| Author | Title | Year | Journal/Proceedings | Reftype | DOI/URL |
|---|---|---|---|---|---|
| Mohammad, S. & Hirst, G. | Distributional measures as proxies for semantic relatedness [BibTeX] |
Submitted for publication | article | URL | |
BibTeX:
@article{mohammadSubmittedDistributional,
author = {Mohammad, Saif and Hirst, Graeme},
title = {Distributional measures as proxies for semantic relatedness},
year = {Submitted for publication},
url = {http://ftp.cs.toronto.edu/pub/gh/Mohammad+Hirst-2005.pdf}
}
|
|||||
| Poelmans, J., Ignatov, D., Viaene, S., Dedene, G. & Kuznetsov, S. | Text Mining Scientific Papers: A Survey on FCA-Based Information Retrieval Research | 2012 | Advances in Data Mining. Applications and Theoretical Aspects | incollection | DOIURL |
| Abstract: Formal Concept Analysis (FCA) is an unsupervised clustering technique and many scientific papers are devoted to applying FCA in Information Retrieval (IR) research. We collected 103 papers published between 2003-2009 which mention FCA and information retrieval in the abstract, title or keywords. Using a prototype of our FCA-based toolset CORDIET, we converted the pdf-files containing the papers to plain text, indexed them with Lucene using a thesaurus containing terms related to FCA research and then created the concept lattice shown in this paper. We visualized, analyzed and explored the literature with concept lattices and discovered multiple interesting research streams in IR of which we give an extensive overview. The core contributions of this paper are the innovative application of FCA to the text mining of scientific papers and the survey of the FCA-based IR research. | |||||
BibTeX:
@incollection{noKey,
author = {Poelmans, Jonas and Ignatov, DmitryI. and Viaene, Stijn and Dedene, Guido and Kuznetsov, SergeiO.},
title = {Text Mining Scientific Papers: A Survey on FCA-Based Information Retrieval Research},
booktitle = {Advances in Data Mining. Applications and Theoretical Aspects},
publisher = {Springer Berlin Heidelberg},
year = {2012},
volume = {7377},
pages = {273-287},
url = {http://dx.doi.org/10.1007/978-3-642-31488-9_22},
doi = {http://dx.doi.org/10.1007/978-3-642-31488-9_22}
}
|
|||||
| Illig, J. | Machine Learnability Analysis of Textclassifications in a Social Bookmarking Folksonomy [BibTeX] |
2008 | School: University of Kassel | mastersthesis | |
BibTeX:
@mastersthesis{illig2008machine,
author = {Illig, Jens},
title = {Machine Learnability Analysis of Textclassifications in a Social Bookmarking Folksonomy},
school = {University of Kassel},
year = {2008}
}
|
|||||
| Cimiano, P., Hotho, A. & Staab, S. | Learning Concept Hierarchies from Text Corpora using Formal Concept Analysis [BibTeX] |
2005 | Journal on Artificial Intelligence Research | article | URL |
BibTeX:
@article{cimiano05learning,
author = {Cimiano, Philipp and Hotho, Andreas and Staab, Steffen},
title = {Learning Concept Hierarchies from Text Corpora using Formal Concept Analysis},
journal = {Journal on Artificial Intelligence Research},
year = {2005},
volume = {24},
pages = {305-339},
url = {http://dblp.uni-trier.de/db/journals/jair/jair24.html#CimianoHS05}
}
|
|||||
| Hotho, A., Staab, S. & Stumme, G. | Wordnet improves text document clustering [BibTeX] |
2003 | Proc. SIGIR Semantic Web Workshop | inproceedings | URL |
BibTeX:
@inproceedings{hotho03wordnet,
author = {Hotho, A and Staab, S. and Stumme, G.},
title = {Wordnet improves text document clustering},
booktitle = {Proc. SIGIR Semantic Web Workshop},
year = {2003},
url = {http://www.kde.cs.uni-kassel.de/stumme/papers/2003/hotho2003wordnet.pdf}
}
|
|||||
| Hotho, A., Staab, S. & Stumme, G. | Explaining Text Clustering Results using Semantic Structures | 2003 | Knowledge Discovery in Databases: PKDD 2003, 7th European Conference on Principles and Practice of Knowledge Discovery in Databases | inproceedings | URL |
| Abstract: Common text clustering techniques offer rather poor capabilities
r explaining to their users why a particular result has been hieved. They have the disadvantage that they do not relate mantically nearby terms and that they cannot explain how sulting clusters are related to each other. n this paper, we discuss a way of integrating a large thesaurus nd the computation of lattices of resulting clusters into common text clustering n order to overcome these two problems. its major result, our approach achieves an explanation using an propriate level of granularity at the concept level as well as appropriate size and complexity of the explaining lattice of sulting clusters. |
|||||
BibTeX:
@inproceedings{hotho03explaining,
author = {Hotho, Andreas and Staab, Steffen and Stumme, Gerd},
title = {Explaining Text Clustering Results using Semantic Structures},
booktitle = {Knowledge Discovery in Databases: PKDD 2003, 7th European Conference on Principles and Practice of Knowledge Discovery in Databases},
publisher = {Springer},
year = {2003},
volume = {2838},
pages = {217-228},
url = {http://www.kde.cs.uni-kassel.de/stumme/papers/2003/hotho2003explaining.pdf}
}
|
|||||
| Hotho, A., Staab, S. & Stumme, G. | Ontologies improve text document clustering [BibTeX] |
2003 | Proceedings of the 2003 IEEE International Conference on Data Mining | inproceedings | URL |
BibTeX:
@inproceedings{hotho03ontologies,
author = {Hotho, Andreas and Staab, Steffen and Stumme, Gerd},
title = {Ontologies improve text document clustering},
booktitle = {Proceedings of the 2003 IEEE International Conference on Data Mining},
publisher = {IEEE {C}omputer {S}ociety},
year = {2003},
pages = {541-544 (Poster},
url = {http://www.kde.cs.uni-kassel.de/stumme/papers/2003/hotho2003ontologies.pdf}
}
|
|||||
| Hotho, A., Staab, S. & Stumme, G. | Text Clustering Based on Background Knowledge | 2003 | techreport | URL | |
| Abstract: Text document clustering plays an important role in providing intuitive
vigation and browsing mechanisms by organizing large amounts of information to a small number of meaningful clusters. Standard partitional or agglomerative ustering methods efficiently compute results to this end. wever, the bag of words representation used for these clustering methods is often satisfactory as it ignores relationships between important terms that do not -occur literally. Also, it is mostly left to the user to find out why a particular partitioning s been achieved, because it is only specified extensionally. In order to al with the two problems, we integrate background knowledge into the process of ustering text documents. rst, we preprocess the texts, enriching their representations by background knowledge ovided in a core ontology — in our application Wordnet. Then, we cluster e documents by a partitional algorithm. Our experimental evaluation on Reuters wsfeeds compares clustering results with pre-categorizations of news. In the experiments, provements of results by background knowledge compared to the baseline n be shown for many interesting tasks. cond, the clustering partitions the large number of documents to a relatively small mber of clusters, which may then be analyzed by conceptual clustering. In our approach, applied Formal Concept Analysis. Conceptual clustering techniques are own to be too slow for directly clustering several hundreds of documents, but they ve an intensional account of cluster results. They allow for a concise description commonalities and distinctions of different clusters. With background knowledge ey even find abstractions like “food” (vs. specializations like “beef” or “corn”). us, in our approach, partitional clustering reduces first the size of the problem ch that it becomes tractable for conceptual clustering, which then facilitates the derstanding of the results. |
|||||
BibTeX:
@techreport{hotho03textclustering,
author = {Hotho, Andreas and Staab, Steffen and Stumme, Gerd},
title = {Text Clustering Based on Background Knowledge},
year = {2003},
volume = {425},
url = {http://www.kde.cs.uni-kassel.de/stumme/papers/2003/hotho2003text.pdf}
}
|
|||||
| Hotho, A. & Stumme, G. | Conceptual Clustering of Text Clusters [BibTeX] |
2002 | Proc. Fachgruppentreffen Maschinelles Lernen (FGML 2002) | inproceedings | URL |
BibTeX:
@inproceedings{hotho02conceptualclustering,
author = {Hotho, A. and Stumme, G.},
title = {Conceptual Clustering of Text Clusters},
booktitle = {Proc. Fachgruppentreffen Maschinelles Lernen (FGML 2002)},
year = {2002},
pages = {37-45},
url = {http://www.kde.cs.uni-kassel.de/stumme/papers/2002/FGML02.pdf}
}
|
|||||
Created by JabRef export filters on 05/05/2024 by the social publication management platform PUMA