Graph-Based Multi-Modality Learning for Topic-Focused Multi-Document Summarization
Proceedings of the Twenty-First International Joint Conference on Artificial Intelligence. Pages 1586-1590.
Abstract
Graph-based manifold-ranking methods have been successfully applied to topic-focused multi-document summarization. This paper further proposes to use the multi-modality manifold-ranking algorithm for extracting topic-focused summary from multiple documents by considering the within-document sentence relationships and the cross-document sentence relationships as two separate modalities (graphs). Three different fusion schemes, namely linear form, sequential form and score combination form, are exploited in the algorithm. Experimental results on the DUC benchmark datasets demonstrate the effectiveness of the proposed multi-modality learning algorithms with all the three fusion schemes.Xiaojun Wan, Jianguo Xiao
@inproceedings{ijcai2009p265,
title = {Graph-Based Multi-Modality Learning for Topic-Focused Multi-Document Summarization},
author = {Wan, Xiaojun and Xiao, Jianguo},
booktitle = {Proceedings of the Twenty-First International Joint Conference on
Artificial Intelligence, {IJCAI-09}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {Hiroaki Kitano},
pages = {1586--1590},
year = {2009},
url = {https://ijcai.org/proceedings/2009/265},
}
TY - CPAPER TI - Graph-Based Multi-Modality Learning for Topic-Focused Multi-Document Summarization AU - Wan, Xiaojun AU - Xiao, Jianguo T2 - Proceedings of the Twenty-First International Joint Conference on Artificial Intelligence, IJCAI-09 PB - International Joint Conferences on Artificial Intelligence PY - 2009 SP - 1586 EP - 1590 UR - https://ijcai.org/proceedings/2009/265 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
