Paper: Single Document Summarization based on Nested Tree Structure

ACL ID P14-2052
Title Single Document Summarization based on Nested Tree Structure
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2014

Many methods of text summarization combining sentence selection and sen- tence compression have recently been pro- posed. Although the dependency between words has been used in most of these methods, the dependency between sen- tences, i.e., rhetorical structures, has not been exploited in such joint methods. We used both dependency between words and dependency between sentences by con- structing a nested tree, in which nodes in the document tree representing depen- dency between sentences were replaced by a sentence tree representing dependency between words. We formulated a sum- marization task as a combinatorial opti- mization problem, in which the nested tree was trimmed without losing impor- tant content in the source document. The results from an empirical evaluation re- vealed that ...