Paper Abstract and Keywords |
Presentation |
2006-07-27 15:50
Detection of Text Sections which contain typical forms from Closed Captions using AdaBoost Algorism Ichiro Yamada, Kikuka Miura, Hideki Sumiyoshi, Nobuyuki Yagi (NHK), Manabu Okumura, Takenobu Tokunaga (Tokyo Institute of Technology) |
Abstract |
(in Japanese) |
(See Japanese page) |
(in English) |
In the closed captions, there are a lot of typical expressions to express specific things, for example, first introduction of a guest in a talk show or explanation of a place in travel program. Such information helps us to put metadata to the corresponding scenes. This paper proposes a method to extract a section including typical expressions. The first step generates tree structures from inputted section of sentences and evaluates the similarities between those tree structures. We use these similarities as weak learners of adaboost algorism to judge whether the section of sentences includes typical expressions or not. In the experiment of detecting sections including typical expressions which explain a place with video targeting closed captions of TV programs concerned with travel, we show the effectiveness of our method. |
Keyword |
(in Japanese) |
(See Japanese page) |
(in English) |
Metadata / Typical expression extraction / Closed-caption / Tree Structure / AdaBoost Algorithm / / / |
Reference Info. |
IEICE Tech. Rep., vol. 106, no. 190, NLC2006-5, pp. 25-30, July 2006. |
Paper # |
NLC2006-5 |
Date of Issue |
2006-07-20 (NLC) |
ISSN |
Print edition: ISSN 0913-5685 |
Download PDF |
|