Presentation 2003/3/8
系列パターンを素性とした論文概要文の自動分類(<特集> 「アクティブマイニング」及び一般 : 文部科学省科学研究費特定領域研究「情報洪水時代におけるアクティブマイニングの実現」公開シンポジウム)
Takahiro YAMASAKI, Masashi SHIMBO, Yuji MATSUMOTO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We explore the use of (possibly non-contiguous) word sequence patterns as the features in the task of automatically classifying sentences in the MEDLINE abstracts. In this task, the categories to which the sentences are classified are determined not by their topics, but in accordance with the typical subsections in the abstracts; i.e., Background, Objectives, Conclusions, etc. The bag-of-words representation commonly used in text categorization is inadequate for this particular task, as the turns of phrase or expression characterize the categories better than the individual content words. An improvement of 3 to 11 points in terms of F-measure was observed when the sequential patterns mined with the PrefixSpan algorithm were used in addition to the bag-of-word features.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Text Categorization / Feature Selection / Sequential Pattern / MEDLINE Abstracts
Paper # AI2002-83
Date of Issue

Conference Information
Committee AI
Conference Date 2003/3/8(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 JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English)
Sub Title (in English)
Keyword(1) Text Categorization
Keyword(2) Feature Selection
Keyword(3) Sequential Pattern
Keyword(4) MEDLINE Abstracts
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 2003/3/8
Paper # AI2002-83
Volume (vol) vol.102
Number (no) 711
Page pp.pp.-
#Pages 6
Date of Issue