Bidirectional Chart Generation of Natural Language Texts
Abstract
This paper presents Bidirectional Chart Generation (BCG) algorithm as an uniform control mechanism for sentence generation and text planning. It is an extension of Semantic Head Driven Generation algorithm [Shieber et al., 1989] in that recomputation of partial structures and backtracking are avoided by using a chart table. These properties enable to handle a large scale grammar including text planning and t.o implement the algorithm in parallel programming languages. Other merits of the algorithm are to deal with multiple contexts and to keep every partial structure in the chart. It becomes easier for the generator to find a recovery strategy when user cannot understand the generated text.
Cite
Text
Haruno et al. "Bidirectional Chart Generation of Natural Language Texts." AAAI Conference on Artificial Intelligence, 1993.Markdown
[Haruno et al. "Bidirectional Chart Generation of Natural Language Texts." AAAI Conference on Artificial Intelligence, 1993.](https://mlanthology.org/aaai/1993/haruno1993aaai-bidirectional/)BibTeX
@inproceedings{haruno1993aaai-bidirectional,
title = {{Bidirectional Chart Generation of Natural Language Texts}},
author = {Haruno, Masahiko and Den, Yasuharu and Matsumoto, Yuji and Nagao, Makoto},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {1993},
pages = {350-356},
url = {https://mlanthology.org/aaai/1993/haruno1993aaai-bidirectional/}
}