Paper: A Bottom-Up Approach To Sentence Ordering For Multi-Document Summarization

ACL ID P06-1049
Title A Bottom-Up Approach To Sentence Ordering For Multi-Document Summarization
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2006
Authors

Ordering information is a difficult but important task for applications generat- ing natural-language text. We present a bottom-up approach to arranging sen- tences extracted for multi-document sum- marization. To capture the association and order of two textual segments (eg, sen- tences), we define four criteria, chronol- ogy, topical-closeness, precedence, and succession. These criteria are integrated into a criterion by a supervised learning approach. We repeatedly concatenate two textual segments into one segment based on the criterion until we obtain the overall segment with all sentences arranged. Our experimental results show a significant im- provement over existing sentence ordering strategies.