- W4320342468 hasConceptScore W4320342468C204321447 @default.
- W4320342468 hasConceptScore W4320342468C2776999362 @default.
- W4320342468 hasConceptScore W4320342468C2985684807 @default.
- W4320342468 hasConceptScore W4320342468C30038468 @default.
- W4320342468 hasConceptScore W4320342468C33923547 @default.
- W4320342468 hasConceptScore W4320342468C36503486 @default.
- W4320342468 hasConceptScore W4320342468C41008148 @default.
- W4320342468 hasConceptScore W4320342468C45235069 @default.
- W4320342468 hasConceptScore W4320342468C71924100 @default.
- W4320342468 hasLocation W43203424681 @default.
- W4320342468 hasOpenAccess W4320342468 @default.
- W4320342468 hasPrimaryLocation W43203424681 @default.
- W4320342468 hasRelatedWork W2056254149 @default.
- W4320342468 hasRelatedWork W2115920894 @default.
- W4320342468 hasRelatedWork W2293457016 @default.
- W4320342468 hasRelatedWork W2359068514 @default.
- W4320342468 hasRelatedWork W2373668538 @default.
- W4320342468 hasRelatedWork W2385034530 @default.
- W4320342468 hasRelatedWork W2610446193 @default.
- W4320342468 hasRelatedWork W2762832356 @default.
- W4320342468 hasRelatedWork W2789919619 @default.
- W4320342468 hasRelatedWork W3179717505 @default.
- W4320342468 isParatext "false" @default.
- W4320342468 isRetracted "false" @default.
- W4320342468 workType "article" @default.