Compressive Document Summarization via Sparse Optimization
Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence. Main Track. Pages 1376-1381.
Abstract
In this paper, we formulate a sparse optimization framework for extractive document summarization. The proposed framework has a decomposable convex objective function. We derive an efficient ADMM algorithm to solve it. To encourage diversity in the summaries, we explicitly introduce an additional sentence dissimilarity term in the optimization framework. We achieve significant improvement over previous related work under similar data reconstruction framework. We then generalize our formulation to the case of compressive summarization and derive a block coordinate descent algorithm to optimize the objective function. Performance on DUC 2006 and DUC 2007 datasets shows that our compressive summarization results are competitive against the state-of-the-art results while maintaining reasonable readability.
@inproceedings{ijcai2015p198,
title = {Compressive Document Summarization via Sparse Optimization},
author = {Yao, Jin-ge and Wan, Xiaojun and Xiao, Jianguo},
booktitle = {Proceedings of the Twenty-Fourth International Joint Conference on
Artificial Intelligence, {IJCAI-15}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {Qiang Yang and Michael Wooldridge},
pages = {1376--1381},
year = {2015},
month = {7},
note = {Main Track},
url = {https://ijcai.org/proceedings/2015/198},
}
TY - CPAPER TI - Compressive Document Summarization via Sparse Optimization AU - Yao, Jin-ge AU - Wan, Xiaojun AU - Xiao, Jianguo T2 - Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-15 PB - International Joint Conferences on Artificial Intelligence PY - 2015 SP - 1376 EP - 1381 UR - https://ijcai.org/proceedings/2015/198 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
