A machine learning approach to the classification of technical abstracts in a two-level ontology

ePubs

The open archive for STFC research publications

DOI	10.5286/raltr.2017004
Persistent URL	http://purl.org/net/epubs/work/32874726
Record Status	Checked
Record Id	32874726
Title	A machine learning approach to the classification of technical abstracts in a two-level ontology
Contributors	E Tattershall (STFC Rutherford Appleton Lab.), E Yang (STFC Rutherford Appleton Lab.)
Abstract	This paper describes an approach to multi-label hierarchical document classification on an open- source corpus of 30,000 grant proposals. After text cleaning and feature extraction, an array of linear classifiers are trained and evaluated with a number of metrics, and found to classify unseen documents into 34 categories with a precision of 80%
Organisation	STFC , SCI-COMP
Keywords
Funding Information
Related Research Object(s):
Licence Information:	Creative Commons Attribution 3.0 Unported (CC BY 3.0)
Language	English (EN)

Type	Details	URI(s)	Local file(s)	Year
Report	RAL Technical Reports RAL-TR-2017-004. 2017.		RAL-TR-2017-004.pdf	2017