@inproceedings{c871dd46d87a42549707ad06e484d20e,
title = "Chinese text summarization using a trainable summarizer and latent semantic analysis",
abstract = "In this paper, two novel approaches are proposed to extract important sentences from a document to create its summary. The first is a corpus-based approach using feature analysis. It brings up three new ideas: 1) to employ ranked position to emphasize the significance of sentence position, 2) to reshape word unit to achieve higher accuracy of keyword importance, and 3) to train a score function by the genetic algorithm for obtaining a suitable combination of feature weights. The second approach combines the ideas of latent semantic analysis and text relationship maps to interpret conceptual structures of a document. Both approaches are applied to Chinese text summarization. The two approaches were evaluated by using a data corpus composed of 100 articles about politics from New Taiwan Weekly, and when the compression ratio was 30%, average recalls of 52.0% and 45.6% were achieved respectively.",
author = "Yeh, {Jen Yuan} and Ke, {Hao Ren} and Yang, {Wei Pang}",
note = "Publisher Copyright: {\textcopyright} Springer-Verlag Berlin Heidelberg 2002.; 5th International Conference on Asian Digital Libraries, ICADL 2002 ; Conference date: 11-12-2002 Through 14-12-2002",
year = "2002",
doi = "10.1007/3-540-36227-4_8",
language = "English",
isbn = "3540002618",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Verlag",
pages = "76--87",
editor = "Ee-Peng Lim and Schubert Foo and Chris Khoo and Hsinchun Chen and Edward Fox and Shalini Urs and Thanos Costantino",
booktitle = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
}