@inproceedings{chrupala2010named, author = {Chrupala, Grzegorz and Klakow, Dietrich}, booktitle = {LREC}, crossref = {conf/lrec/2010}, editor = {Calzolari, Nicoletta and Choukri, Khalid and Maegaard, Bente and Mariani, Joseph and Odijk, Jan and Piperidis, Stelios and Rosner, Mike and Tapias, Daniel}, ee = {http://www.lrec-conf.org/proceedings/lrec2010/summaries/538.html}, interhash = {85b8f5e04b66df3fe9411fc8f81ae43a}, intrahash = {68b98f37dc2dd0a89f580d9e6b65c780}, isbn = {2-9517408-6-7}, publisher = {European Language Resources Association}, title = {A Named Entity Labeler for German: Exploiting Wikipedia and Distributional Clusters.}, url = {http://lexitron.nectec.or.th/public/LREC-2010_Malta/pdf/538_Paper.pdf}, year = 2010 } @inproceedings{mendes2011dbpedia, abstract = {Interlinking text documents with Linked Open Data enables the Web of Data to be used as background knowledge within document-oriented applications such as search and faceted browsing. As a step towards interconnecting the Web of Documents with the Web of Data, we developed DBpedia Spotlight, a system for automatically annotating text documents with DBpedia URIs. DBpedia Spotlight allows users to configure the annotations to their specific needs through the DBpedia Ontology and quality measures such as prominence, topical pertinence, contextual ambiguity and disambiguation confidence. We compare our approach with the state of the art in disambiguation, and evaluate our results in light of three baselines and six publicly available annotation systems, demonstrating the competitiveness of our system. DBpedia Spotlight is shared as open source and deployed as a Web Service freely available for public use.}, acmid = {2063519}, address = {New York, NY, USA}, author = {Mendes, Pablo N. and Jakob, Max and García-Silva, Andrés and Bizer, Christian}, booktitle = {Proceedings of the 7th International Conference on Semantic Systems}, doi = {10.1145/2063518.2063519}, interhash = {92df08698e5608afc6dc5b3e9be76880}, intrahash = {58fbb395741cce1d5370a6f205f24843}, isbn = {978-1-4503-0621-8}, location = {Graz, Austria}, numpages = {8}, pages = {1--8}, publisher = {ACM}, title = {DBpedia spotlight: shedding light on the web of documents}, url = {http://doi.acm.org/10.1145/2063518.2063519}, year = 2011 } @inproceedings{mihalcea2007wikify, abstract = {This paper introduces the use of Wikipedia as a resource for automatic keyword extraction and word sense disambiguation, and shows how this online encyclopedia can be used to achieve state-of-the-art results on both these tasks. The paper also shows how the two methods can be combined into a system able to automatically enrich a text with links to encyclopedic knowledge. Given an input document, the system identifies the important concepts in the text and automatically links these concepts to the corresponding Wikipedia pages. Evaluations of the system show that the automatic annotations are reliable and hardly distinguishable from manual annotations.}, acmid = {1321475}, address = {New York, NY, USA}, author = {Mihalcea, Rada and Csomai, Andras}, booktitle = {Proceedings of the sixteenth ACM Conference on information and knowledge management}, doi = {10.1145/1321440.1321475}, interhash = {8e00f4c1515b89a9a035c9d4b78d7bed}, intrahash = {4917a0c8eb1ea05b2d103166dfaeeb6e}, isbn = {978-1-59593-803-9}, location = {Lisbon, Portugal}, numpages = {10}, pages = {233--242}, publisher = {ACM}, title = {Wikify!: linking documents to encyclopedic knowledge}, url = {http://doi.acm.org/10.1145/1321440.1321475}, year = 2007 } @inproceedings{gunes2012eager, abstract = {Key to named entity recognition, the manual gazetteering of entity lists is a costly, errorprone process that often yields results that are incomplete and suffer from sampling bias. Exploiting current sources of structured information, we propose a novel method for extending minimal seed lists into complete gazetteers. Like previous approaches, we value W IKIPEDIA as a huge, well-curated, and relatively unbiased source of entities. However, in contrast to previous work, we exploit not only its content, but also its structure, as exposed in DBPEDIA. We extend gazetteers through Wikipedia categories, carefully limiting the impact of noisy categorizations. The resulting gazetteers easily outperform previous approaches on named entity recognition. }, author = {Gunes, Omer and Schallhart, Christian and Furche, Tim and Lehmann, Jens and Ngomo, Axel-Cyrille Ngonga}, booktitle = {Proceedings of the 3rd Workshop on the People's Web Meets NLP: Collaboratively Constructed Semantic Resources and their Applications to NLP}, interhash = {20c47a41c89ff6c2a8f7bb524185b8ac}, intrahash = {3eac4c009268cd4f2c264dd24053f8a6}, month = jul, organization = {Association for Computational Linguistics}, pages = {29--33}, title = {EAGER: extending automatically gazetteers for entity recognition}, url = {http://acl.eldoc.ub.rug.nl/mirror/W/W12/W12-4005.pdf}, year = 2012 } @inproceedings{finin2010annotating, abstract = {We describe our experience using both Amazon Mechanical Turk (MTurk) and Crowd-Flower to collect simple named entity annotations for Twitter status updates. Unlike most genres that have traditionally been the focus of named entity experiments, Twitter is far more informal and abbreviated. The collected annotations and annotation techniques will provide a first step towards the full study of named entity recognition in domains like Facebook and Twitter. We also briefly describe how to use MTurk to collect judgements on the quality of "word clouds."}, acmid = {1866709}, address = {Stroudsburg, PA, USA}, author = {Finin, Tim and Murnane, Will and Karandikar, Anand and Keller, Nicholas and Martineau, Justin and Dredze, Mark}, booktitle = {Proceedings of the NAACL HLT 2010 Workshop on Creating Speech and Language Data with Amazon's Mechanical Turk}, interhash = {0fa9636e69f2f516cdb6e11fffd8079b}, intrahash = {f3ce5c15752dab9487220a3aae963655}, location = {Los Angeles, California}, numpages = {9}, pages = {80--88}, publisher = {Association for Computational Linguistics}, title = {Annotating named entities in Twitter data with crowdsourcing}, url = {http://dl.acm.org/citation.cfm?id=1866696.1866709}, year = 2010 }