@inbook{6f99847fe3994ba18877b665e5e97d35,
title = "PSO: A language for Web information extraction and Web page clipping",
abstract = "Web information extraction and Web page clipping are important technique in adaptive hypermedia which adapt or compose contents from real Web pages. A technical problem for them is robustness of specification of parts of Web pages against update of Web pages. In this paper we present a language called PSO for Web information extraction and Web page clipping. Thanks to operations called path set operations which the language provides for the problem, we can specify parts of Web pages with small differences in expected formats by structural similarity between Web pages. We also show application of the language to real Web pages.",
author = "Tetsuya Suzuki and Takehiro Tokuda",
year = "2004",
doi = "10.1007/978-3-540-27780-4_45",
language = "English",
isbn = "3540228950",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Verlag",
pages = "332--335",
editor = "{de Bra}, Paul and Wolfgang Nejdl",
booktitle = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
}