ADROIT: Automatic Discourse Relation Organizer of Internet-Based Text
Abstract
The ADROIT system that we are developing allows automatic discourse analysis of information rich natural language texts extracted directly from the web. We use guidelines and relations of Rhetorical Structure Theory (RST) to decompose texts into elementary segments and to perform the discourse parsing between them. In this paper, we present version 1.0 of ADROIT and focus on the noble technique of cue-phrase disambiguation and machine learning for identification and organization of discourse relations. verbs, verb dependency, etc. to recognize relations when cue-phrases are not available.
Cite
Text
Morshed and Ishizuka. "ADROIT: Automatic Discourse Relation Organizer of Internet-Based Text." AAAI Conference on Artificial Intelligence, 2008.Markdown
[Morshed and Ishizuka. "ADROIT: Automatic Discourse Relation Organizer of Internet-Based Text." AAAI Conference on Artificial Intelligence, 2008.](https://mlanthology.org/aaai/2008/morshed2008aaai-adroit/)BibTeX
@inproceedings{morshed2008aaai-adroit,
title = {{ADROIT: Automatic Discourse Relation Organizer of Internet-Based Text}},
author = {Morshed, A. S. M. Mahbub and Ishizuka, Mitsuru},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2008},
pages = {1824-1825},
url = {https://mlanthology.org/aaai/2008/morshed2008aaai-adroit/}
}