Presentation | 1998/7/24 A new approach to acquiring linguistic knowledge for summarizing parts of news sentences and its evaluation Naoto Katoh, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | This paper proposes a new approach to acquiring linguistic knowledge that plays an important role in summarizing parts of news sentences. The linguistic knowledge, which is composed of transformation knowledge and transformation condition, can provide linguistic constraint of transforming characters, words, Bunsetsu-phrases in summarizing Japanese sentences. The proposed method analyzes original news sentences and the human-summarized ones by Japanese morphological analyzer, and aligns words in the original sentences with words in the summarized ones by DP matching based on distances between the words. Transformation knowledge is acquired as the result of the difference and transformation condition is extracted as n-gram words located near transformation knowledge. We acquired linguistic knowledge from NHK news corpus and conducted a series of experiments to evaluate the linguistic knowledge. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | automatic summarization / corpus / automatic acquisition / linguistic knowledge / Japanese news / n-gram |
Paper # | NLC98-16 |
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) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
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) | A new approach to acquiring linguistic knowledge for summarizing parts of news sentences and its evaluation |
Sub Title (in English) | |
Keyword(1) | automatic summarization |
Keyword(2) | corpus |
Keyword(3) | automatic acquisition |
Keyword(4) | linguistic knowledge |
Keyword(5) | Japanese news |
Keyword(6) | n-gram |
1st Author's Name | Naoto Katoh |
1st Author's Affiliation | NHK Science and Technical Research Laboratories() |
Date | 1998/7/24 |
Paper # | NLC98-16 |
Volume (vol) | vol.98 |
Number (no) | 210 |
Page | pp.pp.- |
#Pages | 8 |
Date of Issue |