@article{DBLP:journals/jise/YangK13, author = {Yang, Wen-Teng and Kao, Hung-Yu}, bibsource = {DBLP, http://dblp.uni-trier.de}, ee = {http://www.iis.sinica.edu.tw/page/jise/2013/201307_01.html}, interhash = {1c27ed73a081f71136c5d58067127342}, intrahash = {aec1722879a25d5eb2ee9035803d9218}, journal = {J. Inf. Sci. Eng.}, number = 4, pages = {615-630}, title = {Measuring Semantic Relatedness using Wikipedia Signed Network}, volume = 29, year = 2013 } @inproceedings{Yeh:2009:WRW:1708124.1708133, abstract = {Computing semantic relatedness of natural language texts is a key component of tasks such as information retrieval and summarization, and often depends on knowledge of a broad range of real-world concepts and relationships. We address this knowledge integration issue by computing semantic relatedness using personalized PageRank (random walks) on a graph derived from Wikipedia. This paper evaluates methods for building the graph, including link selection strategies, and two methods for representing input texts as distributions over the graph nodes: one based on a dictionary lookup, the other based on Explicit Semantic Analysis. We evaluate our techniques on standard word relatedness and text similarity datasets, finding that they capture similarity information complementary to existing Wikipedia-based relatedness measures, resulting in small improvements on a state-of-the-art measure.}, acmid = {1708133}, address = {Stroudsburg, PA, USA}, author = {Yeh, Eric and Ramage, Daniel and Manning, Christopher D. and Agirre, Eneko and Soroa, Aitor}, booktitle = {Proceedings of the 2009 Workshop on Graph-based Methods for Natural Language Processing}, interhash = {8b28cd800b6ad3929eef3b45de997e51}, intrahash = {ffd20a7357ca8e87d46e516589a7769e}, isbn = {978-1-932432-54-1}, location = {Suntec, Singapore}, numpages = {9}, pages = {41--49}, publisher = {Association for Computational Linguistics}, series = {TextGraphs-4}, title = {WikiWalk: random walks on Wikipedia for semantic relatedness}, url = {http://dl.acm.org/citation.cfm?id=1708124.1708133}, year = 2009 } @inproceedings{West2009, abstract = {Computing the semantic distance between realworld concepts is crucial for many intelligent applications. We present a novel method that leverages data from 'Wikispeedia', an online game played on Wikipedia; players have to reach an article from another, unrelated article, only by clicking links in the articles encountered. In order to automatically infer semantic distances between everyday concepts, our method effectively extracts the common sense displayed by humans during play, and is thus more desirable, from a cognitive point of view, than purely corpus-based methods. We show that our method significantly outperforms Latent Semantic Analysis in a psychometric evaluation of the quality of learned semantic distances.}, acmid = {1661702}, address = {San Francisco, CA, USA}, author = {West, Robert and Pineau, Joelle and Precup, Doina}, booktitle = {Proceedings of the 21st international jont conference on Artifical intelligence}, interhash = {fc6cba2420ca9c6d0b82f602a07255cd}, intrahash = {650cbc558eb7dedff546cdc16033707e}, location = {Pasadena, California, USA}, numpages = {6}, pages = {1598--1603}, publisher = {Morgan Kaufmann Publishers Inc.}, series = {IJCAI'09}, title = {Wikispeedia: an online game for inferring semantic distances between concepts}, url = {http://dl.acm.org/citation.cfm?id=1661445.1661702}, year = 2009 } @inproceedings{conf/sigir/HuFCZLYC08, author = {Hu, Jian and Fang, Lujun and Cao, Yang and Zeng, Hua-Jun and Li, Hua and Yang, Qiang and Chen, Zheng}, booktitle = {SIGIR}, crossref = {conf/sigir/2008}, date = {2008-07-27}, editor = {Myaeng, Sung-Hyon and Oard, Douglas W. and Sebastiani, Fabrizio and Chua, Tat-Seng and Leong, Mun-Kew}, ee = {http://doi.acm.org/10.1145/1390334.1390367}, interhash = {0a2878165034dcdfacb9045608ec482a}, intrahash = {76f863a12c0b983ec67682deaec1ada4}, isbn = {978-1-60558-164-4}, pages = {179-186}, publisher = {ACM}, title = {Enhancing text clustering by leveraging Wikipedia semantics.}, url = {http://dblp.uni-trier.de/db/conf/sigir/sigir2008.html#HuFCZLYC08}, year = 2008 } @inproceedings{conf/pakdd/HuangMFW09, author = {Huang, Anna and Milne, David N. and Frank, Eibe and Witten, Ian H.}, booktitle = {PAKDD}, crossref = {conf/pakdd/2009}, date = {2009-04-25}, editor = {Theeramunkong, Thanaruk and Kijsirikul, Boonserm and Cercone, Nick and Ho, Tu Bao}, ee = {http://dx.doi.org/10.1007/978-3-642-01307-2_62}, interhash = {b2ea40479e6537693a659a4342892fee}, intrahash = {63d65d3bd978e39f33f39222be9a3f76}, isbn = {978-3-642-01306-5}, pages = {628-636}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, title = {Clustering Documents Using a Wikipedia-Based Concept Representation.}, url = {http://dblp.uni-trier.de/db/conf/pakdd/pakdd2009.html#HuangMFW09}, volume = 5476, year = 2009 } @inproceedings{conf/aaai/StrubeP06, author = {Strube, Michael and Ponzetto, Simone Paolo}, booktitle = {AAAI}, crossref = {conf/aaai/2006}, date = {2006-07-13}, interhash = {a09d5123ab9ab8cb00b8df6f0a7f5c81}, intrahash = {9216a46b593c3319aa23d13ca8373beb}, publisher = {AAAI Press}, title = {WikiRelate! Computing Semantic Relatedness Using Wikipedia.}, url = {http://www.dit.unitn.it/~p2p/RelatedWork/Matching/aaai06.pdf}, year = 2006 } @inproceedings{5273871, abstract = {This paper introduces WikiOnto: a system that assists in the extraction and modeling of topic ontologies in a semi-automatic manner using a preprocessed document corpus derived from Wikipedia. Based on the Wikipedia XML Corpus, we present a three-tiered framework for extracting topic ontologies in quick time and a modeling environment to refine these ontologies. Using natural language processing (NLP) and other machine learning (ML) techniques along with a very rich document corpus, this system proposes a solution to a task that is generally considered extremely cumbersome. The initial results of the prototype suggest strong potential of the system to become highly successful in ontology extraction and modeling and also inspire further research on extracting ontologies from other semi-structured document corpora as well.}, author = {Silva, L. De and Jayaratne, L.}, booktitle = {Applications of Digital Information and Web Technologies, 2009. ICADIWT '09. Second International Conference on the}, doi = {10.1109/ICADIWT.2009.5273871}, interhash = {c1996cb9e69de56e2bb2f8e763fe0482}, intrahash = {66bec053541e521fbe68c0119806ae49}, month = {Aug.}, pages = {446-451}, title = {Semi-automatic extraction and modeling of ontologies using Wikipedia XML Corpus}, url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?isnumber=5273826&arnumber=5273871&count=156&index=116}, year = 2009 } @article{1356291, address = {Inderscience Publishers, Geneva, SWITZERLAND}, author = {Meyer, M. and Rensing, C. and Steinmetz, R.}, doi = {http://dx.doi.org/10.1504/IJAMC.2008.016758}, interhash = {ef644e35df4c37fb1057330ffe09faf8}, intrahash = {185c6aed86c00188b23c0ca1c83c4e90}, issn = {1462-4613}, journal = {Int. J. Adv. Media Commun.}, number = 1, pages = {59--72}, publisher = {Inderscience Publishers}, title = {Using community & generated contents as a substitute corpus for metadata generation}, url = {http://portal.acm.org/citation.cfm?id=1356291}, volume = 2, year = 2008 } @misc{Medelyan2008, abstract = { Wikipedia is a goldmine of information; not just for its many readers, but also for the growing community of researchers who recognize it as a resource of exceptional scale and utility. It represents a vast investment of manual effort and judgment: a huge, constantly evolving tapestry of concepts and relations that is being applied to a host of tasks. This article provides a comprehensive description of this work. It focuses on research that extracts and makes use of the concepts, relations, facts and descriptions found in Wikipedia, and organizes the work into four broad categories: applying Wikipedia to natural language processing; using it to facilitate information retrieval and information extraction; and as a resource for ontology building. The article addresses how Wikipedia is being used as is, how it is being improved and adapted, and how it is being combined with other structures to create entirely new resources. We identify the research groups and individuals involved, and how their work has developed in the last few years. We provide a comprehensive list of the open-source software they have produced. We also discuss the implications of this work for the long-awaited semantic web. }, author = {Medelyan, Olena and Legg, Catherine and Milne, David and Witten, Ian H.}, interhash = {6614c7cd27d80abd691b2ef463941d1c}, intrahash = {0e7499a4f087f74ad0be674047cf315d}, note = {cite arxiv:0809.4530 Comment: An extensive survey of re-using information in Wikipedia in natural language processing, information retreival and extraction and ontology building. submitted}, title = {Mining Meaning from Wikipedia}, url = {http://arxiv.org/abs/0809.4530}, year = 2008 } @inproceedings{PuWang:2007, abstract = {The exponential growth of text documents available on the Internet has created an urgent need for accurate, fast, and general purpose text classification algorithms. However, the "bag of words" representation used for these classification methods is often unsatisfactory as it ignores relationships between important terms that do not co-occur literally. In order to deal with this problem, we integrate background knowledge - in our application: Wikipedia - into the process of classifying text documents. The experimental evaluation on Reuters newsfeeds and several other corpus shows that our classification results with encyclopedia knowledge are much better than the baseline "bag of words " methods.}, author = {Wang, Pu and Hu, Jian and Zeng, Hua-Jun and Chen, Lijun and Chen, Zheng}, booktitle = {Data Mining, 2007. ICDM 2007. Seventh IEEE International Conference on}, doi = {10.1109/ICDM.2007.77}, interhash = {8a899b60047e20e162fc12b2ff6f8142}, intrahash = {66058efbca5abd1222f72c32365d23fa}, isbn = {978-0-7695-3018-5}, issn = {1550-4786}, pages = {332-341}, title = {Improving Text Classification by Using Encyclopedia Knowledge}, url = {ftp://ftp.computer.org/press/outgoing/proceedings/icdm07/Data/3018a332.pdf}, year = 2007 } @article{journals/corr/abs-physics-0602026, author = {Capocci, Andrea and Servedio, Vito Domenico Pietro and Colaiori, Francesca and Buriol, Luciana S. and Donato, Debora and Leonardi, Stefano and Caldarelli, Guido}, date = {2008-01-02}, ee = {http://arxiv.org/abs/physics/0602026}, interhash = {88bf1242c692479acc414f633c4bab44}, intrahash = {3c16ad257c21304d02f1d108571d9c8c}, journal = {CoRR}, note = {informal publication}, title = {Preferential attachment in the growth of social networks: the case of Wikipedia}, url = {http://dblp.uni-trier.de/db/journals/corr/corr0602.html#abs-physics-0602026}, volume = {abs/physics/0602026}, year = 2006 } @article{1551, abstract = {Wikipedia is the world's largest collaboratively edited source of encyclopaedic knowledge. But in spite of its utility, its content is barely machine-interpretable and only weakly structured. With Semantic MediaWiki we provide an extension that enables wiki-users to semantically annotate wiki pages, based on which the wiki contents can be browsed, searched, and reused in novel ways. In this paper, we give an extended overview of Semantic MediaWiki and discuss experiences regarding performance and current applications.}, author = {Krötzsch, Markus and Vrandecic, Denny and Völkel, Max and Haller, Heiko and Studer, Rudi}, interhash = {7957ab402fcb10d64e148f499deacba4}, intrahash = {03d24fef49e40d9dec474d04d0b27000}, journal = {Journal of Web Semantics}, month = DEC, note = {To appear.}, title = {Semantic Wikipedia}, url = {http://korrekt.org/papers/KroetzschVrandecicVoelkelHaller_SemanticMediaWiki_2007.pdf}, year = 2007 } @misc{text2006Mehler, author = {Mehler, A.}, booktitle = {Proceedings of the EACL 2006 Workshop on New Text-Wikis and blogs and other dynamic text sources}, date = {(2006):April 3-7}, editor = {Jussi, Karlgren}, interhash = {7b7bd4573d9d121dccb5a489084e06d7}, intrahash = {be8f323d6ff541a4f6355f8dce8b5790}, location = {Trento, Italy}, pages = {1-8}, title = {Text Linkage in the Wiki Medium-A comparative study}, url = {http://www.sics.se/jussi/newtext/working_notes/01_mehler.pdf}, year = 2006 } @inproceedings{bunescu-etal-2006, author = {Bunescu, Razvan and Pasca, Marius}, booktitle = {Proceedings of the 11th Conference of the European Chapter of the Association for Computational Linguistics (EACL-06), Trento, Italy}, interhash = {f1e2bfaf83e0af0d90b42c8f70394fa4}, intrahash = {cc98e8aa7e3fb7d8addc0ec4fe45f7d2}, month = {April}, pages = {9-16}, title = {Using Encyclopedic Knowledge for Named Entity Disambiguation }, url = {http://www.cs.utexas.edu/~ml/publication/paper.cgi?paper=encyc-eacl-06.ps.gz}, year = 2006 } @article{wikipediaxml:2005, author = {Denoyer, Ludovic and Gallinari, Patrick}, interhash = {0e9b9afb15804d3e625d73ada85900b1}, intrahash = {493b849942fcaf9ba8e8e68e3cb46d38}, journal = {SIGIR Forum}, title = {{T}he {W}ikipedia {X}{M}{L} {C}orpus}, url = {http://www-connex.lip6.fr/~denoyer/wikipediaXML/}, year = 2006 }