NATSUM: Narrative abstractive summarization through cross-document timeline generation

Please use this identifier to cite or link to this item: http://hdl.handle.net/10045/93991
Información del item - Informació de l'item - Item information
Title: NATSUM: Narrative abstractive summarization through cross-document timeline generation
Authors: Barros, Cristina | Lloret, Elena | Saquete Boró, Estela | Navarro Colorado, Borja
Research Group/s: Procesamiento del Lenguaje y Sistemas de Información (GPLSI)
Center, Department or Service: Universidad de Alicante. Departamento de Lenguajes y Sistemas Informáticos
Keywords: Narrative summarization | Abstractive summarization | Timeline generation | Temporal information processing | Natural language generation
Knowledge Area: Lenguajes y Sistemas Informáticos
Issue Date: Sep-2019
Publisher: Elsevier
Citation: Information Processing & Management. 2019, 56(5): 1775-1793. doi:10.1016/j.ipm.2019.02.010
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.
Sponsor: This research work has been partially funded by the Ministerio de Economía y Competitividad. España through projects TIN2015-65100-R, TIN2015-65136-C2-2-R, as well as by the project “Analisis de Sentimientos Aplicado a la Prevencion del Suicidio en las Redes Sociales (ASAP)” funded by Ayudas Fundación BBVA a equipos de investigacion cientifica. Moreover, it has been also funded by Generalitat Valenciana through project “SIIA: Tecnologías del lenguaje humano para una sociedad inclusiva, igualitaria, y accesible” with grant reference PROMETEU/2018/089.
URI: http://hdl.handle.net/10045/93991
ISSN: 0306-4573 (Print) | 1873-5371 (Online)
DOI: 10.1016/j.ipm.2019.02.010
Language: eng
Type: info:eu-repo/semantics/article
Rights: © 2019 Elsevier Ltd.
Peer Review: si
Publisher version: https://doi.org/10.1016/j.ipm.2019.02.010
Appears in Collections:INV - GPLSI - Artículos de Revistas

Files in This Item:
Files in This Item:
File Description SizeFormat 
Thumbnail2019_Barros_etal_InformProcessManag_final.pdfVersión final (acceso restringido)1,49 MBAdobe PDFOpen    Request a copy


Items in RUA are protected by copyright, with all rights reserved, unless otherwise indicated.