Proof Verbalization as an Application of NLG

Abstract

This paper describes the linguistic part of a system called PROVERB, which transforms, abstracts, and verbalizes machine-found proofs into formated texts. Linguistically, the architecture of PROVERB follows most application oriented systems, and is a pipe-lined control of three components. Its macroplanner linearizes a proof and plans mediating communicative acts by employing a combination of hierarchical planning and focus-guided navigation. The microplanner then maps communicative acts and domain concepts into linguistic resources, paraphrases and aggregates such resources to produce the final Text Structure. A Text Structure contains all necessary syntactic information, and can be executed by our realizer into grammatical sentences. The system works fully automatically and performs particularly well for textbook size examples. 1

Cite

Text

Huang and Fiedler. "Proof Verbalization as an Application of NLG." International Joint Conference on Artificial Intelligence, 1997.

Markdown

[Huang and Fiedler. "Proof Verbalization as an Application of NLG." International Joint Conference on Artificial Intelligence, 1997.](https://mlanthology.org/ijcai/1997/huang1997ijcai-proof/)

BibTeX

@inproceedings{huang1997ijcai-proof,
  title     = {{Proof Verbalization as an Application of NLG}},
  author    = {Huang, Xiaorong and Fiedler, Armin},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {1997},
  pages     = {965-972},
  url       = {https://mlanthology.org/ijcai/1997/huang1997ijcai-proof/}
}