Positioning for Conceptual Development
using Latent Semantic Analysis

Fridolin Wild; Bernhard Hoisl; Gaston Burek

Positioning for Conceptual Development using Latent Semantic Analysis

Fridolin Wild, Bernhard Hoisl, Gaston Burek

Institute for Complex Networks

Publication: Chapter in book/Conference proceeding › Contribution to conference proceedings

Abstract

With increasing opportunities to learn online, the problem of positioning learners in an educational network of content offers new possibilities for the utilisation of geometry-based natural language processing techniques.
In this article, the adoption of latent semantic analysis (LSA) for guiding learners in their conceptual development is investigated. We propose five new algorithmic derivations of LSA and test their validity for positioning in an experiment in order to draw back conclusions on the suitability of machine learning from previously accredited evidence. Special attention is thereby directed towards the role of distractors and the calculation of thresholds when using similarities as a proxy for assessing conceptual closeness.
Results indicate that learning improves positioning. Distractors are of low value and seem to be replaceable by generic noise to improve threshold calculation. Furthermore, new ways to flexibly calculate thresholds could be identified.

Original language	English
Title of host publication	Proceedings of the EACL Workshop on GEMS: Geometrical Models of Natural Language Semantics
Editors	R. Basili and M. Pennacchiotti
Place of Publication	Athens
Publisher	Association for Computational Linguistics
Pages	41 - 48
Publication status	Published - 1 Sept 2009

Austrian Classification of Fields of Science and Technology (ÖFOS)

102
101029 Mathematical statistics
102009 Computer simulation
602011 Computational linguistics

Check availability

University Library Catalogue

Cite this

@inproceedings{3443052b7edb4777a1e80c28eedf2f65,

title = "Positioning for Conceptual Development using Latent Semantic Analysis",

abstract = "With increasing opportunities to learn online, the problem of positioning learners in an educational network of content offers new possibilities for the utilisation of geometry-based natural language processing techniques. In this article, the adoption of latent semantic analysis (LSA) for guiding learners in their conceptual development is investigated. We propose five new algorithmic derivations of LSA and test their validity for positioning in an experiment in order to draw back conclusions on the suitability of machine learning from previously accredited evidence. Special attention is thereby directed towards the role of distractors and the calculation of thresholds when using similarities as a proxy for assessing conceptual closeness. Results indicate that learning improves positioning. Distractors are of low value and seem to be replaceable by generic noise to improve threshold calculation. Furthermore, new ways to flexibly calculate thresholds could be identified.",

author = "Fridolin Wild and Bernhard Hoisl and Gaston Burek",

year = "2009",

month = sep,

day = "1",

language = "English",

pages = "41 -- 48",

editor = "{R. Basili and M. Pennacchiotti}",

booktitle = "Proceedings of the EACL Workshop on GEMS: Geometrical Models of Natural Language Semantics",

publisher = "Association for Computational Linguistics",

}

Positioning for Conceptual Development using Latent Semantic Analysis. / Wild, Fridolin; Hoisl, Bernhard; Burek, Gaston.
Proceedings of the EACL Workshop on GEMS: Geometrical Models of Natural Language Semantics. ed. / R. Basili and M. Pennacchiotti. Athens: Association for Computational Linguistics, 2009. p. 41 - 48.

Publication: Chapter in book/Conference proceeding › Contribution to conference proceedings

TY - GEN

T1 - Positioning for Conceptual Development using Latent Semantic Analysis

AU - Wild, Fridolin

AU - Hoisl, Bernhard

AU - Burek, Gaston

PY - 2009/9/1

Y1 - 2009/9/1

N2 - With increasing opportunities to learn online, the problem of positioning learners in an educational network of content offers new possibilities for the utilisation of geometry-based natural language processing techniques. In this article, the adoption of latent semantic analysis (LSA) for guiding learners in their conceptual development is investigated. We propose five new algorithmic derivations of LSA and test their validity for positioning in an experiment in order to draw back conclusions on the suitability of machine learning from previously accredited evidence. Special attention is thereby directed towards the role of distractors and the calculation of thresholds when using similarities as a proxy for assessing conceptual closeness. Results indicate that learning improves positioning. Distractors are of low value and seem to be replaceable by generic noise to improve threshold calculation. Furthermore, new ways to flexibly calculate thresholds could be identified.

AB - With increasing opportunities to learn online, the problem of positioning learners in an educational network of content offers new possibilities for the utilisation of geometry-based natural language processing techniques. In this article, the adoption of latent semantic analysis (LSA) for guiding learners in their conceptual development is investigated. We propose five new algorithmic derivations of LSA and test their validity for positioning in an experiment in order to draw back conclusions on the suitability of machine learning from previously accredited evidence. Special attention is thereby directed towards the role of distractors and the calculation of thresholds when using similarities as a proxy for assessing conceptual closeness. Results indicate that learning improves positioning. Distractors are of low value and seem to be replaceable by generic noise to improve threshold calculation. Furthermore, new ways to flexibly calculate thresholds could be identified.

UR - http://www.aclweb.org/anthology/W/W09/W09-0206.pdf

M3 - Contribution to conference proceedings

SP - 41

EP - 48

BT - Proceedings of the EACL Workshop on GEMS: Geometrical Models of Natural Language Semantics

A2 - R. Basili and M. Pennacchiotti, null

PB - Association for Computational Linguistics

CY - Athens

ER -

Positioning for Conceptual Development using Latent Semantic Analysis

Abstract

Austrian Classification of Fields of Science and Technology (ÖFOS)

Check availability

Other files and links

Language Technologies for Lifelong Learning

Cite this

Positioning for Conceptual Development using Latent Semantic Analysis

Abstract

Austrian Classification of Fields of Science and Technology (ÖFOS)

Check availability

Other files and links

Projects

Language Technologies for Lifelong Learning

Cite this