Extractive Summarization By Maximizing Semantic Volume
Abstract
The most successful approaches to extractive text summarization seek to maximize bigram coverage subject to a budget constraint. In this work, we propose instead to maximize semantic volume. We embed each sentence in a semantic space and construct a summary by choosing a subset of sentences whose convex hull maximizes volume in that space. We provide a greedy algorithm based on the Gram-Schmidt process to efficiently perform volume maximization. Our method outperforms the state-of-the-art summarization approaches on benchmark datasets.
Publication Date
1-1-2015
Publication Title
Conference Proceedings - EMNLP 2015: Conference on Empirical Methods in Natural Language Processing
Number of Pages
1961-1966
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
DOI Link
https://doi.org/10.18653/v1/d15-1228
Copyright Status
Unknown
Socpus ID
84959867982 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/84959867982
STARS Citation
Yogatama, Dani; Liu, Fei; and Smith, Noah A., "Extractive Summarization By Maximizing Semantic Volume" (2015). Scopus Export 2015-2019. 1851.
https://stars.library.ucf.edu/scopus2015/1851