A Bottom-Up Approach to Sentence Ordering for Multi-Document Summarization [chapter]

Danushka Bollegala, Naoaki Okazaki, Mitsuru Ishizuka
2012 Multi-source, Multilingual Information Extraction and Summarization  
Ordering information is a difficult but important task for applications generating natural-language text. We present a bottom-up approach to arranging sentences extracted for multi-document summarization. To capture the association and order of two textual segments (eg, sentences), we define four criteria, chronology, topical-closeness, precedence, and succession. These criteria are integrated into a criterion by a supervised learning approach. We repeatedly concatenate two textual segments
more » ... one segment based on the criterion until we obtain the overall segment with all sentences arranged. Our experimental results show a significant improvement over existing sentence ordering strategies.
doi:10.1007/978-3-642-28569-1_12 dblp:series/tanlp/BollegalaOI13 fatcat:f2tlbuennzcvlpvamf4evroelm