Metadata Extraction with Cue Model

被引：0

作者：

Isa, Wan Malini Wan ^{[1
]}

Hamid, Jamaliah Abdul

Ibrahim, Hamidah ^{[1
]}

Abdullah, Rusli ^{[1
]}

Selamat, Mohd. Hasan ^{[1
]}

Abdullah, Muhamad Taufik ^{[1
]}

Nasharuddin, Nurul Amelina ^{[1
]}

机构：

[1] Univ Putra Malaysia, Fac Comp Sci & Informat Technol, Upm Serdang 43400, Selangor, Malaysia

来源：

KMICE 2008 - KNOWLEDGE MANAGEMENT INTERNATIONAL CONFERENCE, 2008 - TRANSFERRING, MANAGING AND MAINTAINING KNOWLEDGE FOR NATION CAPACITY DEVELOPMENT | 2008年

关键词：

Metadata extraction; Cue Model; machine learning; rule based; template matching;

D O I：

暂无

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Metadata extraction from texts is important since it enables search for documents based on the metadata identified. It is impossible to retrieve journal articles without the metadata of documents, which includes information such as author, title, and journal publication details. This paper proposes a new technique to extract metadata of documents, called Metadata Extraction with Cue Model, which uses combinations of a few features to extract metadata automatically from documents. Automatic metadata extraction is increasingly important in today's influx of published material.

引用

页码：107 / 111

页数：5