@proceedings{DBLP:conf/semweb/2021, added-at = {2022-01-27T12:46:25.000+0100}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://www.bibsonomy.org/bibtex/2d8f94f524d2d0933ab091f4f1d2843a3/hotho}, doi = {10.1007/978-3-030-88361-4}, editor = {Hotho, Andreas and Blomqvist, Eva and Dietze, Stefan and Fokoue, Achille and Ding, Ying and Barnaghi, Payam M. and Haller, Armin and Dragoni, Mauro and Alani, Harith}, interhash = {fe3a5f7f92792ac1855d3327853302e6}, intrahash = {d8f94f524d2d0933ab091f4f1d2843a3}, isbn = {978-3-030-88360-7}, keywords = {2021 conference myown semantic web}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, timestamp = {2022-01-27T12:46:25.000+0100}, title = {The Semantic Web - {ISWC} 2021 - 20th International Semantic Web Conference, {ISWC} 2021, Virtual Event, October 24-28, 2021, Proceedings}, url = {https://doi.org/10.1007/978-3-030-88361-4}, volume = 12922, year = 2021 } @inproceedings{omeliyanenko2020lm4kg, abstract = {Language Models (LMs) and Knowledge Graphs (KGs) are both active research areas in Machine Learning and Semantic Web. While LMs have brought great improvements for many downstream tasks on their own, they are often combined with KGs providing additionally aggregated, well structured knowledge. Usually, this is done by leveraging KGs to improve LMs. But what happens if we turn this around and use LMs to improve KGs?}, added-at = {2021-01-24T18:31:20.000+0100}, address = {Cham}, author = {Omeliyanenko, Janna and Zehe, Albin and Hettinger, Lena and Hotho, Andreas}, biburl = {https://www.bibsonomy.org/bibtex/2f24522aac1d51bace861cd03d4fb7cf9/hotho}, booktitle = {The Semantic Web -- ISWC 2020}, description = {LM4KG: Improving Common Sense Knowledge Graphs with Language Models | SpringerLink}, editor = {Pan, Jeff Z. and Tamma, Valentina and d'Amato, Claudia and Janowicz, Krzysztof and Fu, Bo and Polleres, Axel and Seneviratne, Oshani and Kagal, Lalana}, interhash = {417fb85b2e86797f00438d569a1a3e46}, intrahash = {f24522aac1d51bace861cd03d4fb7cf9}, isbn = {978-3-030-62419-4}, keywords = {2020 graph kg knowledge language lm model myown nlp selected semantic}, pages = {456--473}, publisher = {Springer International Publishing}, timestamp = {2021-05-12T08:30:53.000+0200}, title = {LM4KG: Improving Common Sense Knowledge Graphs with Language Models}, url = {https://www.informatik.uni-wuerzburg.de/datascience/news/single/news/our-paper-lm4kg-improving-common-sense-knowledge-graphs-with-language-models-has-been-presented-a/}, year = 2020 } @article{journals/coling/BeltagyRCEM16, added-at = {2018-09-07T19:56:07.000+0200}, author = {Beltagy, Islam and Roller, Stephen and Cheng, Pengxiang and Erk, Katrin and Mooney, Raymond J.}, biburl = {https://www.bibsonomy.org/bibtex/27ebbf12ac7b76be7bc9188671122b5cb/hotho}, ee = {http://dx.doi.org/10.1162/COLI_a_00266}, interhash = {3d6859c02605afd86ec919f7c3cc4b0f}, intrahash = {7ebbf12ac7b76be7bc9188671122b5cb}, journal = {Computational Linguistics}, keywords = {logic semantic toread}, number = 4, pages = {763-808}, timestamp = {2018-09-07T19:56:07.000+0200}, title = {Representing Meaning with a Combination of Logical and Distributional Models.}, url = {http://dblp.uni-trier.de/db/journals/coling/coling42.html#BeltagyRCEM16}, volume = 42, year = 2016 } @inproceedings{hettinger2018semeval, added-at = {2018-06-30T11:15:17.000+0200}, address = {New Orleans, LA, USA}, author = {Hettinger, Lena and Dallmann, Alexander and Zehe, Albin and Niebler, Thomas and Hotho, Andreas}, biburl = {https://www.bibsonomy.org/bibtex/26c725d01df9bfe964ad30b0c087737c4/hotho}, booktitle = {Proceedings of International Workshop on Semantic Evaluation (SemEval-2018)}, interhash = {d4b56c2236530cc866ebbe7ef576524a}, intrahash = {6c725d01df9bfe964ad30b0c087737c4}, keywords = {2018 classification embeddings myown relation scientific semantic senegal w2v word}, timestamp = {2018-06-30T11:15:17.000+0200}, title = {ClaiRE at SemEval-2018 Task 7: Classification of Relations using Embeddings}, year = 2018 } @article{biancalana2013social, added-at = {2017-12-17T16:49:16.000+0100}, author = {Biancalana, Claudio and Gasparetti, Fabio and Micarelli, Alessandro and Sansonetti, Giuseppe}, biburl = {https://www.bibsonomy.org/bibtex/2f3a42df03c463d396fd67cd7103d8f22/hotho}, interhash = {a36ec8d0de87cbe6394bab401f87eb0a}, intrahash = {f3a42df03c463d396fd67cd7103d8f22}, journal = {ACM Transactions on Intelligent Systems and Technology (TIST)}, keywords = {semantic query expansion search citedby:scholar:count:100 citedby:scholar:timestamp:2017-12-17}, number = 4, pages = 60, publisher = {ACM}, timestamp = {2017-12-17T16:49:16.000+0100}, title = {Social semantic query expansion}, volume = 4, year = 2013 } @inbook{Baier2017, abstract = {Structured scene descriptions of images are useful for the automatic processing and querying of large image databases. We show how the combination of a statistical semantic model and a visual model can improve on the task of mapping images to their associated scene description. In this paper we consider scene descriptions which are represented as a set of triples (subject, predicate, object), where each triple consists of a pair of visual objects, which appear in the image, and the relationship between them (e.g. man-riding-elephant, man-wearing-hat). We combine a standard visual model for object detection, based on convolutional neural networks, with a latent variable model for link prediction. We apply multiple state-of-the-art link prediction methods and compare their capability for visual relationship detection. One of the main advantages of link prediction methods is that they can also generalize to triples which have never been observed in the training data. Our experimental results on the recently published Stanford Visual Relationship dataset, a challenging real world dataset, show that the integration of a statistical semantic model using link prediction methods can significantly improve visual relationship detection. Our combined approach achieves superior performance compared to the state-of-the-art method from the Stanford computer vision group.}, added-at = {2017-10-24T11:09:51.000+0200}, address = {Cham}, author = {Baier, Stephan and Ma, Yunpu and Tresp, Volker}, biburl = {https://www.bibsonomy.org/bibtex/254bf16ded7e59ce9ed6cf811ba466c65/hotho}, booktitle = {The Semantic Web -- ISWC 2017: 16th International Semantic Web Conference, Vienna, Austria, October 21--25, 2017, Proceedings, Part I}, description = {Improving Visual Relationship Detection Using Semantic Modeling of Scene Descriptions | SpringerLink}, doi = {10.1007/978-3-319-68288-4_4}, editor = {d'Amato, Claudia and Fernandez, Miriam and Tamma, Valentina and Lecue, Freddy and Cudr{\'e}-Mauroux, Philippe and Sequeda, Juan and Lange, Christoph and Heflin, Jeff}, interhash = {83c02ed55678c847cff2b936295045e8}, intrahash = {54bf16ded7e59ce9ed6cf811ba466c65}, isbn = {978-3-319-68288-4}, keywords = {learning prior relation semantic toread}, pages = {53--68}, publisher = {Springer International Publishing}, timestamp = {2017-10-24T11:09:51.000+0200}, title = {Improving Visual Relationship Detection Using Semantic Modeling of Scene Descriptions}, url = {https://doi.org/10.1007/978-3-319-68288-4_4}, year = 2017 } @inproceedings{niebler2017learning_2, added-at = {2017-09-27T07:51:17.000+0200}, author = {Niebler, Thomas and Hahn, Luzian and Hotho, Andreas}, biburl = {https://www.bibsonomy.org/bibtex/243fb590e432f966dd664d7ddfd8f73aa/hotho}, booktitle = {Proceedings of the LWDA}, interhash = {a8757399d7eaa602a74388adf8cf0b0b}, intrahash = {43fb590e432f966dd664d7ddfd8f73aa}, keywords = {2017 bibsonomy citeulike delicious embeddings glove line myown relatedness semantic tag word2vec}, timestamp = {2017-09-27T07:51:17.000+0200}, title = {Learning Word Embeddings from Tagging Data: A methodological comparison}, year = 2017 } @inproceedings{wang2015relational, added-at = {2017-06-24T01:36:15.000+0200}, author = {Wang, Hao and Shi, Xingjian and Yeung, Dit-Yan}, biburl = {https://www.bibsonomy.org/bibtex/2c13e8177f3d8b53e0c34859c55af1c5e/hotho}, booktitle = {AAAI}, interhash = {4b8e0244c0c511049e60087ec2b777de}, intrahash = {c13e8177f3d8b53e0c34859c55af1c5e}, keywords = {tag recommender embedding semantic sendto:thomas citedby:scholar:count:23 citedby:scholar:timestamp:2017-6-23}, pages = {3052--3058}, timestamp = {2017-06-24T01:36:15.000+0200}, title = {Relational Stacked Denoising Autoencoder for Tag Recommendation.}, year = 2015 } @article{Jabeen2016, abstract = {Web 2.0 has brought many collaborative and novel applications which transformed the web as a medium and resulted in its exponential growth. Tagging systems are one of these killer applications. Tags are in free-form but represent the link between objective information and users' cognitive information. However, tags have ambiguity problem reducing precision. Hence search and retrieval pose a challenge on folksonomy systems which have flat, unstructured, non-hierarchical organization with unsupervised vocabulary. We present a brief survey of different approaches for adding semantics in folksonomies thus bringing structure and precision in search and navigation. We did comparative analysis to estimate the significance of each source of semantics. Then, we have categorized the approaches in a systematic way and summarized the feature set support. Based on the survey we end up with recommendations. Our survey and conclusion will prove to be relevant and beneficial for engineers and designers aiming to design and maintain well structured folksonomy with precise search and navigation results.}, added-at = {2017-06-19T21:12:46.000+0200}, author = {Jabeen, Fouzia and Khusro, Shah and Majid, Amna and Rauf, Azhar}, biburl = {https://www.bibsonomy.org/bibtex/2110d6485bc147bb4a5b5cfa87884418a/hotho}, description = {Semantics discovery in social tagging systems: A review | SpringerLink}, doi = {10.1007/s11042-014-2309-3}, interhash = {251e70bc7ad424f91b57e4e3f14cce6c}, intrahash = {110d6485bc147bb4a5b5cfa87884418a}, issn = {1573-7721}, journal = {Multimedia Tools and Applications}, keywords = {folksonomy learning semantic survey toread}, number = 1, pages = {573--605}, timestamp = {2017-06-19T21:12:46.000+0200}, title = {Semantics discovery in social tagging systems: A review}, url = {http://dx.doi.org/10.1007/s11042-014-2309-3}, volume = 75, year = 2016 } @article{bontcheva2014making, added-at = {2017-06-19T04:43:17.000+0200}, author = {Bontcheva, Kalina and Rout, Dominic}, biburl = {https://www.bibsonomy.org/bibtex/2419a48b78fd2e0aa515244bb1782fe59/hotho}, interhash = {63c6eefd94f352ac29363823455132b6}, intrahash = {419a48b78fd2e0aa515244bb1782fe59}, journal = {Semantic Web}, keywords = {extraction learning media relatedness search semantic social survey tag}, number = 5, pages = {373--403}, publisher = {IOS Press}, timestamp = {2017-09-08T17:00:35.000+0200}, title = {Making sense of social media streams through semantics: a survey}, volume = 5, year = 2014 } @article{ASI:ASI23353, abstract = {Tag recommendation strategies that exploit term co-occurrence patterns with tags previously assigned to the target object have consistently produced state-of-the-art results. However, such techniques work only for objects with previously assigned tags. Here we focus on tag recommendation for objects with no tags, a variation of the well-known \textit{cold start} problem. We start by evaluating state-of-the-art co-occurrence based methods in cold start. Our results show that the effectiveness of these methods suffers in this situation. Moreover, we show that employing various automatic filtering strategies to generate an initial tag set that enables the use of co-occurrence patterns produces only marginal improvements. We then propose a new approach that exploits both positive and negative user feedback to iteratively select input tags along with a genetic programming strategy to learn the recommendation function. Our experimental results indicate that extending the methods to include user relevance feedback leads to gains in precision of up to 58% over the best baseline in cold start scenarios and gains of up to 43% over the best baseline in objects that contain some initial tags (i.e., no cold start). We also show that our best relevance-feedback-driven strategy performs well even in scenarios that lack user cooperation (i.e., users may refuse to provide feedback) and user reliability (i.e., users may provide the wrong feedback).}, added-at = {2017-06-17T01:51:11.000+0200}, author = {Martins, Eder F. and Belém, Fabiano M. and Almeida, Jussara M. and Gonçalves, Marcos A.}, biburl = {https://www.bibsonomy.org/bibtex/27d8a8e73eb2b016d1d98271394feeb2f/hotho}, doi = {10.1002/asi.23353}, interhash = {cf469bd0c596b8140a948e2beff2be7c}, intrahash = {7d8a8e73eb2b016d1d98271394feeb2f}, issn = {2330-1643}, journal = {Journal of the Association for Information Science and Technology}, keywords = {recommendation semantic tag toread}, number = 1, pages = {83--105}, timestamp = {2017-06-17T01:51:11.000+0200}, title = {On cold start for associative tag recommendation}, url = {http://dx.doi.org/10.1002/asi.23353}, volume = 67, year = 2016 } @inproceedings{movshovitzattias2015kblda, added-at = {2017-06-11T18:42:27.000+0200}, author = {Movshovitz-Attias, Dana and Cohen, William W.}, biburl = {https://www.bibsonomy.org/bibtex/2696ae5cd7f9ca0d5f551fe15033ceefc/hotho}, booktitle = {ACL (1)}, crossref = {conf/acl/2015-1}, ee = {http://aclweb.org/anthology/P/P15/P15-1140.pdf}, interhash = {2bd9901dfc5421896ada65fb94d95f44}, intrahash = {696ae5cd7f9ca0d5f551fe15033ceefc}, isbn = {978-1-941643-72-3}, keywords = {base clustering concept knowledge lda semantic}, pages = {1449-1459}, publisher = {The Association for Computer Linguistics}, timestamp = {2017-06-11T18:42:27.000+0200}, title = {KB-LDA: Jointly Learning a Knowledge Base of Hierarchy, Relations, and Facts.}, url = {http://dblp.uni-trier.de/db/conf/acl/acl2015-1.html#Movshovitz-Attias15}, year = 2015 } @article{wrro115871, added-at = {2017-05-30T10:56:16.000+0200}, author = {Hotho, A. and Jaeschke, R. and Lerman, K.}, biburl = {https://www.bibsonomy.org/bibtex/2dfa668b67165e8f52def015f9324caef/hotho}, description = {Mining social semantics on the social web - White Rose Research Online}, interhash = {46cbcf61b5e6ae3097eb4310d0802525}, intrahash = {dfa668b67165e8f52def015f9324caef}, journal = {Semantic Web}, keywords = {2017 mining myown semantic social web}, month = {April}, note = {\copyright 2017 IOS Press and the authors. This is an author produced version of a paper subsequently published in Semantic Web. Uploaded in accordance with the publisher's self-archiving policy.}, number = 5, pages = {623--624}, publisher = {IOS Press}, timestamp = {2017-05-30T10:57:41.000+0200}, title = {Mining social semantics on the social web}, url = {http://eprints.whiterose.ac.uk/115871/}, volume = 8, year = 2017 } @misc{niebler2017learning, abstract = {Assessing the degree of semantic relatedness between words is an important task with a variety of semantic applications, such as ontology learning for the Semantic Web, semantic search or query expansion. To accomplish this in an automated fashion, many relatedness measures have been proposed. However, most of these metrics only encode information contained in the underlying corpus and thus do not directly model human intuition. To solve this, we propose to utilize a metric learning approach to improve existing semantic relatedness measures by learning from additional information, such as explicit human feedback. For this, we argue to use word embeddings instead of traditional high-dimensional vector representations in order to leverage their semantic density and to reduce computational cost. We rigorously test our approach on several domains including tagging data as well as publicly available embeddings based on Wikipedia texts and navigation. Human feedback about semantic relatedness for learning and evaluation is extracted from publicly available datasets such as MEN or WS-353. We find that our method can significantly improve semantic relatedness measures by learning from additional information, such as explicit human feedback. For tagging data, we are the first to generate and study embeddings. Our results are of special interest for ontology and recommendation engineers, but also for any other researchers and practitioners of Semantic Web techniques.}, added-at = {2017-05-30T10:53:33.000+0200}, author = {Niebler, Thomas and Becker, Martin and Pölitz, Christian and Hotho, Andreas}, biburl = {https://www.bibsonomy.org/bibtex/238ec3d4e41af2acda32f86c37ac89ad0/hotho}, description = {Learning Semantic Relatedness From Human Feedback Using Metric Learning}, interhash = {c7a3f26c61a1ac7b5789fbfb484b6a27}, intrahash = {38ec3d4e41af2acda32f86c37ac89ad0}, keywords = {2017 learning metric myown relatedness semantic}, note = {cite arxiv:1705.07425Comment: Under review at ISWC 2017}, timestamp = {2017-05-30T10:53:33.000+0200}, title = {Learning Semantic Relatedness From Human Feedback Using Metric Learning}, url = {http://arxiv.org/abs/1705.07425}, year = 2017 } @book{ontohandbook, added-at = {2016-11-27T22:19:21.000+0100}, bibsource = {DBLP, http://dblp.uni-trier.de}, biburl = {https://www.bibsonomy.org/bibtex/292d0b6d054d0032cc10c1752169503bc/hotho}, booktitle = {Handbook on Ontologies}, edition = {2nd edition}, editor = {Staab, Steffen and Studer, Rudi}, interhash = {c2e7c401bef2cee2bb8b12334d3c7a88}, intrahash = {92d0b6d054d0032cc10c1752169503bc}, isbn = {3-540-40834-7}, keywords = {ontologies proposal semantic tau web}, publisher = {Springer}, series = {International Handbooks on Information Systems}, timestamp = {2016-11-27T22:19:21.000+0100}, title = {Handbook on Ontologies}, year = 2009 } @article{journals/ki/NieblerS0H16, added-at = {2016-10-08T18:43:20.000+0200}, author = {Niebler, Thomas and Schlör, Daniel and Becker, Martin and Hotho, Andreas}, biburl = {https://www.bibsonomy.org/bibtex/20968a771aa0819dce2fbf7f5c9b94cda/hotho}, ee = {http://dx.doi.org/10.1007/s13218-015-0417-5}, interhash = {9d31f37eca5c6e62ebb26285cdef8155}, intrahash = {0968a771aa0819dce2fbf7f5c9b94cda}, journal = {KI}, keywords = {2015 2016 behaviour extracting extraction log myown navigation relatedness semantic user wikipedia}, number = 2, pages = {163-168}, timestamp = {2016-10-08T18:52:27.000+0200}, title = {Extracting Semantics from Unconstrained Navigation on Wikipedia}, url = {http://dblp.uni-trier.de/db/journals/ki/ki30.html#NieblerS0H16}, volume = 30, year = 2016 } @inproceedings{conf/semweb/WalkSNTMS15, added-at = {2016-07-16T19:47:22.000+0200}, author = {Walk, Simon and Singer, Philipp and Espín-Noboa, Lisette and Tudorache, Tania and Musen, Mark A. and Strohmaier, Markus}, biburl = {https://www.bibsonomy.org/bibtex/234164a261a9ea1daa2aaaa91c4ce1342/hotho}, booktitle = {International Semantic Web Conference (1)}, crossref = {conf/semweb/2015-1}, editor = {Arenas, Marcelo and Corcho, Óscar and Simperl, Elena and Strohmaier, Markus and d'Aquin, Mathieu and Srinivas, Kavitha and Groth, Paul T. and Dumontier, Michel and Heflin, Jeff and Thirunarayan, Krishnaprasad and Staab, Steffen}, ee = {http://dx.doi.org/10.1007/978-3-319-25007-6_32}, interhash = {69c08aa4c930b39c08ba3d6eba8a1e9b}, intrahash = {34164a261a9ea1daa2aaaa91c4ce1342}, isbn = {978-3-319-25006-9}, keywords = {edit hyptrails ontology semantic}, pages = {551-568}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, timestamp = {2016-07-16T19:48:34.000+0200}, title = {Understanding How Users Edit Ontologies: Comparing Hypotheses About Four Real-World Projects}, url = {http://dblp.uni-trier.de/db/conf/semweb/iswc2015-1.html#WalkSNTMS15}, volume = 9366, year = 2015 } @inproceedings{Liu:2010:OEF:1871437.1871578, abstract = {The folksonomies built from the large-scale social annotations made by collaborating users are perfect data sources for bootstrapping Semantic Web applications. In this paper, we develop an ontology induction approach to harvest the emergent semantics from the folksonomies. We propose a latent subsumption hierarchy model to uncover the implicit structure of tag space and develop our ontology induction approach on basis of this model. We identify tag subsumptions with a set-theoretical approach and model the tag space as a tag subsumption graph. While turning this graph into a concept hierarchy, we address the problem of inconsistent subsumptions and propose a random walk based tag generality ranking procedure to settle it. We propose an agglomerative hierarchical clustering algorithm utilizing the result of tag generality ranking to generate the concept hierarchy. We conduct experiments on the Delicious dataset. The results of both qualitative and quantitative evaluation demonstrate the effectiveness of the proposed approach.}, acmid = {1871578}, added-at = {2016-07-16T17:17:16.000+0200}, address = {New York, NY, USA}, author = {Liu, Kaipeng and Fang, Binxing and Zhang, Weizhe}, biburl = {https://www.bibsonomy.org/bibtex/2e74a5f3a7982ecfd6e2aebbe4b06f5c5/hotho}, booktitle = {Proceedings of the 19th ACM International Conference on Information and Knowledge Management}, doi = {10.1145/1871437.1871578}, interhash = {1fc81f009817beab0c1f098870ce62fa}, intrahash = {e74a5f3a7982ecfd6e2aebbe4b06f5c5}, isbn = {978-1-4503-0099-5}, keywords = {folkonomy learning ol ontology tagging semantic}, location = {Toronto, ON, Canada}, numpages = {10}, pages = {1109--1118}, publisher = {ACM}, series = {CIKM '10}, timestamp = {2016-07-16T17:21:42.000+0200}, title = {Ontology Emergence from Folksonomies}, url = {http://doi.acm.org/10.1145/1871437.1871578}, year = 2010 } @article{journals/informs/LauZZCN15, added-at = {2016-07-16T17:10:49.000+0200}, author = {Lau, Raymond Y. K. and Zhao, J. Leon and Zhang, Wenping and Cai, Yi and Ngai, Eric W. T.}, biburl = {https://www.bibsonomy.org/bibtex/2a0246e608bc806143edd711b3db77051/hotho}, ee = {http://dx.doi.org/10.1287/ijoc.2015.0644}, interhash = {c19933b075e2171846cedc03bc001023}, intrahash = {a0246e608bc806143edd711b3db77051}, journal = {INFORMS Journal on Computing}, keywords = {domain folksonomy learning ol ontology toread semantic}, number = 3, pages = {561-578}, timestamp = {2016-07-16T17:21:42.000+0200}, title = {Learning Context-Sensitive Domain Ontologies from Folksonomies: A Cognitively Motivated Method}, url = {http://dblp.uni-trier.de/db/journals/informs/informs27.html#LauZZCN15}, volume = 27, year = 2015 } @inproceedings{Nastase:2008:DWC:1620163.1620262, abstract = {This paper presents an approach to acquire knowledge from Wikipedia categories and the category network. Many Wikipedia categories have complex names which reflect human classification and organizing instances, and thus encode knowledge about class attributes, taxonomic and other semantic relations. We decode the names and refer back to the network to induce relations between concepts in Wikipedia represented through pages or categories. The category structure allows us to propagate a relation detected between constituents of a category name to numerous concept links. The results of the process are evaluated against ResearchCyc and a subset also by human judges. The results support the idea that Wikipedia category names are a rich source of useful and accurate knowledge.}, acmid = {1620262}, added-at = {2016-07-16T17:06:35.000+0200}, author = {Nastase, Vivi and Strube, Michael}, biburl = {https://www.bibsonomy.org/bibtex/2ce830844472b2cc149392bdf1d254b29/hotho}, booktitle = {Proceedings of the 23rd National Conference on Artificial Intelligence - Volume 2}, interhash = {11a25a068561112fdd8123ba5d382252}, intrahash = {ce830844472b2cc149392bdf1d254b29}, isbn = {978-1-57735-368-3}, keywords = {knowledge semantic wikipedia}, location = {Chicago, Illinois}, numpages = {6}, pages = {1219--1224}, publisher = {AAAI Press}, series = {AAAI'08}, timestamp = {2016-07-16T17:06:35.000+0200}, title = {Decoding Wikipedia Categories for Knowledge Acquisition}, url = {http://dl.acm.org/citation.cfm?id=1620163.1620262}, year = 2008 }