2020
|
Röder, Michael; Sherif, Mohamed Ahmed; Saleem, Muhammad; Conrads, Felix; Ngomo, Axel-Cyrille Ngonga Benchmarking the Lifecycle of Knowledge Graphs Incollection Knowledge Graphs for eXplainable Artificial Intelligence: Foundations,
Applications and Challenges, 47 , pp. 73–97, IOS Press, 2020. Links | BibTeX @incollection{DBLP:series/ssw/RoderS0CN20,
title = {Benchmarking the Lifecycle of Knowledge Graphs},
author = {Michael Röder and
Mohamed Ahmed Sherif and
Muhammad Saleem and
Felix Conrads and
Axel-Cyrille Ngonga Ngomo},
url = {https://doi.org/10.3233/SSW200012},
doi = {10.3233/SSW200012},
year = {2020},
date = {2020-01-01},
booktitle = {Knowledge Graphs for eXplainable Artificial Intelligence: Foundations,
Applications and Challenges},
volume = {47},
pages = {73--97},
publisher = {IOS Press},
series = {Studies on the Semantic Web},
keywords = {},
pubstate = {published},
tppubtype = {incollection}
}
|
Bigerl, Alexander; Conrads, Felix; Behning, Charlotte; Sherif, Mohamed Ahmed; Saleem, Muhammad; Ngomo, Axel-Cyrille Ngonga Tentris - A Tensor-Based Triple Store Inproceedings The Semantic Web - ISWC 2020 - 19th International Semantic Web Conference,
Athens, Greece, November 2-6, 2020, Proceedings, Part I, pp. 56–73, Springer, 2020. Links | BibTeX @inproceedings{DBLP:conf/semweb/BigerlCBSSN20,
title = {Tentris - A Tensor-Based Triple Store},
author = {Alexander Bigerl and
Felix Conrads and
Charlotte Behning and
Mohamed Ahmed Sherif and
Muhammad Saleem and
Axel-Cyrille Ngonga Ngomo},
url = {https://doi.org/10.1007/978-3-030-62419-4_4},
doi = {10.1007/978-3-030-62419-4_4},
year = {2020},
date = {2020-01-01},
booktitle = {The Semantic Web - ISWC 2020 - 19th International Semantic Web Conference,
Athens, Greece, November 2-6, 2020, Proceedings, Part I},
volume = {12506},
pages = {56--73},
publisher = {Springer},
series = {Lecture Notes in Computer Science},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
2019
|
Athanasiou, Spiros; Giannopoulos, Giorgos; Graux, Damien; Karagiannakis, Nikos; Lehmann, Jens; Ngomo, Axel-Cyrille Ngonga; Patroumpas, Kostas; Sherif, Mohamed Ahmed; Skoutas, Dimitrios Big POI data integration with Linked Data technologies Inproceedings Advances in Database Technology - 22nd International Conference on
Extending Database Technology, EDBT 2019, Lisbon, Portugal, March
26-29, 2019, pp. 477–488, OpenProceedings.org, 2019. Links | BibTeX @inproceedings{DBLP:conf/edbt/AthanasiouGGK0N19,
title = {Big POI data integration with Linked Data technologies},
author = {Spiros Athanasiou and
Giorgos Giannopoulos and
Damien Graux and
Nikos Karagiannakis and
Jens Lehmann and
Axel-Cyrille Ngonga Ngomo and
Kostas Patroumpas and
Mohamed Ahmed Sherif and
Dimitrios Skoutas},
url = {https://doi.org/10.5441/002/edbt.2019.44},
doi = {10.5441/002/edbt.2019.44},
year = {2019},
date = {2019-01-01},
booktitle = {Advances in Database Technology - 22nd International Conference on
Extending Database Technology, EDBT 2019, Lisbon, Portugal, March
26-29, 2019},
pages = {477--488},
publisher = {OpenProceedings.org},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Ahmed, Abdullah Fathi; Sherif, Mohamed Ahmed; Ngomo, Axel-Cyrille Ngonga Do your Resources Sound Similar?: On the Impact of Using Phonetic
Similarity in Link Discovery Inproceedings Proceedings of the 10th International Conference on Knowledge Capture,
K-CAP 2019, Marina Del Rey, CA, USA, November 19-21, 2019, pp. 53–60, ACM, 2019. Links | BibTeX @inproceedings{DBLP:conf/kcap/AhmedSN19,
title = {Do your Resources Sound Similar?: On the Impact of Using Phonetic
Similarity in Link Discovery},
author = {Abdullah Fathi Ahmed and
Mohamed Ahmed Sherif and
Axel-Cyrille Ngonga Ngomo},
url = {https://doi.org/10.1145/3360901.3364426},
doi = {10.1145/3360901.3364426},
year = {2019},
date = {2019-01-01},
booktitle = {Proceedings of the 10th International Conference on Knowledge Capture,
K-CAP 2019, Marina Del Rey, CA, USA, November 19-21, 2019},
pages = {53--60},
publisher = {ACM},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Zahera, Hamada M; Sherif, Mohamed Ahmed; Ngomo, Axel-Cyrille Ngonga Jointly Learning from Social Media and Environmental Data for Typhoon
Intensity Prediction Inproceedings Proceedings of the 10th International Conference on Knowledge Capture,
K-CAP 2019, Marina Del Rey, CA, USA, November 19-21, 2019, pp. 231–234, ACM, 2019. Links | BibTeX @inproceedings{DBLP:conf/kcap/ZaheraSN19,
title = {Jointly Learning from Social Media and Environmental Data for Typhoon
Intensity Prediction},
author = {Hamada M. Zahera and
Mohamed Ahmed Sherif and
Axel-Cyrille Ngonga Ngomo},
url = {https://doi.org/10.1145/3360901.3364413},
doi = {10.1145/3360901.3364413},
year = {2019},
date = {2019-01-01},
booktitle = {Proceedings of the 10th International Conference on Knowledge Capture,
K-CAP 2019, Marina Del Rey, CA, USA, November 19-21, 2019},
pages = {231--234},
publisher = {ACM},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Ahmed, Abdullah Fathi; Sherif, Mohamed Ahmed; Ngomo, Axel-Cyrille Ngonga LSVS: Link Specification Verbalization and Summarization Inproceedings Natural Language Processing and Information Systems - 24th International
Conference on Applications of Natural Language to Information Systems,
NLDB 2019, Salford, UK, June 26-28, 2019, Proceedings, pp. 66–78, Springer, 2019. Links | BibTeX @inproceedings{DBLP:conf/nldb/AhmedSN19,
title = {LSVS: Link Specification Verbalization and Summarization},
author = {Abdullah Fathi Ahmed and
Mohamed Ahmed Sherif and
Axel-Cyrille Ngonga Ngomo},
url = {https://doi.org/10.1007/978-3-030-23281-8_6},
doi = {10.1007/978-3-030-23281-8_6},
year = {2019},
date = {2019-01-01},
booktitle = {Natural Language Processing and Information Systems - 24th International
Conference on Applications of Natural Language to Information Systems,
NLDB 2019, Salford, UK, June 26-28, 2019, Proceedings},
volume = {11608},
pages = {66--78},
publisher = {Springer},
series = {Lecture Notes in Computer Science},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Sherif, Mohamed Ahmed; Svetlana, Pestryakova; Dreßler, Kevin; Ngomo, Axel-Cyrille Ngonga LimesWebUI - Link Discovery Made Simple Inproceedings Proceedings of the ISWC 2019 Satellite Tracks (Posters & Demonstrations,
Industry, and Outrageous Ideas) co-located with 18th International
Semantic Web Conference (ISWC 2019), Auckland, New Zealand, October
26-30, 2019, pp. 205–208, CEUR-WS.org, 2019. Links | BibTeX @inproceedings{DBLP:conf/semweb/SherifSDN19,
title = {LimesWebUI - Link Discovery Made Simple},
author = {Mohamed Ahmed Sherif and
Pestryakova Svetlana and
Kevin Dreßler and
Axel-Cyrille Ngonga Ngomo},
url = {http://ceur-ws.org/Vol-2456/paper53.pdf},
year = {2019},
date = {2019-01-01},
booktitle = {Proceedings of the ISWC 2019 Satellite Tracks (Posters & Demonstrations,
Industry, and Outrageous Ideas) co-located with 18th International
Semantic Web Conference (ISWC 2019), Auckland, New Zealand, October
26-30, 2019},
volume = {2456},
pages = {205--208},
publisher = {CEUR-WS.org},
series = {CEUR Workshop Proceedings},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Zahera, Hamada M; Elgendy, Ibrahim A; Jalota, Rricha; Sherif, Mohamed Ahmed Fine-tuned BERT Model for Multi-Label Tweets Classification Inproceedings Proceedings of the Twenty-Eighth Text REtrieval Conference, TREC
2019, Gaithersburg, Maryland, USA, November 13-15, 2019, National Institute of Standards and Technology (NIST), 2019. Links | BibTeX @inproceedings{DBLP:conf/trec/ZaheraEJS19,
title = {Fine-tuned BERT Model for Multi-Label Tweets Classification},
author = {Hamada M. Zahera and
Ibrahim A. Elgendy and
Rricha Jalota and
Mohamed Ahmed Sherif},
url = {https://trec.nist.gov/pubs/trec28/papers/DICE_UPB.IS.pdf},
year = {2019},
date = {2019-01-01},
booktitle = {Proceedings of the Twenty-Eighth Text REtrieval Conference, TREC
2019, Gaithersburg, Maryland, USA, November 13-15, 2019},
volume = {1250},
publisher = {National Institute of Standards and Technology (NIST)},
series = {NIST Special Publication},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
2018
|
Sherif, Mohamed Ahmed; Ngomo, Axel-Cyrille Ngonga A systematic survey of point set distance measures for link discovery Journal Article Semantic Web, 9 (5), pp. 589–604, 2018. Abstract | Links | BibTeX @article{DBLP:journals/semweb/SherifN18,
title = {A systematic survey of point set distance measures for link discovery},
author = {Mohamed Ahmed Sherif and
Axel-Cyrille Ngonga Ngomo},
url = {http://www.semantic-web-journal.net/content/systematic-survey-point-set-distance-measures-link-discovery-1},
doi = {10.3233/SW-170285},
year = {2018},
date = {2018-01-01},
journal = {Semantic Web},
volume = {9},
number = {5},
pages = {589--604},
abstract = {Large amounts of geo-spatial information have been made available with the growth of the Web of Data. While discovering links between resources on the Web of Data has been shown to be a demanding task, discovering links between geo-spatial resources proves to be even more challenging. This is partly due to the resources being described by the means of vector geometry. Especially, discrepancies in granularity and error measurements across data sets render the selection of appropriate distance measures for geo-spatial resources difficult. In this paper, we survey existing literature for point-set measures that can be used to measure the similarity of vector geometries. We then present and evaluate the ten measures that we derived from literature. We evaluate these measures with respect to their time-efficiency and their robustness against discrepancies in measurement and in granularity. To this end, we use samples of real data sets of different granularity as input for our evaluation framework. The results obtained on three different data sets suggest that most distance approaches can be led to scale. Moreover, while some distance measures are significantly slower than other measures, distance measure based on means, surjections and sums of minimal distances are robust against the different types of discrepancies.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Large amounts of geo-spatial information have been made available with the growth of the Web of Data. While discovering links between resources on the Web of Data has been shown to be a demanding task, discovering links between geo-spatial resources proves to be even more challenging. This is partly due to the resources being described by the means of vector geometry. Especially, discrepancies in granularity and error measurements across data sets render the selection of appropriate distance measures for geo-spatial resources difficult. In this paper, we survey existing literature for point-set measures that can be used to measure the similarity of vector geometries. We then present and evaluate the ten measures that we derived from literature. We evaluate these measures with respect to their time-efficiency and their robustness against discrepancies in measurement and in granularity. To this end, we use samples of real data sets of different granularity as input for our evaluation framework. The results obtained on three different data sets suggest that most distance approaches can be led to scale. Moreover, while some distance measures are significantly slower than other measures, distance measure based on means, surjections and sums of minimal distances are robust against the different types of discrepancies. |
Wauer, Matthias; Sherif, Mohamed Ahmed; Ngomo, Axel-Cyrille Ngonga Towards a Semantic Message-driven Microservice Platform for Geospatial
and Sensor Data Inproceedings Proceedings of the 3rd International Workshop on Geospatial Linked
Data and the 2nd Workshop on Querying the Web of Data co-located with
15th Extended Semantic Web Conference (ESWC 2018), Heraklion, Greece,
June 3, 2018, pp. 47–58, CEUR-WS.org, 2018. Links | BibTeX @inproceedings{DBLP:conf/esws/WauerSN18,
title = {Towards a Semantic Message-driven Microservice Platform for Geospatial
and Sensor Data},
author = {Matthias Wauer and
Mohamed Ahmed Sherif and
Axel-Cyrille Ngonga Ngomo},
url = {http://ceur-ws.org/Vol-2110/paper5.pdf},
year = {2018},
date = {2018-01-01},
booktitle = {Proceedings of the 3rd International Workshop on Geospatial Linked
Data and the 2nd Workshop on Querying the Web of Data co-located with
15th Extended Semantic Web Conference (ESWC 2018), Heraklion, Greece,
June 3, 2018},
volume = {2110},
pages = {47--58},
publisher = {CEUR-WS.org},
series = {CEUR Workshop Proceedings},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Ahmed, Abdullah Fathi; Sherif, Mohamed Ahmed; Ngomo, Axel-Cyrille Ngonga On the Effect of Geometries Simplification on Geo-spatial Link Discovery Inproceedings Proceedings of the 14th International Conference on Semantic Systems,
SEMANTICS 2018, Vienna, Austria, September 10-13, 2018, pp. 139–150, Elsevier, 2018. Links | BibTeX @inproceedings{DBLP:conf/i-semantics/AhmedSN18,
title = {On the Effect of Geometries Simplification on Geo-spatial Link Discovery},
author = {Abdullah Fathi Ahmed and
Mohamed Ahmed Sherif and
Axel-Cyrille Ngonga Ngomo},
url = {https://doi.org/10.1016/j.procs.2018.09.014},
doi = {10.1016/j.procs.2018.09.014},
year = {2018},
date = {2018-01-01},
booktitle = {Proceedings of the 14th International Conference on Semantic Systems,
SEMANTICS 2018, Vienna, Austria, September 10-13, 2018},
volume = {137},
pages = {139--150},
publisher = {Elsevier},
series = {Procedia Computer Science},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Moussallem, Diego; Sherif, Mohamed Ahmed; Esteves, Diego; Zampieri, Marcos; Ngomo, Axel-Cyrille Ngonga LIdioms: A Multilingual Linked Idioms Data Set Inproceedings Proceedings of the Eleventh International Conference on Language Resources
and Evaluation, LREC 2018, Miyazaki, Japan, May 7-12, 2018, European Language Resources Association (ELRA), 2018. Links | BibTeX @inproceedings{DBLP:conf/lrec/MoussallemSEZN18,
title = {LIdioms: A Multilingual Linked Idioms Data Set},
author = {Diego Moussallem and
Mohamed Ahmed Sherif and
Diego Esteves and
Marcos Zampieri and
Axel-Cyrille Ngonga Ngomo},
url = {http://www.lrec-conf.org/proceedings/lrec2018/summaries/46.html},
year = {2018},
date = {2018-01-01},
booktitle = {Proceedings of the Eleventh International Conference on Language Resources
and Evaluation, LREC 2018, Miyazaki, Japan, May 7-12, 2018},
publisher = {European Language Resources Association (ELRA)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Ahmed, Abdullah Fathi; Sherif, Mohamed Ahmed; Ngomo, Axel-Cyrille Ngonga RADON2 - a buffered-intersection matrix computing approach to accelerate
link discovery over geo-spatial RDF knowledge bases: OAEI2018
results Inproceedings Proceedings of the 13th International Workshop on Ontology Matching co-located with the 17th International Semantic Web Conference, OM@ISWC
2018, Monterey, CA, USA, October 8, 2018, pp. 197–204, CEUR-WS.org, 2018. Links | BibTeX @inproceedings{DBLP:conf/semweb/AhmedSN18,
title = {RADON2 - a buffered-intersection matrix computing approach to accelerate
link discovery over geo-spatial RDF knowledge bases: OAEI2018
results},
author = {Abdullah Fathi Ahmed and
Mohamed Ahmed Sherif and
Axel-Cyrille Ngonga Ngomo},
url = {http://ceur-ws.org/Vol-2288/oaei18_paper13.pdf},
year = {2018},
date = {2018-01-01},
booktitle = {Proceedings of the 13th International Workshop on Ontology Matching co-located with the 17th International Semantic Web Conference, OM@ISWC
2018, Monterey, CA, USA, October 8, 2018},
volume = {2288},
pages = {197--204},
publisher = {CEUR-WS.org},
series = {CEUR Workshop Proceedings},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Jiménez-Ruiz, Ernesto; Saveta, Tzanina; Zamazal, Ondrej; Hertling, Sven; Röder, Michael; Fundulaki, Irini; Ngomo, Axel-Cyrille Ngonga; Sherif, Mohamed Ahmed; Annane, Amina; Bellahsene, Zohra; Yahia, Sadok Ben; Diallo, Gayo; Faria, Daniel; Kachroudi, Marouen; Khiat, Abderrahmane; Lambrix, Patrick; Li, Huanyu; Mackeprang, Maximilian; Mohammadi, Majid; Rybinski, Maciej; Balasubramani, Booma Sowkarthiga; Trojahn, Cássia Introducing the HOBBIT platform into the ontology alignment evaluation
campaign Inproceedings Proceedings of the 13th International Workshop on Ontology Matching co-located with the 17th International Semantic Web Conference, OM@ISWC
2018, Monterey, CA, USA, October 8, 2018, pp. 49–60, CEUR-WS.org, 2018. Links | BibTeX @inproceedings{DBLP:conf/semweb/Jimenez-RuizSZH18,
title = {Introducing the HOBBIT platform into the ontology alignment evaluation
campaign},
author = {Ernesto Jiménez-Ruiz and
Tzanina Saveta and
Ondrej Zamazal and
Sven Hertling and
Michael Röder and
Irini Fundulaki and
Axel-Cyrille Ngonga Ngomo and
Mohamed Ahmed Sherif and
Amina Annane and
Zohra Bellahsene and
Sadok Ben Yahia and
Gayo Diallo and
Daniel Faria and
Marouen Kachroudi and
Abderrahmane Khiat and
Patrick Lambrix and
Huanyu Li and
Maximilian Mackeprang and
Majid Mohammadi and
Maciej Rybinski and
Booma Sowkarthiga Balasubramani and
Cássia Trojahn},
url = {http://ceur-ws.org/Vol-2288/om2018_LTpaper5.pdf},
year = {2018},
date = {2018-01-01},
booktitle = {Proceedings of the 13th International Workshop on Ontology Matching co-located with the 17th International Semantic Web Conference, OM@ISWC
2018, Monterey, CA, USA, October 8, 2018},
volume = {2288},
pages = {49--60},
publisher = {CEUR-WS.org},
series = {CEUR Workshop Proceedings},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
2017
|
Sherif, Mohamed Ahmed; Dreßler, Kevin; Smeros, Panayiotis; Ngomo, Axel-Cyrille Ngonga Radon - Rapid Discovery of Topological Relations Inproceedings Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence,
February 4-9, 2017, San Francisco, California, USA, pp. 175–181, AAAI Press, 2017. Abstract | Links | BibTeX @inproceedings{DBLP:conf/aaai/SherifDSN17,
title = {Radon - Rapid Discovery of Topological Relations},
author = {Mohamed Ahmed Sherif and
Kevin Dreßler and
Panayiotis Smeros and
Axel-Cyrille Ngonga Ngomo},
url = {https://svn.aksw.org/papers/2017/AAAI_RADON/public.pdf},
year = {2017},
date = {2017-01-01},
booktitle = {Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence,
February 4-9, 2017, San Francisco, California, USA},
pages = {175--181},
publisher = {AAAI Press},
abstract = {Geospatial data is at the core of the Semantic Web, of which the largest knowledge base contains more than 30 billions facts. Reasoning on these large amounts of geospatial data requires efficient methods for the computation of links between the resources contained in these knowledge bases. In this paper, we present RADON - efficient solution for the discovery of topological relations between geospatial resources according to the DE9-IM standard. Our evaluation shows that we outperform the state of the art significantly and by several orders of magnitude.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Geospatial data is at the core of the Semantic Web, of which the largest knowledge base contains more than 30 billions facts. Reasoning on these large amounts of geospatial data requires efficient methods for the computation of links between the resources contained in these knowledge bases. In this paper, we present RADON - efficient solution for the discovery of topological relations between geospatial resources according to the DE9-IM standard. Our evaluation shows that we outperform the state of the art significantly and by several orders of magnitude. |
Sherif, Mohamed Ahmed; Ngomo, Axel-Cyrille Ngonga; Lehmann, Jens Wombat - A Generalization Approach for Automatic Link Discovery Inproceedings The Semantic Web - 14th International Conference, ESWC 2017, Portorov z, Slovenia, May 28 - June 1, 2017, Proceedings, Part I, pp. 103–119, 2017. Links | BibTeX @inproceedings{DBLP:conf/esws/SherifNL17,
title = {Wombat - A Generalization Approach for Automatic Link Discovery},
author = {Mohamed Ahmed Sherif and
Axel-Cyrille Ngonga Ngomo and
Jens Lehmann},
url = {http://svn.aksw.org/papers/2017/ESWC_WOMBAT/public.pdf},
doi = {10.1007/978-3-319-58068-5_7},
year = {2017},
date = {2017-01-01},
booktitle = {The Semantic Web - 14th International Conference, ESWC 2017, Portorov z, Slovenia, May 28 - June 1, 2017, Proceedings, Part I},
volume = {10249},
pages = {103--119},
series = {Lecture Notes in Computer Science},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Dreßler, Kevin; Sherif, Mohamed Ahmed; Ngomo, Axel-Cyrille Ngonga Radon results for OAEI 2017 Inproceedings Proceedings of the 12th International Workshop on Ontology Matching
co-located with the 16th International Semantic Web Conference (ISWC
2017), Vienna, Austria, October 21, 2017, pp. 178–184, CEUR-WS.org, 2017. Links | BibTeX @inproceedings{DBLP:conf/semweb/DresslerSN17,
title = {Radon results for OAEI 2017},
author = {Kevin Dreßler and
Mohamed Ahmed Sherif and
Axel-Cyrille Ngonga Ngomo},
url = {http://ceur-ws.org/Vol-2032/oaei17_paper11.pdf},
year = {2017},
date = {2017-01-01},
booktitle = {Proceedings of the 12th International Workshop on Ontology Matching
co-located with the 16th International Semantic Web Conference (ISWC
2017), Vienna, Austria, October 21, 2017},
volume = {2032},
pages = {178--184},
publisher = {CEUR-WS.org},
series = {CEUR Workshop Proceedings},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
2016
|
Sherif, Mohamed Ahmed Automating Geospatial RDF Dataset Integration and Enrichment PhD Thesis University of Leipzig, 2016, (rulhttp://www.qucosa.de/recherche/frontdoor/?tx_slubopus4frontend[id]=21570). Abstract | Links | BibTeX @phdthesis{Sherif-thesis-2016,
title = {Automating Geospatial RDF Dataset Integration and Enrichment},
author = {Mohamed Ahmed Sherif},
url = {http://www.qucosa.de/recherche/frontdoor/?tx_slubopus4frontend[id]=21570},
year = {2016},
date = {2016-12-01},
address = {Leipzig, Germany},
school = {University of Leipzig},
abstract = {Over the last years, the Linked Open Data (LOD) has evolved from a mere 12 to more than 10, 000 knowledge bases. These knowledge bases come from diverse domains including (but not limited to) publications, life sciences, social networking, government, media, linguistics. Moreover, the LOD cloud also contains a large number of crossdomain knowledge bases such as DBpedia and Yago2. These knowledge bases are commonly managed in a decentralized fashion and contain partly overlapping information. This architectural choice has led to knowledge pertaining to the same domain being published by independent entities in the LOD cloud. For example, information on drugs can be found in Diseasome as well as DBpedia and Drugbank. Furthermore, certain knowledge bases such as DBLP have been published by several bodies, which in turn has lead to duplicated content in the LOD. In addition, large amounts of geo-spatial information have been made available with the growth of heterogeneous Web of Data. The concurrent publication of knowledge bases containing related information promises to become a phenomenon of increasing importance with the growth of the number of independent data providers. Enabling the joint use of the knowledge bases published by these providers for tasks such as federated queries, cross-ontology question answering and data integration is most commonly tackled by creating links between the resources described within these knowledge bases. Within this thesis, we spur the transition from isolated knowledge bases to enriched Linked Data sets where information can be easily integrated and processed. To achieve this goal, we provide concepts, approaches and use cases that facilitate the integration and enrichment of information with other data types that are already present on the Linked Data Web with a focus on geo-spatial data. The first challenge that motivates our work is the lack of measures that use the geographic data for linking geo-spatial knowledge bases. This is partly due to the geo-spatial resources being described by the means of vector geometry. In particular, discrepancies in granularity and error measurements across knowledge bases render the selection of appropriate distance measures for geo-spatial resources difficult. We address this challenge by evaluating existing literature for pointset measures that can be used to measure the similarity of vector geometries. Then, we present and evaluate the ten measures that we derived from the literature on samples of three real knowledge bases. The second challenge we address in this thesis is the lack of automatic Link Discovery (LD) approaches capable of dealing with geospatial knowledge bases with missing and erroneous data. To this end,we present Colibri, an unsupervised approach that allows discovering links between knowledge bases while improving the quality of the instance data in these knowledge bases. A Colibri iteration begins by generating links between knowledge bases. Then, the approach makes use of these links to detect resources with probably erroneous or missing information. This erroneous or missing infor- mation detected by the approach is finally corrected or added. The third challenge we address is the lack of scalable LD approaches for tackling big geo-spatial knowledge bases. Thus, we present Deterministic Particle-Swarm Optimization (DPSO), a novel load balancing technique for LD on parallel hardware based on particle-swarm optimization. We combine this approach with the Orchid algorithm for geo-spatial linking and evaluate it on real and artificial data sets. The lack of approaches for automatic updating of links of an evolving knowledge base is our fourth challenge. This challenge is addressed in this thesis by the Wombat algorithm. Wombat is a novel approach for the discovery of links between knowledge bases that relies exclusively on positive examples. Wombat is based on generalisation via an upward refinement operator to traverse the space of Link Specifications (LS). We study the theoretical characteristics of Wombat and evaluate it on different benchmark data sets. The last challenge addressed herein is the lack of automatic approaches for geo-spatial knowledge base enrichment. Thus, we propose Deer, a supervised learning approach based on a refinement operator for enriching Resource Description Framework (RDF) data sets. We show how we can use exemplary descriptions of enriched resources to generate accurate enrichment pipelines. We evaluate our approach against manually defined enrichment pipelines and show that our approach can learn accurate pipelines even when provided with a small number of training examples. Each of the proposed approaches is implemented and evaluated against state-of-the-art approaches on real and/or artificial data sets. Moreover, all approaches are peer-reviewed and published in a con- ference or a journal paper. Throughout this thesis, we detail the ideas, implementation and the evaluation of each of the approaches. Moreover, we discuss each approach and present lessons learned. Finally, we conclude this thesis by presenting a set of possible future extensions and use cases for each of the proposed approaches.},
note = {rulhttp://www.qucosa.de/recherche/frontdoor/?tx_slubopus4frontend[id]=21570},
keywords = {},
pubstate = {published},
tppubtype = {phdthesis}
}
Over the last years, the Linked Open Data (LOD) has evolved from a mere 12 to more than 10, 000 knowledge bases. These knowledge bases come from diverse domains including (but not limited to) publications, life sciences, social networking, government, media, linguistics. Moreover, the LOD cloud also contains a large number of crossdomain knowledge bases such as DBpedia and Yago2. These knowledge bases are commonly managed in a decentralized fashion and contain partly overlapping information. This architectural choice has led to knowledge pertaining to the same domain being published by independent entities in the LOD cloud. For example, information on drugs can be found in Diseasome as well as DBpedia and Drugbank. Furthermore, certain knowledge bases such as DBLP have been published by several bodies, which in turn has lead to duplicated content in the LOD. In addition, large amounts of geo-spatial information have been made available with the growth of heterogeneous Web of Data. The concurrent publication of knowledge bases containing related information promises to become a phenomenon of increasing importance with the growth of the number of independent data providers. Enabling the joint use of the knowledge bases published by these providers for tasks such as federated queries, cross-ontology question answering and data integration is most commonly tackled by creating links between the resources described within these knowledge bases. Within this thesis, we spur the transition from isolated knowledge bases to enriched Linked Data sets where information can be easily integrated and processed. To achieve this goal, we provide concepts, approaches and use cases that facilitate the integration and enrichment of information with other data types that are already present on the Linked Data Web with a focus on geo-spatial data. The first challenge that motivates our work is the lack of measures that use the geographic data for linking geo-spatial knowledge bases. This is partly due to the geo-spatial resources being described by the means of vector geometry. In particular, discrepancies in granularity and error measurements across knowledge bases render the selection of appropriate distance measures for geo-spatial resources difficult. We address this challenge by evaluating existing literature for pointset measures that can be used to measure the similarity of vector geometries. Then, we present and evaluate the ten measures that we derived from the literature on samples of three real knowledge bases. The second challenge we address in this thesis is the lack of automatic Link Discovery (LD) approaches capable of dealing with geospatial knowledge bases with missing and erroneous data. To this end,we present Colibri, an unsupervised approach that allows discovering links between knowledge bases while improving the quality of the instance data in these knowledge bases. A Colibri iteration begins by generating links between knowledge bases. Then, the approach makes use of these links to detect resources with probably erroneous or missing information. This erroneous or missing infor- mation detected by the approach is finally corrected or added. The third challenge we address is the lack of scalable LD approaches for tackling big geo-spatial knowledge bases. Thus, we present Deterministic Particle-Swarm Optimization (DPSO), a novel load balancing technique for LD on parallel hardware based on particle-swarm optimization. We combine this approach with the Orchid algorithm for geo-spatial linking and evaluate it on real and artificial data sets. The lack of approaches for automatic updating of links of an evolving knowledge base is our fourth challenge. This challenge is addressed in this thesis by the Wombat algorithm. Wombat is a novel approach for the discovery of links between knowledge bases that relies exclusively on positive examples. Wombat is based on generalisation via an upward refinement operator to traverse the space of Link Specifications (LS). We study the theoretical characteristics of Wombat and evaluate it on different benchmark data sets. The last challenge addressed herein is the lack of automatic approaches for geo-spatial knowledge base enrichment. Thus, we propose Deer, a supervised learning approach based on a refinement operator for enriching Resource Description Framework (RDF) data sets. We show how we can use exemplary descriptions of enriched resources to generate accurate enrichment pipelines. We evaluate our approach against manually defined enrichment pipelines and show that our approach can learn accurate pipelines even when provided with a small number of training examples. Each of the proposed approaches is implemented and evaluated against state-of-the-art approaches on real and/or artificial data sets. Moreover, all approaches are peer-reviewed and published in a con- ference or a journal paper. Throughout this thesis, we detail the ideas, implementation and the evaluation of each of the approaches. Moreover, we discuss each approach and present lessons learned. Finally, we conclude this thesis by presenting a set of possible future extensions and use cases for each of the proposed approaches. |
Georgala, Kleanthi; Sherif, Mohamed Ahmed; Ngomo, Axel-Cyrille Ngonga An Efficient Approach for the Generation of Allen Relations Inproceedings ECAI 2016 - 22nd European Conference on Artificial Intelligence,
29 August-2 September 2016, The Hague, The Netherlands - Including
Prestigious Applications of Artificial Intelligence (PAIS 2016), pp. 948–956, IOS Press, 2016. Links | BibTeX @inproceedings{DBLP:conf/ecai/GeorgalaSN16,
title = {An Efficient Approach for the Generation of Allen Relations},
author = {Kleanthi Georgala and
Mohamed Ahmed Sherif and
Axel-Cyrille Ngonga Ngomo},
url = {http://svn.aksw.org/papers/2016/ECAI_AEGLE/public.pdf},
doi = {10.3233/978-1-61499-672-9-948},
year = {2016},
date = {2016-01-01},
booktitle = {ECAI 2016 - 22nd European Conference on Artificial Intelligence,
29 August-2 September 2016, The Hague, The Netherlands - Including
Prestigious Applications of Artificial Intelligence (PAIS 2016)},
volume = {285},
pages = {948--956},
publisher = {IOS Press},
series = {Frontiers in Artificial Intelligence and Applications},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Sherif, Mohamed Ahmed; Hassan, Mofeed M; Soru, Tommaso; Ngomo, Axel-Cyrille Ngonga; Lehmann, Jens Lion's Den: feeding the LinkLion Inproceedings Proceedings of the 11th International Workshop on Ontology Matching
co-located with the 15th International Semantic Web Conference (ISWC
2016), Kobe, Japan, October 18, 2016, pp. 235–236, CEUR-WS.org, 2016. Links | BibTeX @inproceedings{DBLP:conf/semweb/SherifHSNL16,
title = {Lion's Den: feeding the LinkLion},
author = {Mohamed Ahmed Sherif and
Mofeed M. Hassan and
Tommaso Soru and
Axel-Cyrille Ngonga Ngomo and
Jens Lehmann},
url = {http://ceur-ws.org/Vol-1766/om2016_poster5.pdf},
year = {2016},
date = {2016-01-01},
booktitle = {Proceedings of the 11th International Workshop on Ontology Matching
co-located with the 15th International Semantic Web Conference (ISWC
2016), Kobe, Japan, October 18, 2016},
volume = {1766},
pages = {235--236},
publisher = {CEUR-WS.org},
series = {CEUR Workshop Proceedings},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
2015
|
Lehmann, Jens; Athanasiou, Spiros; Both, Andreas; Buehmann, Lorenz; Garcia-Rojas, Alejandra; Giannopoulos, Giorgos; Hladky, Daniel; Hoeffner, Konrad; Grange, Jon Jay Le; Ngomo, Axel-Cyrille Ngonga; Pietzsch, Rene; Isele, Robert; Sherif, Mohamed Ahmed; Stadler, Claus; Wauer, Matthias; Westphal, Patrick The GeoKnow Handbook Technical Report 2015. Links | BibTeX @techreport{geoknow_handbook,
title = {The GeoKnow Handbook},
author = {Jens Lehmann and Spiros Athanasiou and Andreas Both and Lorenz Buehmann and Alejandra Garcia-Rojas and Giorgos Giannopoulos and Daniel Hladky and Konrad Hoeffner and Jon Jay Le Grange and Axel-Cyrille Ngonga Ngomo and Rene Pietzsch and Robert Isele and Mohamed Ahmed Sherif and Claus Stadler and Matthias Wauer and Patrick Westphal},
url = {http://jens-lehmann.org/files/2015/geoknow_handbook.pdf},
year = {2015},
date = {2015-01-01},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
|
Sherif, Mohamed Ahmed; Ngomo, Axel-Cyrille Ngonga; Lehmann, Jens Automating RDF Dataset Transformation and Enrichment Inproceedings The Semantic Web. Latest Advances and New Domains - 12th European
Semantic Web Conference, ESWC 2015, Portoroz, Slovenia, May 31 -
June 4, 2015. Proceedings, pp. 371–387, Springer, 2015. Abstract | Links | BibTeX @inproceedings{DBLP:conf/esws/SherifNL15,
title = {Automating RDF Dataset Transformation and Enrichment},
author = {Mohamed Ahmed Sherif and
Axel-Cyrille Ngonga Ngomo and
Jens Lehmann},
url = {http://svn.aksw.org/papers/2015/ESWC_DEER/public.pdf},
doi = {10.1007/978-3-319-18818-8_23},
year = {2015},
date = {2015-01-01},
booktitle = {The Semantic Web. Latest Advances and New Domains - 12th European
Semantic Web Conference, ESWC 2015, Portoroz, Slovenia, May 31 -
June 4, 2015. Proceedings},
volume = {9088},
pages = {371--387},
publisher = {Springer},
series = {Lecture Notes in Computer Science},
abstract = {With the adoption of RDF across several domains, come growing requirements pertaining to the completeness and quality of RDF datasets. Currently, this problem is most commonly addressed by manually devising means of enriching an input dataset. The few tools that aim at supporting this endeavour usually focus on supporting the manual definition of enrichment pipelines. In this paper, we present a supervised learning approach based on a refinement operator for enriching RDF datasets. We show how we can use exemplary descriptions of enriched resources to generate accurate enrichment pipelines. We evaluate our approach against eight manually defined enrichment pipelines and show that our approach can learn accurate pipelines even when provided with a small number of training examples.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
With the adoption of RDF across several domains, come growing requirements pertaining to the completeness and quality of RDF datasets. Currently, this problem is most commonly addressed by manually devising means of enriching an input dataset. The few tools that aim at supporting this endeavour usually focus on supporting the manual definition of enrichment pipelines. In this paper, we present a supervised learning approach based on a refinement operator for enriching RDF datasets. We show how we can use exemplary descriptions of enriched resources to generate accurate enrichment pipelines. We evaluate our approach against eight manually defined enrichment pipelines and show that our approach can learn accurate pipelines even when provided with a small number of training examples. |
Sherif, Mohamed Ahmed; Ngomo, Axel-Cyrille Ngonga An optimization approach for load balancing in parallel link discovery Inproceedings Proceedings of the 11th International Conference on Semantic Systems,
SEMANTICS 2015, Vienna, Austria, September 15-17, 2015, pp. 161–168, ACM, 2015. Links | BibTeX @inproceedings{DBLP:conf/i-semantics/SherifN15,
title = {An optimization approach for load balancing in parallel link discovery},
author = {Mohamed Ahmed Sherif and
Axel-Cyrille Ngonga Ngomo},
url = {http://svn.aksw.org/papers/2015/SEMANTICS_DPSO/public.pdf},
doi = {10.1145/2814864.2814872},
year = {2015},
date = {2015-01-01},
booktitle = {Proceedings of the 11th International Conference on Semantic Systems,
SEMANTICS 2015, Vienna, Austria, September 15-17, 2015},
pages = {161--168},
publisher = {ACM},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Stadler, Claus; Unbehauen, Jörg; Westphal, Patrick; Sherif, Mohamed Ahmed; Lehmann, Jens Simplified RDB2RDF Mapping Inproceedings Proceedings of the Workshop on Linked Data on the Web, LDOW 2015,
co-located with the 24th International World Wide Web Conference (WWW
2015), Florence, Italy, May 19th, 2015, CEUR-WS.org, 2015. Abstract | Links | BibTeX @inproceedings{DBLP:conf/www/StadlerUWSL15,
title = {Simplified RDB2RDF Mapping},
author = {Claus Stadler and
Jörg Unbehauen and
Patrick Westphal and
Mohamed Ahmed Sherif and
Jens Lehmann},
url = {svn.aksw.org/papers/2015/LDOW_SML/paper-camery-ready_public.pdf},
year = {2015},
date = {2015-01-01},
booktitle = {Proceedings of the Workshop on Linked Data on the Web, LDOW 2015,
co-located with the 24th International World Wide Web Conference (WWW
2015), Florence, Italy, May 19th, 2015},
volume = {1409},
publisher = {CEUR-WS.org},
series = {CEUR Workshop Proceedings},
abstract = {The combination of the advantages of widely used relational databases and semantic technologies has attracted significant research over the past decade. In particular, mapping languages for the conversion of databases to RDF knowledge bases have been developed and standardized in the form of R2RML. In this article, we first review those mapping languages and then devise work towards a unified formal model for them. Based on this, we present the Sparqlification Mapping Language (SML), which provides an intuitive way to declare mappings based on SQL VIEWS and SPARQL construct queries. We show that SML has the same expressivity as R2RML by enumerating the language features and show the correspondences, and we outline how one syntax can be converted into the other. A conducted user study for this paper juxtaposing SML and R2RML provides evidence that SML is a more compact syntax which is easier to understand and read and thus lowers the barrier to offer SPARQL access to relational databases.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
The combination of the advantages of widely used relational databases and semantic technologies has attracted significant research over the past decade. In particular, mapping languages for the conversion of databases to RDF knowledge bases have been developed and standardized in the form of R2RML. In this article, we first review those mapping languages and then devise work towards a unified formal model for them. Based on this, we present the Sparqlification Mapping Language (SML), which provides an intuitive way to declare mappings based on SQL VIEWS and SPARQL construct queries. We show that SML has the same expressivity as R2RML by enumerating the language features and show the correspondences, and we outline how one syntax can be converted into the other. A conducted user study for this paper juxtaposing SML and R2RML provides evidence that SML is a more compact syntax which is easier to understand and read and thus lowers the barrier to offer SPARQL access to relational databases. |
Lehmann, Jens; Athanasiou, Spiros; Both, Andreas; 'i, Alejandra Garc; Giannopoulos, Giorgos; Hladky, Daniel; Grange, Jon Jay Le; Ngomo, Axel-Cyrille Ngonga; Sherif, Mohamed Ahmed; Stadler, Claus; Wauer, Matthias; Westphal, Patrick; Zaslawski, Vadim Managing Geospatial Linked Data in the GeoKnow Project Incollection The Semantic Web in Earth and Space Science. Current Status and Future
Directions, 20 , pp. 51–78, IOS Press, 2015. Links | BibTeX @incollection{DBLP:books/ios/p/LehmannABGGHGNSSWWZ15,
title = {Managing Geospatial Linked Data in the GeoKnow Project},
author = {Jens Lehmann and
Spiros Athanasiou and
Andreas Both and
Alejandra Garc{'i}a-Rojas and
Giorgos Giannopoulos and
Daniel Hladky and
Jon Jay Le Grange and
Axel-Cyrille Ngonga Ngomo and
Mohamed Ahmed Sherif and
Claus Stadler and
Matthias Wauer and
Patrick Westphal and
Vadim Zaslawski},
url = {http://jens-lehmann.org/files/2015/ios_geoknow_chapter.pdf},
doi = {10.3233/978-1-61499-501-2-51},
year = {2015},
date = {2015-01-01},
booktitle = {The Semantic Web in Earth and Space Science. Current Status and Future
Directions},
volume = {20},
pages = {51--78},
publisher = {IOS Press},
series = {Studies on the Semantic Web},
keywords = {},
pubstate = {published},
tppubtype = {incollection}
}
|
Sherif, Mohamed Ahmed; Ngomo, Axel-Cyrille Ngonga Semantic Quran Journal Article Semantic Web, 6 (4), pp. 339–345, 2015. Links | BibTeX @article{DBLP:journals/semweb/SherifN15,
title = {Semantic Quran},
author = {Mohamed Ahmed Sherif and
Axel-Cyrille Ngonga Ngomo},
url = {https://doi.org/10.3233/SW-140137},
doi = {10.3233/SW-140137},
year = {2015},
date = {2015-01-01},
journal = {Semantic Web},
volume = {6},
number = {4},
pages = {339--345},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
|
2014
|
Grange, Jon Jay Le; Lehmann, Jens; Athanasiou, Spiros; Rojas, Alejandra Garcia; Giannopoulos, Giorgos; Hladky, Daniel; Isele, Robert; Ngomo, Axel-Cyrille Ngonga; Sherif, Mohamed Ahmed; Stadler, Claus; Wauer, Matthias The GeoKnow Generator: Managing Geospatial Data in the Linked Data Web Inproceedings Proceedings of the Linking Geospatial Data Workshop, 2014. Links | BibTeX @inproceedings{lgd_geoknow_generator,
title = {The GeoKnow Generator: Managing Geospatial Data in the Linked Data Web},
author = {Jon Jay Le Grange and Jens Lehmann and Spiros Athanasiou and Alejandra Garcia Rojas and Giorgos Giannopoulos and Daniel Hladky and Robert Isele and Axel-Cyrille Ngonga Ngomo and Mohamed Ahmed Sherif and Claus Stadler and Matthias Wauer},
url = {http://jens-lehmann.org/files/2014/lgd_geoknow_generator.pdf},
year = {2014},
date = {2014-01-01},
booktitle = {Proceedings of the Linking Geospatial Data Workshop},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Sherif, Mohamed Ahmed; Ngomo, Axel-Cyrille Ngonga Semantic Quran: A Multilingual Resource for Natural-Language Processing Journal Article Semantic Web Journal, XXX , pp. 1-5, 2014. Abstract | Links | BibTeX @article{SHNG14,
title = {Semantic Quran: A Multilingual Resource for Natural-Language Processing},
author = {Mohamed Ahmed Sherif and Axel-Cyrille Ngonga Ngomo},
url = {http://www.semantic-web-journal.net/system/files/swj503.pdf},
year = {2014},
date = {2014-01-01},
journal = {Semantic Web Journal},
volume = {XXX},
pages = {1-5},
abstract = {In this paper we describe the Semantic Quran dataset, a multilingual RDF representation of translations of the Quran. The dataset was created by integrating data from two different semi-structured sources and aligned to an ontology designed to represent multilingual data from sources with a hierarchical structure. The resulting RDF data encompasses 43 different languages which belong to the most under-represented languages in the Linked Data Cloud, including Arabic, Amharic and Amazigh. We designed the dataset to be easily usable in natural-language processing applications with the goal of facilitating the development of knowledge extraction tools for these languages. In particular, the Semantic Quran is compatible with the Natural-Language Interchange Format and contains explicit morpho-syntactic information on the utilized terms. We present the ontology devised for structuring the data. We also provide the transformation rules implemented in our extraction framework. Finally, we detail the link creation process as well as possible usage scenarios for the Semantic Quran dataset.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
In this paper we describe the Semantic Quran dataset, a multilingual RDF representation of translations of the Quran. The dataset was created by integrating data from two different semi-structured sources and aligned to an ontology designed to represent multilingual data from sources with a hierarchical structure. The resulting RDF data encompasses 43 different languages which belong to the most under-represented languages in the Linked Data Cloud, including Arabic, Amharic and Amazigh. We designed the dataset to be easily usable in natural-language processing applications with the goal of facilitating the development of knowledge extraction tools for these languages. In particular, the Semantic Quran is compatible with the Natural-Language Interchange Format and contains explicit morpho-syntactic information on the utilized terms. We present the ontology devised for structuring the data. We also provide the transformation rules implemented in our extraction framework. Finally, we detail the link creation process as well as possible usage scenarios for the Semantic Quran dataset. |
Ngomo, Axel-Cyrille Ngonga; Sherif, Mohamed Ahmed; Lyko, Klaus Unsupervised Link Discovery through Knowledge Base Repair Inproceedings The Semantic Web: Trends and Challenges - 11th International Conference,
ESWC 2014, Anissaras, Crete, Greece, May 25-29, 2014. Proceedings, pp. 380–394, Springer, 2014. Links | BibTeX @inproceedings{DBLP:conf/esws/NgomoSL14,
title = {Unsupervised Link Discovery through Knowledge Base Repair},
author = {Axel-Cyrille Ngonga Ngomo and
Mohamed Ahmed Sherif and
Klaus Lyko},
url = {http://svn.aksw.org/papers/2013/ISWC_CHIMERA/public.pdf},
doi = {10.1007/978-3-319-07443-6_26},
year = {2014},
date = {2014-01-01},
booktitle = {The Semantic Web: Trends and Challenges - 11th International Conference,
ESWC 2014, Anissaras, Crete, Greece, May 25-29, 2014. Proceedings},
volume = {8465},
pages = {380--394},
publisher = {Springer},
series = {Lecture Notes in Computer Science},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Sherif, Mohamed Ahmed; Coelho, Sandro; Usbeck, Ricardo; Hellmann, Sebastian; Lehmann, Jens; Brümmer, Martin; Both, Andreas NIF4OGGD - NLP Interchange Format for Open German Governmental Data Inproceedings Proceedings of the Ninth International Conference on Language Resources
and Evaluation, LREC 2014, Reykjavik, Iceland, May 26-31, 2014, pp. 3524–3528, European Language Resources Association (ELRA), 2014. Links | BibTeX @inproceedings{DBLP:conf/lrec/SherifCUHLBB14,
title = {NIF4OGGD - NLP Interchange Format for Open German Governmental Data},
author = {Mohamed Ahmed Sherif and
Sandro Coelho and
Ricardo Usbeck and
Sebastian Hellmann and
Jens Lehmann and
Martin Brümmer and
Andreas Both},
url = {http://www.lrec-conf.org/proceedings/lrec2014/summaries/780.html},
year = {2014},
date = {2014-01-01},
booktitle = {Proceedings of the Ninth International Conference on Language Resources
and Evaluation, LREC 2014, Reykjavik, Iceland, May 26-31, 2014},
pages = {3524--3528},
publisher = {European Language Resources Association (ELRA)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Pokharel, Suresh; Sherif, Mohamed Ahmed; Lehmann, Jens Ontology Based Data Access and Integration for Improving the Effectiveness
of Farming in Nepal Inproceedings 2014 IEEE/WIC/ACM International Joint Conferences on Web Intelligence
(WI) and Intelligent Agent Technologies (IAT), Warsaw, Poland, August
11-14, 2014 - Volume I, pp. 319–326, IEEE Computer Society, 2014. Links | BibTeX @inproceedings{DBLP:conf/webi/PokharelSL14,
title = {Ontology Based Data Access and Integration for Improving the Effectiveness
of Farming in Nepal},
author = {Suresh Pokharel and
Mohamed Ahmed Sherif and
Jens Lehmann},
url = {http://svn.aksw.org/papers/2014/WI2014_agriNepalData/public.pdf},
doi = {10.1109/WI-IAT.2014.114},
year = {2014},
date = {2014-01-01},
booktitle = {2014 IEEE/WIC/ACM International Joint Conferences on Web Intelligence
(WI) and Intelligent Agent Technologies (IAT), Warsaw, Poland, August
11-14, 2014 - Volume I},
pages = {319--326},
publisher = {IEEE Computer Society},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
2013
|
Zaveri, Amrapali; Kontokostas, Dimitris; Sherif, Mohamed Ahmed; Bühmann, Lorenz; Morsey, Mohamed; Auer, Sören; Lehmann, Jens User-driven quality evaluation of DBpedia Inproceedings I-SEMANTICS 2013 - 9th International Conference on Semantic Systems,
ISEM '13, Graz, Austria, September 4-6, 2013, pp. 97–104, ACM, 2013. Abstract | Links | BibTeX @inproceedings{DBLP:conf/i-semantics/ZaveriKSBMAL13,
title = {User-driven quality evaluation of DBpedia},
author = {Amrapali Zaveri and
Dimitris Kontokostas and
Mohamed Ahmed Sherif and
Lorenz Bühmann and
Mohamed Morsey and
Sören Auer and
Jens Lehmann},
url = {http://svn.aksw.org/papers/2013/ISemantics_DBpediaDQ/public.pdf},
doi = {10.1145/2506182.2506195},
year = {2013},
date = {2013-01-01},
booktitle = {I-SEMANTICS 2013 - 9th International Conference on Semantic Systems,
ISEM '13, Graz, Austria, September 4-6, 2013},
pages = {97--104},
publisher = {ACM},
abstract = {Linked Open Data (LOD) comprises of an unprecedented volume of structured datasets on the Web. However, these datasets are of varying quality ranging from extensively curated datasets to crowdsourced and even extracted data of relatively low quality. We present a methodology for assessing the quality of linked data resources, which comprises of a manual and a semi-automatic process. The first phase includes the detection of common quality problems and their representation in a quality problem taxonomy. In the manual process, the second phase comprises of the evaluation of a large number of individual resources, according to the quality problem taxonomy via crowdsourcing. This process is accompanied by a tool wherein a user assesses an individual resource and evaluates each fact for correctness. The semi-automatic process involves the generation and verification of schema axioms. We report the results obtained by applying this methodology to DBpedia. We identified 17 data quality problem types and 58 users assessed a total of 521 resources. Overall, 11.93% of the evaluated DBpedia triples were identified to have some quality issues. Applying the semi-automatic component yielded a total of 222,982 triples that have a high probability to be incorrect. In particular, we found that problems such as object values being incorrectly extracted, irrelevant extraction of information and broken links were the most recurring quality problems. With this study, we not only aim to assess the quality of this sample of DBpedia resources but also adopt an agile methodology to improve the quality in future versions by regularly providing feedback to the DBpedia maintainers.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Linked Open Data (LOD) comprises of an unprecedented volume of structured datasets on the Web. However, these datasets are of varying quality ranging from extensively curated datasets to crowdsourced and even extracted data of relatively low quality. We present a methodology for assessing the quality of linked data resources, which comprises of a manual and a semi-automatic process. The first phase includes the detection of common quality problems and their representation in a quality problem taxonomy. In the manual process, the second phase comprises of the evaluation of a large number of individual resources, according to the quality problem taxonomy via crowdsourcing. This process is accompanied by a tool wherein a user assesses an individual resource and evaluates each fact for correctness. The semi-automatic process involves the generation and verification of schema axioms. We report the results obtained by applying this methodology to DBpedia. We identified 17 data quality problem types and 58 users assessed a total of 521 resources. Overall, 11.93% of the evaluated DBpedia triples were identified to have some quality issues. Applying the semi-automatic component yielded a total of 222,982 triples that have a high probability to be incorrect. In particular, we found that problems such as object values being incorrectly extracted, irrelevant extraction of information and broken links were the most recurring quality problems. With this study, we not only aim to assess the quality of this sample of DBpedia resources but also adopt an agile methodology to improve the quality in future versions by regularly providing feedback to the DBpedia maintainers. |