Presentation 1998/7/24
Partitioning long sentences: how useful it is for sentences extraction
Takahiro Wakao, Terumasa Ehara, Katsuhiko Shirai,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) It is known that there are fewer sentences in a TV news text and the sentences are longer compared with those in a newspaper article. We use such TV news texts and would like to summarize them by selecting important sentences. However, since each sentences is rather long, we end up losing a good amount of information if we omit a whole sentence. Therefore, we adopted a method in which we partition long sentences into shorter sentences, and select important sentences from them. We evaluate the results of the method as well as those of the simple sentence extraction where there is no partitioning of the sentences.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Sentence extraction / Sentence partitioning / Text summarization / TV news text
Paper # NLC98-15
Date of Issue

Conference Information
Committee NLC
Conference Date 1998/7/24(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Vice Chair

Paper Information
Registration To Natural Language Understanding and Models of Communication (NLC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Partitioning long sentences: how useful it is for sentences extraction
Sub Title (in English)
Keyword(1) Sentence extraction
Keyword(2) Sentence partitioning
Keyword(3) Text summarization
Keyword(4) TV news text
1st Author's Name Takahiro Wakao
1st Author's Affiliation TAO of Japan()
2nd Author's Name Terumasa Ehara
2nd Author's Affiliation NHK/TAO
3rd Author's Name Katsuhiko Shirai
3rd Author's Affiliation Waseda University/TAO
Date 1998/7/24
Paper # NLC98-15
Volume (vol) vol.98
Number (no) 210
Page pp.pp.-
#Pages 6
Date of Issue