NATSUM: Narrative abstractive summarization through cross-document timeline generation |
| |
Authors: | Cristina Barros Elena Lloret Estela Saquete Borja Navarro-Colorado |
| |
Institution: | Department of Software and Computing Systems, University of Alicante Apdo. de Correos 99 Alicante, E-03080, Spain |
| |
Abstract: | A new approach to narrative abstractive summarization (NATSUM) is presented in this paper. NATSUM is centered on generating a narrative chronologically ordered summary about a target entity from several news documents related to the same topic. To achieve this, first, our system creates a cross-document timeline where a time point contains all the event mentions that refer to the same event. This timeline is enriched with all the arguments of the events that are extracted from different documents. Secondly, using natural language generation techniques, one sentence for each event is produced using the arguments involved in the event. Specifically, a hybrid surface realization approach is used, based on over-generation and ranking techniques. The evaluation demonstrates that NATSUM performed better than extractive summarization approaches and competitive abstractive baselines, improving the F1-measure at least by 50%, when a real scenario is simulated. |
| |
Keywords: | Corresponding author Narrative summarization Abstractive summarization Timeline generation Temporal information processing Natural language generation |
本文献已被 ScienceDirect 等数据库收录! |
|