https://wiki.sarg.dev/index.php?action=history&feed=atom&title=Topic-based_vector_space_modelTopic-based vector space model - Revision history2026-04-19T05:48:19ZRevision history for this page on the wikiMediaWiki 1.44.2https://wiki.sarg.dev/index.php?title=Topic-based_vector_space_model&diff=720305&oldid=previmported>Bender the Bot: /* Implementations */ HTTP to HTTPS for SourceForge2025-08-11T03:53:37Z<p><span class="autocomment">Implementations: </span> HTTP to HTTPS for <a href="/index.php/SourceForge" title="SourceForge">SourceForge</a></p>
<p><b>New page</b></p><div>The '''Topic-based Vector Space Model (TVSM)'''<ref>{{citation | url=http://www.kuropka.net/files/TVSM.pdf | title=Topic-based Vector Space Model | author1=Dominik Kuropka | author2=Jörg Becker | year=2003}}</ref> (literature: [http://www.logos-verlag.de/cgi-bin/engbuchmid?isbn=0514&lng=eng&id=]) extends the [[vector space model]] of [[information retrieval]] by removing the constraint that the term-vectors be orthogonal. The assumption of orthogonal terms is incorrect regarding natural languages which causes problems with synonyms and strong related terms. This facilitates the use of stopword lists, stemming and thesaurus in TVSM.<br />
In contrast to the [[generalized vector space model]] the TVSM does not depend on concurrence-based similarities between terms. <br />
<br />
==Definitions==<br />
The basic premise of TVSM is the existence of a ''d'' dimensional space ''R'' with only positive axis intercepts, i.e. ''R in R<sup>+</sup>'' and ''d in N<sup>+</sup>''. Each dimension of ''R'' represents a fundamental topic. A term vector ''t'' has a specific weight for a certain ''R''. To calculate these weights assumptions are made taking into account the document contents. Ideally important terms will have a high weight and stopwords and irrelevants terms to the topic will have a low weight. The TVSM document model is obtained as a sum of term vectors representing terms in the document. The similarity between two documents ''Di'' and ''Dj'' is defined as the scalar product of document vectors.<br />
<br />
==Enhanced Topic-based Vector Space Model==<br />
The enhancement of the Enhanced Topic-based Vector Space Model (eTVSM)<ref>{{citation | url= http://kuropka.net/files/HPI_Evaluation_of_eTVSM.pdf | author1=Dominik Kuropka | author2=Artem Polyvyanyy | title=A Quantitative Evaluation of the Enhanced Topic-Based Vector Space Model | year=2007}}</ref> (literature: [http://www.logos-verlag.de/cgi-bin/engbuchmid?isbn=0514&lng=eng&id=]) is a proposal on how to derive term vectors from an [[Ontology_(information_science) | Ontology]]. Using a synonym Ontology created from [[WordNet]] Kuropka shows good results for document similarity. If a trivial Ontology is used the results are similar to Vector Space model.<br />
<br />
==Implementations==<br />
* [https://sourceforge.net/projects/etvsm/ Implementation of eTVSM in python]<br />
<br />
== References ==<br />
{{reflist}}<br />
<br />
[[Category:Vector space model]]</div>imported>Bender the Bot