A modular T5-based pipeline using RDF triples, sentence aggregation, and style transfer generates factual text with subjective interpretations from tables, achieving moderate gains over several LLM baselines.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Ta-G-T: Subjectivity Capture in Table to Text Generation via RDF Graphs
A modular T5-based pipeline using RDF triples, sentence aggregation, and style transfer generates factual text with subjective interpretations from tables, achieving moderate gains over several LLM baselines.