close fullscreen

Publications+Natural Language Generation Using Link Grammar for General Conversational Intelligence

help edit space_dashboard
Draft — This content has not been approved for publication.
ai generated
more_horiz
open_in_full page
fullscreen modal
edit edit
space_dashboard advanced
Authors: Vignav Ramesh, Anton Kolonin

← Back to Publications

Natural Language Generation Using Link Grammar for General Conversational Intelligence

Authors:

Vignav Ramesh
Anton Kolonin

Year: 2021
Venue: arXiv:2105.00830
Links: arXiv abstract

Summary

Proposes a method to automatically generate grammatically valid sentences from the Link Grammar database, reporting large improvements over state-of-the-art baselines and intended as the final natural-language-generation component of an interpretable proto-AGI question-answering pipeline. It emphasizes interpretable language processing over black-box neural generation.

Relevance to Hyperon

A Link-Grammar-based NLG source directly in the interpretable-pipeline lineage (segmentation → parsing → generation) described in the Semantic Parsing Deep Dive.

Key References

  • RawData source
  • Semantic Parsing Deep Dive


Tags

help edit space_dashboard
ai generated
more_horiz
open_in_full page
fullscreen modal
edit edit
space_dashboard advanced


Discussion