Natural Language Generation for Text-to-Text Applications Using an Information-Slim Representation
Abstract
I propose a representation formalism and algorithms to be used in a new language generation mechanism for text-to-text applications. The generation process is driven by both text-specific information encoded via probability distributions over words and phrases derived from the input text, and general language knowledge captured by n-gram and syntactic language models.
Cite
Text
Soricut. "Natural Language Generation for Text-to-Text Applications Using an Information-Slim Representation." AAAI Conference on Artificial Intelligence, 2005.Markdown
[Soricut. "Natural Language Generation for Text-to-Text Applications Using an Information-Slim Representation." AAAI Conference on Artificial Intelligence, 2005.](https://mlanthology.org/aaai/2005/soricut2005aaai-natural/)BibTeX
@inproceedings{soricut2005aaai-natural,
title = {{Natural Language Generation for Text-to-Text Applications Using an Information-Slim Representation}},
author = {Soricut, Radu},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2005},
pages = {1662-1663},
url = {https://mlanthology.org/aaai/2005/soricut2005aaai-natural/}
}