Abstract
We explore using relevant tweets of a given news article to help sentence com-pression for generating compressive news highlights. We extend an unsupervised dependency-tree based sentence compres-sion approach by incorporating tweet in-formation to weight the tree edge in terms of informativeness and syntactic impor-tance. The experimental results on a pub-lic corpus that contains both news arti-cles and relevant tweets show that our pro-posed tweets guided sentence compres-sion method can improve the summariza-tion performance significantly compared to the baseline generic sentence compres-sion method.
Cite
CITATION STYLE
Wei, Z., Liu, Y., Li, C., & Gao, W. (2015). Using tweets to help sentence compression for news highlights generation. In ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference (Vol. 2, pp. 50–56). Association for Computational Linguistics (ACL). https://doi.org/10.3115/v1/p15-2009
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.
