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.
|Publisher||Association for Computational Linguistics|
|Number of pages||11|
|Publication status||Published - 11 Dec 2016|
- sematnic link network