This paper studies the abstractive multi-document summarization for event-oriented news texts through event information extraction and abstract representation. Fine-grained event mentions and semantic relations between them are extracted to build a unified and connected event semantic link network, an abstract representation of source texts. A network reduction algorithm is proposed to summarize the most salient and coherent event information. New sentences with good linguistic quality are automatically generated and selected through sentences over-generation and greedy-selection processes. Experimental results on DUC2006 and DUC2007 datasets show that our system significantly outperforms the state-of-the-art extractive and abstractive baselines under both pyramid and ROUGE evaluation metrics.
|Title of host publication||The 26th International Conference on Computational Linguistics|
|Publisher||Association for Computational Linguistics|
|Publication status||Published - 11 Dec 2016|
|Event||26th International Conference on Computational Linguistics: COLIN 2016 - Osaka, Japan|
Duration: 11 Dec 2016 → 16 Dec 2016
|Conference||26th International Conference on Computational Linguistics|
|Period||11/12/16 → 16/12/16|
Bibliographical noteThis work is licenced under a Creative Commons Attribution 4.0 International License. License details: http://
- sematnic link network
Li, W., He, L., & Zhuge, H. (2016). Abstractive news summarization based on event semantic link network. In The 26th International Conference on Computational Linguistics Association for Computational Linguistics.