Many current artificial general intelligence (AGI) and natural language processing (NLP) architectures do not possess general conversational intelligence--that is, they either do not deal with language or are unable to convey knowledge in a form similar to the human language without manual, labor-intensive methods such as template-based customization. In this paper, we propose a new technique to automatically generate grammatically valid sentences using the Link Grammar database. This natural language generation method far outperforms current state-of-the-art baselines and may serve as the final component in a proto-AGI question answering pipeline that understandably handles natural language material.
@article{arxiv.2105.00830,
title = {Natural Language Generation Using Link Grammar for General Conversational Intelligence},
author = {Vignav Ramesh and Anton Kolonin},
journal= {arXiv preprint arXiv:2105.00830},
year = {2021}
}