{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T04:12:03Z","timestamp":1750306323683,"version":"3.41.0"},"publisher-location":"New York, New York, USA","reference-count":49,"publisher":"ACM Press","license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Science Foundation","award":["IIS-1320617","IIS-1017362"],"award-info":[{"award-number":["IIS-1320617","IIS-1017362"]}]},{"name":"U.S. Army Research Lab.","award":["W911NF-09-2-0053"],"award-info":[{"award-number":["W911NF-09-2-0053"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016]]},"DOI":"10.1145\/2872518.2891065","type":"proceedings-article","created":{"date-parts":[[2017,1,23]],"date-time":"2017-01-23T20:35:52Z","timestamp":1485203752000},"page":"1025-1028","source":"Crossref","is-referenced-by-count":6,"title":["Automatic Entity Recognition and Typing in Massive Text Corpora"],"prefix":"10.1145","author":[{"given":"Xiang","family":"Ren","sequence":"first","affiliation":[{"name":"University of Illinois at Urbana-Champaign, Urbana, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ahmed","family":"El-Kishky","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, Urbana, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chi","family":"Wang","sequence":"additional","affiliation":[{"name":"Microsoft Research, Redmond, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiawei","family":"Han","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, URBANA, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","reference":[{"key":"key-10.1145\/2872518.2891065-1","doi-asserted-by":"crossref","unstructured":"R. K. Ando and T. Zhang. A high-performance semi-supervised learning method for text chunking. In ACL, 2005.","DOI":"10.3115\/1219840.1219841"},{"key":"key-10.1145\/2872518.2891065-2","doi-asserted-by":"crossref","unstructured":"S. Auer, C. Bizer, G. Kobilarov, J. Lehmann, R. Cyganiak, and Z. Ives. Dbpedia: A nucleus for a web of open data. Springer, 2007.","DOI":"10.1007\/978-3-540-76298-0_52"},{"key":"key-10.1145\/2872518.2891065-3","doi-asserted-by":"crossref","unstructured":"D. M. Bikel, R. Schwartz, and R. M. Weischedel. An algorithm that learns what's in a name. Machine learning, 34(1--3):211--231, 1999.","DOI":"10.1023\/A:1007558221122"},{"key":"key-10.1145\/2872518.2891065-4","doi-asserted-by":"crossref","unstructured":"A. Blum and T. Mitchell. Combining labeled and unlabeled data with co-training. In COLT Workshop on Computational Learning Theory, 1998.","DOI":"10.1145\/279943.279962"},{"key":"key-10.1145\/2872518.2891065-5","doi-asserted-by":"crossref","unstructured":"K. Bollacker, C. Evans, P. Paritosh, T. Sturge, and J. Taylor. Freebase: a collaboratively created graph database for structuring human knowledge. In SIGMOD, 2008.","DOI":"10.1145\/1376616.1376746"},{"key":"key-10.1145\/2872518.2891065-6","doi-asserted-by":"crossref","unstructured":"A. Carlson, J. Betteridge, R. C. Wang, E. R. Hruschka Jr, and T. M. Mitchell. Coupled semi-supervised learning for information extraction. In WSDM, 2010.","DOI":"10.1145\/1718487.1718501"},{"key":"key-10.1145\/2872518.2891065-7","doi-asserted-by":"crossref","unstructured":"W. W. Cohen and S. Sarawagi. Exploiting dictionaries in named entity extraction: combining semi-markov extraction processes and data integration methods. In SIGKDD, 2004.","DOI":"10.1145\/1014052.1014065"},{"key":"key-10.1145\/2872518.2891065-8","doi-asserted-by":"crossref","unstructured":"M. Collins. Ranking algorithms for named-entity extraction: Boosting and the voted perceptron. In Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, pages 489--496. Association for Computational Linguistics, 2002.","DOI":"10.3115\/1073083.1073165"},{"key":"key-10.1145\/2872518.2891065-9","doi-asserted-by":"crossref","unstructured":"J. R. Curran and S. Clark. Language independent ner using a maximum entropy tagger. In HLT-NAACL, 2003.","DOI":"10.3115\/1119176.1119200"},{"key":"key-10.1145\/2872518.2891065-10","doi-asserted-by":"crossref","unstructured":"B. B. Dalvi, W. W. Cohen, and J. Callan. Websets: Extracting sets of entities from the web using unsupervised information extraction. In WSDM, 2012.","DOI":"10.1145\/2124295.2124327"},{"key":"key-10.1145\/2872518.2891065-11","doi-asserted-by":"crossref","unstructured":"X. L. Dong, T. Strohmann, S. Sun, and W. Zhang. Knowledge vault: A web-scale approach to probabilistic knowledge fusion. In SIGKDD, 2014.","DOI":"10.1145\/2623330.2623623"},{"key":"key-10.1145\/2872518.2891065-12","doi-asserted-by":"crossref","unstructured":"A. El-Kishky, Y. Song, C. Wang, C. R. Voss, and J. Han. Scalable topical phrase mining from text corpora. VLDB, 2015.","DOI":"10.14778\/2735508.2735519"},{"key":"key-10.1145\/2872518.2891065-13","doi-asserted-by":"crossref","unstructured":"O. Etzioni, M. Cafarella, D. Downey, A.-M. Popescu, T. Shaked, S. Soderland, D. S. Weld, and A. Yates. Unsupervised named-entity extraction from the web: An experimental study. Artificial Intelligence, 165(1):91--134, 2005.","DOI":"10.1016\/j.artint.2005.03.001"},{"key":"key-10.1145\/2872518.2891065-14","unstructured":"A. Fader, S. Soderland, and O. Etzioni. Identifying relations for open information extraction. In EMNLP, 2011."},{"key":"key-10.1145\/2872518.2891065-15","doi-asserted-by":"crossref","unstructured":"J. R. Finkel, T. Grenager, and C. Manning. Incorporating non-local information into information extraction systems by gibbs sampling. In ACL, 2005.","DOI":"10.3115\/1219840.1219885"},{"key":"key-10.1145\/2872518.2891065-16","doi-asserted-by":"crossref","unstructured":"V. Ganti, A. C. König, and R. Vernica. Entity categorization over large document collections. In SIGKDD, 2008.","DOI":"10.1145\/1401890.1401927"},{"key":"key-10.1145\/2872518.2891065-17","doi-asserted-by":"crossref","unstructured":"W. Gao, P. Li, and K. Darwish. Joint topic modeling for event summarization across news and social media streams. In CIKM, 2012.","DOI":"10.1145\/2396761.2398417"},{"key":"key-10.1145\/2872518.2891065-18","doi-asserted-by":"crossref","unstructured":"A. Gattani, D. S. Lamba, N. Garera, M. Tiwari, X. Chai, S. Das, S. Subramaniam, A. Rajaraman, V. Harinarayan, and A. Doan. Entity extraction, linking, classification, and tagging for social media: a wikipedia-based approach. VLDB, 6(11):1126--1137, 2013.","DOI":"10.14778\/2536222.2536237"},{"key":"key-10.1145\/2872518.2891065-19","unstructured":"W. Guo, H. Li, Ji, and M. T. Diab. Linking tweets to news: A framework to enrich short text data in social media. In ACL, 2013."},{"key":"key-10.1145\/2872518.2891065-20","doi-asserted-by":"crossref","unstructured":"S. Gupta and C. D. Manning. Improved pattern learning for bootstrapped entity extraction. In CONLL, 2014.","DOI":"10.3115\/v1\/W14-1611"},{"key":"key-10.1145\/2872518.2891065-21","doi-asserted-by":"crossref","unstructured":"Y. He and D. Xin. Seisa: set expansion by iterative similarity aggregation. In WWW, 2011.","DOI":"10.1145\/1963405.1963467"},{"key":"key-10.1145\/2872518.2891065-22","unstructured":"R. Huang and E. Riloff. Inducing domain-specific semantic class taggers from (almost) nothing. In ACL, 2010."},{"key":"key-10.1145\/2872518.2891065-23","unstructured":"H. Ji and R. Grishman. Knowledge base population: Successful approaches and challenges. In ACL, 2011."},{"key":"key-10.1145\/2872518.2891065-24","doi-asserted-by":"crossref","unstructured":"D. S. Kim, K. Verma, and P. Z. Yeh. Joint extraction and labeling via graph propagation for dictionary construction. In AAAI, 2013.","DOI":"10.1609\/aaai.v27i1.8597"},{"key":"key-10.1145\/2872518.2891065-25","unstructured":"Z. Kozareva, K. Voevodski, and S.-H. Teng. Class label enhancement via related instances. In EMNLP, 2011."},{"key":"key-10.1145\/2872518.2891065-26","doi-asserted-by":"crossref","unstructured":"C. Li, J. Weng, Q. He, Y. Yao, A. Datta, A. Sun, and B.-S. Lee. Twiner: named entity recognition in targeted twitter stream. In SIGIR, 2012.","DOI":"10.1145\/2348283.2348380"},{"key":"key-10.1145\/2872518.2891065-27","doi-asserted-by":"crossref","unstructured":"Q. Li and H. Ji. Incremental joint extraction of entity mentions and relations. In ACL, 2014.","DOI":"10.3115\/v1\/P14-1038"},{"key":"key-10.1145\/2872518.2891065-28","doi-asserted-by":"crossref","unstructured":"G. Limaye, S. Sarawagi, and S. Chakrabarti. Annotating and searching web tables using entities, types and relationships. VLDB, 3(1--2):1338--1347, 2010.","DOI":"10.14778\/1920841.1921005"},{"key":"key-10.1145\/2872518.2891065-29","doi-asserted-by":"crossref","unstructured":"D. Lin and X. Wu. Phrase clustering for discriminative learning. In ACL, 2009.","DOI":"10.3115\/1690219.1690290"},{"key":"key-10.1145\/2872518.2891065-30","doi-asserted-by":"crossref","unstructured":"H. Lin, Y. Jia, Y. Wang, X. Jin, X. Li, and X. Cheng. Populating knowledge base with collective entity mentions: A graph-based approach. In ASONAM, 2014.","DOI":"10.1109\/ASONAM.2014.6921648"},{"key":"key-10.1145\/2872518.2891065-31","unstructured":"T. Lin, O. Etzioni, et al. No noun phrase left behind: detecting and typing unlinkable entities. In EMNLP, 2012."},{"key":"key-10.1145\/2872518.2891065-32","unstructured":"W. Lin, R. Yangarber, and R. Grishman. Bootstrapped learning of semantic classes from positive and negative examples. In ICML Workshop on The Continuum from Labeled to Unlabeled Data, 2003."},{"key":"key-10.1145\/2872518.2891065-33","unstructured":"X. Ling and D. S. Weld. Fine-grained entity recognition. In AAAI, 2012."},{"key":"key-10.1145\/2872518.2891065-34","doi-asserted-by":"crossref","unstructured":"J. Liu, J. Shang, C. Wang, X. Ren, and J. Han. Mining quality phrases from massive text corpora. In SIGMOD, 2015.","DOI":"10.1145\/2723372.2751523"},{"key":"key-10.1145\/2872518.2891065-35","unstructured":"A. McCallum, D. Freitag, and F. C. Pereira. Maximum entropy markov models for information extraction and segmentation. In ICML, volume 17, pages 591--598, 2000."},{"key":"key-10.1145\/2872518.2891065-36","doi-asserted-by":"crossref","unstructured":"P. McNamee and J. Mayfield. Entity extraction without language-specific resources. In COLING, 2002.","DOI":"10.3115\/1118853.1118873"},{"key":"key-10.1145\/2872518.2891065-37","doi-asserted-by":"crossref","unstructured":"D. Nadeau and S. Sekine. A survey of named entity recognition and classification. Lingvisticae Investigationes, 30(1):3--26, 2007.","DOI":"10.1075\/li.30.1.03nad"},{"key":"key-10.1145\/2872518.2891065-38","unstructured":"N. Nakashole, T. Tylenda, and G. Weikum. Fine-grained semantic typing of emerging entities. In ACL, 2013."},{"key":"key-10.1145\/2872518.2891065-39","doi-asserted-by":"crossref","unstructured":"K. Nigam and R. Ghani. Analyzing the effectiveness and applicability of co-training. In CIKM, 2000.","DOI":"10.1145\/354756.354805"},{"key":"key-10.1145\/2872518.2891065-40","doi-asserted-by":"crossref","unstructured":"L. Ratinov and D. Roth. Design challenges and misconceptions in named entity recognition. In ACL, 2009.","DOI":"10.3115\/1596374.1596399"},{"key":"key-10.1145\/2872518.2891065-41","doi-asserted-by":"crossref","unstructured":"X. Ren, A. El-Kishky, C. Wang, F. Tao, C. R. Voss, and J. Han. Clustype: Effective entity recognition and typing by relation phrase-based clustering. In SIGKDD, 2015.","DOI":"10.1145\/2783258.2783362"},{"key":"key-10.1145\/2872518.2891065-42","unstructured":"A. Ritter, S. Clark, O. Etzioni, et al. Named entity recognition in tweets: an experimental study. In EMNLP, 2011."},{"key":"key-10.1145\/2872518.2891065-43","unstructured":"W. Shen, J. Wang, and J. Han. Entity linking with a knowledge base: Issues, techniques, and solutions. TKDE, (99):1--20, 2014."},{"key":"key-10.1145\/2872518.2891065-44","doi-asserted-by":"crossref","unstructured":"W. Shen, J. Wang, P. Luo, and M. Wang. A graph-based approach for ontology population with named entities. In CIKM, 2012.","DOI":"10.1145\/2396761.2396807"},{"key":"key-10.1145\/2872518.2891065-45","doi-asserted-by":"crossref","unstructured":"Y. Sun and J. Han. Mining heterogeneous information networks: a structural analysis approach. SIGKDD Explorations, 14(2):20--28, 2013.","DOI":"10.1145\/2481244.2481248"},{"key":"key-10.1145\/2872518.2891065-46","doi-asserted-by":"crossref","unstructured":"P. P. Talukdar, T. Brants, M. Liberman, and F. Pereira. A context pattern induction method for named entity extraction. In CONLL, 2006.","DOI":"10.3115\/1596276.1596303"},{"key":"key-10.1145\/2872518.2891065-47","unstructured":"P. P. Talukdar and F. Pereira. Experiments in graph-based semi-supervised learning methods for class-instance acquisition. In ACL, 2010."},{"key":"key-10.1145\/2872518.2891065-48","unstructured":"J. Turian, L. Ratinov, and Y. Bengio. Word representations: a simple and general method for semi-supervised learning. In ACL, 2010."},{"key":"key-10.1145\/2872518.2891065-49","doi-asserted-by":"crossref","unstructured":"R. Yangarber, W. Lin, and R. Grishman. Unsupervised learning of generalized names. In COLING, 2002.","DOI":"10.3115\/1072228.1072382"}],"event":{"number":"25","sponsor":["SIGWEB, ACM Special Interest Group on Hypertext, Hypermedia, and Web","IW3C2, International World Wide Web Conference Committee"],"acronym":"WWW '16 Companion","name":"the 25th International Conference Companion","start":{"date-parts":[[2016,4,11]]},"location":"Montréal, Québec, Canada","end":{"date-parts":[[2016,4,15]]}},"container-title":["Proceedings of the 25th International Conference Companion on World Wide Web - WWW '16 Companion"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2872518.2891065","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/dl.acm.org\/ft_gateway.cfm?id=2891065&ftid=1707838&dwn=1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:54:23Z","timestamp":1750222463000},"score":1,"resource":{"primary":{"URL":"http:\/\/dl.acm.org\/citation.cfm?doid=2872518.2891065"}},"subtitle":[],"proceedings-subject":"World Wide Web","short-title":[],"issued":{"date-parts":[[2016]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1145\/2872518.2891065","relation":{},"subject":[],"published":{"date-parts":[[2016]]}}}