Presentation 2003/9/7
A MEDLINE document search system using section information
Takahiro YAMASAKI, Masashi SHIMBO, Yuji MATSUMOTO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We present an experimental text retrieval system to facilitate search in the MEDLINE database. A unique feature of the system is that users can search not only through the whole abstract text for his specified keywords, but also from limited sections in the abstracts. The sections reflect the structure of abstract texts, such as BACKGROUND and CONCLUSIONS. This feature makes it easier to narrow down search results when adding extra keywords does not work, and allows for ranking search results according to users' needs. The MEDLINE database contains a small portion of "structured" abstracts, in which sections are explicitly marked by the headings. They thus require no additional processing for inferring which section each sentence belongs to. They also provide training data for constructing classifiers that section the rest of the unstructured abstracts lacking explicit section heading, which form a majority of the MEDLINE corpus.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) MEDLINE database / structured abstracts / information retrieval / text classification
Paper # AI2003-34
Date of Issue

Conference Information
Committee AI
Conference Date 2003/9/7(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 Artificial Intelligence and Knowledge-Based Processing (AI)
Language ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A MEDLINE document search system using section information
Sub Title (in English)
Keyword(1) MEDLINE database
Keyword(2) structured abstracts
Keyword(3) information retrieval
Keyword(4) text classification
1st Author's Name Takahiro YAMASAKI
1st Author's Affiliation Graduate School of Information Science Nara Institute of Science and Technology()
2nd Author's Name Masashi SHIMBO
2nd Author's Affiliation Graduate School of Information Science Nara Institute of Science and Technology
3rd Author's Name Yuji MATSUMOTO
3rd Author's Affiliation Graduate School of Information Science Nara Institute of Science and Technology
Date 2003/9/7
Paper # AI2003-34
Volume (vol) vol.103
Number (no) 304
Page pp.pp.-
#Pages 6
Date of Issue