MDL-based Acquisition of Substitutability Relationships between Discourse Connectives
Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence. Pages 1690-1690.
Abstract
Knowledge of which lexical items convey the same meaning in a given context is important for many Natural Language Processing tasks. This paper concerns the substitutability of discourse connectives in particular. This paper proposes a datadriven method based on a Minimum Description Length (MDL) criterion for automatically learning substitutability of connectives. The method is shown to outperform two baseline classifiers.
Ben Hutchinson. 2005. MDL-based Acquisition of Substitutability Relationships between Discourse Connectives. In Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence, IJCAI-05. IJCAI, 1690–1690. https://ijcai.org/proceedings/2005/244
Hutchinson, B. (2005). MDL-based Acquisition of Substitutability Relationships between Discourse Connectives. In Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence, IJCAI-05 (pp. 1690–1690). IJCAI. https://ijcai.org/proceedings/2005/244
@inproceedings{ijcai2005p244,
title = {MDL-based Acquisition of Substitutability Relationships between Discourse Connectives},
author = {Hutchinson, Ben},
booktitle = {Proceedings of the Nineteenth International Joint Conference on
Artificial Intelligence, {IJCAI-05}},
publisher = {International Joint Conferences on Artificial Intelligence},
pages = {1690--1690},
year = {2005},
url = {https://ijcai.org/proceedings/2005/244},
}
TY - CPAPER TI - MDL-based Acquisition of Substitutability Relationships between Discourse Connectives AU - Hutchinson, Ben T2 - Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence, IJCAI-05 PB - International Joint Conferences on Artificial Intelligence PY - 2005 SP - 1690 EP - 1690 UR - https://ijcai.org/proceedings/2005/244 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
