ML Anthology

Towards CST-Enhanced Summarization

Zhu Zhang, Sasha Blair-Goldensohn, Dragomir R. Radev
AAAI 2002 pp. 439-446
doi:10.5555/777092.777162 /aaai/2002/zhang2002aaai-cst/

Abstract

In this paper, we propose to enhance the process of automatic extractive multi-document text summarization by taking into account cross-document structural relationships as posited in Cross-document Structure Theory (CST). An arbitrary multidocument extract can be CST-enhanced by replacing low-salience sentences with other sentences that increase the total number of CST relationships included in the summary. We show that CST-enhanced summaries outperform their unmodified counterparts using the relative utility evaluation metric. We also show that the effect of a CST relationship on an extract depends on its type.

PDF AAAI Semantic Scholar

Cite

Text

Zhang et al. "Towards CST-Enhanced Summarization." AAAI Conference on Artificial Intelligence, 2002. doi:10.5555/777092.777162

Markdown

[Zhang et al. "Towards CST-Enhanced Summarization." AAAI Conference on Artificial Intelligence, 2002.](https://mlanthology.org/aaai/2002/zhang2002aaai-cst/) doi:10.5555/777092.777162

BibTeX

@inproceedings{zhang2002aaai-cst,
  title     = {{Towards CST-Enhanced Summarization}},
  author    = {Zhang, Zhu and Blair-Goldensohn, Sasha and Radev, Dragomir R.},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2002},
  pages     = {439-446},
  doi       = {10.5555/777092.777162},
  url       = {https://mlanthology.org/aaai/2002/zhang2002aaai-cst/}
}