- 【Updated on May 12, 2025】 Integration of CiNii Dissertations and CiNii Books into CiNii Research
- Trial version of CiNii Research Automatic Translation feature is available on CiNii Labs
- Suspension and deletion of data provided by Nikkei BP
- Regarding the recording of “Research Data” and “Evidence Data”
Summarizing a Document by Trimming a Nested Tree Structure
-
- Kikuchi Yuta
- Tokyo Institute of Technology
-
- Hirao Tsutomu
- NTT Communication Science Laboratories, Nippon Telegraph and Telephone Corporation
-
- Takamura Hiroya
- Tokyo Institute of Technology
-
- Okumura Manabu
- Tokyo Institute of Technology
-
- Nagata Masaaki
- NTT Communication Science Laboratories, Nippon Telegraph and Telephone Corporation
Bibliographic Information
- Other Title
-
- 入れ子依存木の刈り込みによる単一文書要約手法
- イレコ イソン ボク ノ カリコミ ニ ヨル タンイツ ブンショ ヨウヤク シュホウ
Search this article
Description
Many methods of text summarization that have recently been proposed combine sentence selection and sentence compression. Although the dependency between words has been used in most of these methods, the dependency between sentences, i.e., the rhetorical structure, has not been exploited in such joint methods. We use both the dependency between words and the dependency between sentences by constructing a nested tree, in which nodes in a document tree representing the dependency between sentences were replaced by a sentence tree representing the dependency between words. We formulate a summarization task as a combinatorial optimization problem, in which the nested tree is 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 performance of text summarization.
Journal
-
- Journal of Natural Language Processing
-
Journal of Natural Language Processing 22 (3), 197-217, 2015
The Association for Natural Language Processing
- Tweet
Details 詳細情報について
-
- CRID
- 1390282679453148672
-
- NII Article ID
- 130005114020
-
- NII Book ID
- AN10472659
-
- ISSN
- 21858314
- 13407619
-
- NDL BIB ID
- 026744901
-
- Text Lang
- ja
-
- Article Type
- journal article
-
- Data Source
-
- JaLC
- NDL Search
- Crossref
- CiNii Articles
- KAKEN
- OpenAIRE
-
- Abstract License Flag
- Disallowed