Papers with realization

2 papers
Step-by-Step: Separating Planning from Realization in Neural Data-to-Text Generation (N19-1)

Copied to clipboard

Challenge: Modern neural generation systems conflate these two steps into a single end-to-end differentiable system.
Approach: They propose to split the generation process into a symbolic text-planning stage that is faithful to the input, followed by a neural generation stage that focuses only on realization.
Outcome: The proposed method improves reliability and adequacy while maintaining fluent output.
Nutri-bullets Hybrid: Consensual Multi-document Summarization (2021.naacl-main)

Copied to clipboard

Challenge: Existing methods for generating comparative summaries that highlight similarities and contradictions in input documents are lacking large parallel training data for their training.
Approach: They propose a method for generating comparative summaries that highlight similarities and contradictions in input documents by using a neural interpretation of traditional concept-to-text generation systems.
Outcome: The proposed model is compared with conventional methods in the domain of nutrition and health, where the existing models lack large parallel training data.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations