Name
Abstract | ||
|---|---|---|
Many methods of text summarization combining sentence selection and sentence compression have recently been proposed. Although the dependency between words has been used in most of these methods, the dependency between sentences, i.e., rhetorical structures, has not been exploited in such joint methods. We used both dependency between words and dependency between sentences by constructing a nested tree, in which nodes in the document tree representing dependency between sentences were replaced by a sentence tree representing dependency between words. We formulated a summarization task as a combinatorial optimization problem, in which the nested tree was trimmed without losing important content in the source document. The results from an empirical evaluation revealed that our method based on the trimming of the nested tree significantly improved the summarization of texts. |
Year | Venue | Field |
|---|---|---|
2014 | PROCEEDINGS OF THE 52ND ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 2 | Automatic summarization,Combinatorial optimization problem,Computer science,Rhetorical question,Speech recognition,Document summarization,Sentence compression,Natural language processing,Tree structure,Artificial intelligence,Trimming,Sentence |
DocType | Volume | Citations |
Conference | P14-2 | 10 |
PageRank | References | Authors |
0.54 | 15 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Yuta Kikuchi | 1 | 28 | 3.27 |
| Tsutomu Hirao | 2 | 18 | 4.14 |
| Hiroya Takamura | 3 | 529 | 64.23 |
| Manabu Okumura | 4 | 830 | 114.41 |
| Masaaki Nagata | 5 | 19 | 5.41 |