A neural pipeline with explicit ordering, structuring, lexicalization, and referring-expression steps outperforms end-to-end sequence models for generating text from RDF triples, especially on unseen domains.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Neural data-to-text generation: A comparison between pipeline and end-to-end architectures
A neural pipeline with explicit ordering, structuring, lexicalization, and referring-expression steps outperforms end-to-end sequence models for generating text from RDF triples, especially on unseen domains.