2013
DOI: 10.29173/cais250
|View full text |Cite
|
Sign up to set email alerts
|

A Method for Comparing Large Scale Inter-indexer Consistency Using IR Modeling

Abstract: The authors present a method for comparing indexing consistency between groups of indexers based on the vector space IR model. Terms assigned by indexers are treated as vectors whose distances from a central vector may be compared. The method is outlined and demonstrated with an example.Résumé : Les auteurs présentent un modèle pour comparer la cohérence interindexeurs entre des groupes d'indexeurs basé sur le modèle de RI d'espace vectoriel. Les termes attribués par les indexeurs sont traités comme des vecteu… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
11
0

Year Published

2014
2014
2014
2014

Publication Types

Select...
5

Relationship

0
5

Authors

Journals

citations
Cited by 6 publications
(11 citation statements)
references
References 15 publications
0
11
0
Order By: Relevance
“…The three‐dimensional space may be extended to n dimensions when n different index terms are present. Wolfram and Olson () applied the concept of document space in the VSM to the terms assigned by a group of indexers to a document, and defined an indexer/tagger Space. Wolfram and Olson proposed a method, the inter‐indexer consistency density (ICD), by calculating the distance between each indexer/tagger's resulting vector and the indexing centroid (or average vector across all indexers/taggers).…”
Section: Assessment Of Tagging Quality: Methodsmentioning
confidence: 99%
See 4 more Smart Citations
“…The three‐dimensional space may be extended to n dimensions when n different index terms are present. Wolfram and Olson () applied the concept of document space in the VSM to the terms assigned by a group of indexers to a document, and defined an indexer/tagger Space. Wolfram and Olson proposed a method, the inter‐indexer consistency density (ICD), by calculating the distance between each indexer/tagger's resulting vector and the indexing centroid (or average vector across all indexers/taggers).…”
Section: Assessment Of Tagging Quality: Methodsmentioning
confidence: 99%
“…Wolfram and Olson ()'s inter‐indexer (tagger) consistency density (ICD) is calculated as follows: I C D = i = 1 m s i m ( I i , C ) m …”
Section: Assessment Of Tagging Quality: Methodsmentioning
confidence: 99%
See 3 more Smart Citations