{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T07:06:16Z","timestamp":1778137576619,"version":"3.51.4"},"reference-count":62,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2017,7,1]],"date-time":"2017-07-01T00:00:00Z","timestamp":1498867200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2017,2,13]],"date-time":"2017-02-13T00:00:00Z","timestamp":1486944000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000266","name":"EPSRC","doi-asserted-by":"publisher","award":["EP\/K017896\/1"],"award-info":[{"award-number":["EP\/K017896\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computer Speech & Language"],"published-print":{"date-parts":[[2017,7]]},"DOI":"10.1016\/j.csl.2017.01.012","type":"journal-article","created":{"date-parts":[[2017,2,14]],"date-time":"2017-02-14T19:32:37Z","timestamp":1487100757000},"page":"61-83","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":40,"special_numbering":"C","title":["Generalisation in named entity recognition: A quantitative analysis"],"prefix":"10.1016","volume":"44","author":[{"given":"Isabelle","family":"Augenstein","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Leon","family":"Derczynski","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kalina","family":"Bontcheva","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.csl.2017.01.012_bib0001","series-title":"Proceedings of the Forty Annual Meeting on Association for Computational Linguistics","first-page":"400","article-title":"Translating named entities using monolingual and bilingual resources","author":"Al-Onaizan","year":"2002"},{"key":"10.1016\/j.csl.2017.01.012_bib0002","series-title":"Proceedings of the First Workshop on Vector Space Modeling for Natural Language Processing","first-page":"109","article-title":"DeepNL: a deep learning NLP pipeline","author":"Attardi","year":"2015"},{"key":"10.1016\/j.csl.2017.01.012_bib0060","doi-asserted-by":"crossref","unstructured":"Augenstein, I., 2014. Joint information extraction from the web using linked data. In Proceedings of the International Semantic Web Conference, Springer, pp. 505\u2013512.","DOI":"10.1007\/978-3-319-11915-1_32"},{"key":"10.1016\/j.csl.2017.01.012_bib0003","series-title":"Proceedings of the 2013 International Joint Conference on Natural Language Processing (IJCNLP)","first-page":"356","article-title":"How noisy social media text, how different social media sources?","author":"Baldwin","year":"2013"},{"key":"10.1016\/j.csl.2017.01.012_bib0004","series-title":"Proceedings of the 2015 Workshop on Noisy User-generated Text","first-page":"126","article-title":"Shared tasks of the 2015 workshop on noisy user-generated text: Twitter lexical normalization and named entity recognition","author":"Baldwin","year":"2015"},{"key":"10.1016\/j.csl.2017.01.012_bib0005","series-title":"Proceedings of the 2012 Workshop on Unsupervised and Transfer Learning Challenges in Machine Learning","first-page":"19","article-title":"Deep learning of representations for unsupervised and transfer learning","volume":"vol. 7","author":"Bengio","year":"2012"},{"key":"10.1016\/j.csl.2017.01.012_bib0006","series-title":"Proceedings of the 2008 ACM SIGMOD International Conference on Management of Data","first-page":"1247","article-title":"Freebase: a collaboratively created graph database for structuring human knowledge","author":"Bollacker","year":"2008"},{"key":"10.1016\/j.csl.2017.01.012_bib0007","series-title":"Proceedings of Recent Advances in Natural Language Processing","first-page":"83","article-title":"TwitIE: An Open-Source Information Extraction Pipeline for Microblog Text","author":"Bontcheva","year":"2014"},{"issue":"4","key":"10.1016\/j.csl.2017.01.012_bib0008","first-page":"467","article-title":"Class-based n-gram models of natural language","volume":"18","author":"Brown","year":"1992","journal-title":"Comput. Linguist."},{"key":"10.1016\/j.csl.2017.01.012_bib0009","series-title":"Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","first-page":"735","article-title":"The unreasonable effectiveness of word representations for Twitter named entity recognition","author":"Cherry","year":"2015"},{"key":"10.1016\/j.csl.2017.01.012_bib0010","series-title":"Proceedings of the Seventh Message Understanding Conference (MUC-7). Fairfax, VA","article-title":"Proceedings of the seventh message understanding conference (MUC-7) named entity task definition","author":"Chinchor","year":"1998"},{"key":"10.1016\/j.csl.2017.01.012_bib0011","series-title":"Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Cambridge, MA","first-page":"1002","article-title":"Domain adaptation of rule-based annotators for named-entity recognition tasks","author":"Chiticariu","year":"2010"},{"key":"10.1016\/j.csl.2017.01.012_bib0012","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1162\/tacl_a_00104","article-title":"Named entity recognition with bidirectional LSTM-SNNs","volume":"6","author":"Chiu","year":"2016","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"10.1016\/j.csl.2017.01.012_bib0013","first-page":"2493","article-title":"Natural language processing (almost) from scratch","volume":"999888","author":"Collobert","year":"2011","journal-title":"J. Mach. Learn. Res. (JMLR)"},{"key":"10.1016\/j.csl.2017.01.012_bib0014","series-title":"Proceedings of the Forty-fifth Annual Meeting of the Association of Computational Linguistics","first-page":"256","article-title":"Frustratingly Easy Domain Adaptation","author":"Daum\u00e9","year":"2007"},{"key":"10.1016\/j.csl.2017.01.012_bib0061","doi-asserted-by":"crossref","unstructured":"Derczynski, L., Augenstein, I., Bontcheva, K., 2015. USFD: Twitter NER with drift compensation and linked data. Proceedings of the Workshop on Noisy User-generated Text (W-NUT), pp. 48\u201353.","DOI":"10.18653\/v1\/W15-4306"},{"key":"10.1016\/j.csl.2017.01.012_bib0015","series-title":"Proceedings of the 2016 Annual Conference of the Association for Advancement of Artificial Intelligence","article-title":"Generalised Brown clustering and roll-up feature generation","author":"Derczynski","year":"2016"},{"key":"10.1016\/j.csl.2017.01.012_bib0016","series-title":"Proceedings of the Twenty-fourth ACM Conference on Hypertext and Social Media","first-page":"21","article-title":"Microblog-genre noise and impact on semantic annotation accuracy","author":"Derczynski","year":"2013"},{"key":"10.1016\/j.csl.2017.01.012_bib0017","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1016\/j.ipm.2014.10.006","article-title":"Analysis of named entity recognition and linking for Tweets","volume":"51","author":"Derczynski","year":"2015","journal-title":"Inf. Process. Manag."},{"key":"10.1016\/j.csl.2017.01.012_bib0018","series-title":"Proceedings of the 2013 Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (HLT-NAACL)","first-page":"359","article-title":"What to do about bad language on the internet","author":"Eisenstein","year":"2013"},{"key":"10.1016\/j.csl.2017.01.012_bib0019","series-title":"Proceedings of the NAACL HLT 2010 Workshop on Creating Speech and Language Data with Amazon\u2019s Mechanical Turk","first-page":"80","article-title":"Annotating named entities in Twitter data with crowdsourcing","author":"Finin","year":"2010"},{"key":"10.1016\/j.csl.2017.01.012_bib0020","series-title":"Proceedings of the Forty-third Annual Meeting of the Association for Computational Linguistics (ACL\u201905)","first-page":"363","article-title":"Incorporating non-local information into information extraction systems by Gibbs sampling","author":"Finkel","year":"2005"},{"key":"10.1016\/j.csl.2017.01.012_bib0021","series-title":"Proceedings of the Eighth European Conference on Principles and Practice of Knowledge Discovery in Databases (PKDD \u201904)","first-page":"161","article-title":"Learning from little: comparison of classifiers given little training","author":"Forman","year":"2004"},{"key":"10.1016\/j.csl.2017.01.012_bib0022","series-title":"Proceedings of the 2014 International Conference on Language Resources and Evaluation Conference (LREC)","first-page":"2544","article-title":"Crowdsourcing and annotating NER for Twitter #drift","author":"Fromreide","year":"2014"},{"key":"10.1016\/j.csl.2017.01.012_bib0023","series-title":"Proceedings of the 2014 Conference of the European Chapter of the Association for Computational Linguistics (EACL)","first-page":"215","article-title":"One sense per tweeter... and other lexical semantic tales of Twitter","author":"Gella","year":"2014"},{"key":"10.1016\/j.csl.2017.01.012_bib0024","series-title":"Proceedings of the Twenty-eighth International Conference on Machine Learning (ICML)","first-page":"513","article-title":"Domain adaptation for large-scale sentiment classification: a deep learning approach","author":"Glorot","year":"2011"},{"key":"10.1016\/j.csl.2017.01.012_bib0025","series-title":"Proceedings of the 1995 International Conference on Computational Linguistics (COLING)","article-title":"Message understanding conference-6: a brief history","author":"Grishman","year":"1995"},{"key":"10.1016\/j.csl.2017.01.012_bib0026","series-title":"Proceedings of the 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics of the Human Language Technologies","first-page":"281","article-title":"Domain adaptation with latent semantic association for named entity recognition","author":"Guo","year":"2009"},{"key":"10.1016\/j.csl.2017.01.012_bib0027","series-title":"Proceedings of the Twenty-fourth International Conference on World Wide Web. International World Wide Web Conferences Steering Committee","first-page":"452","article-title":"User review sites as a resource for large-scale sociolinguistic studies","author":"Hovy","year":"2015"},{"key":"10.1016\/j.csl.2017.01.012_sbref0027","series-title":"Proceedings of the 2006 Human Language Technology Conference of the NAACL","first-page":"57","article-title":"OntoNotes: the 90% solution","author":"Hovy","year":"2006"},{"key":"10.1016\/j.csl.2017.01.012_bib0029","series-title":"Proceedings of the 2013 International Conference on Weblogs and Social Media (ICWSM)","article-title":"Dude, srsly?: the surprisingly formal nature of Twitter\u2019s language","author":"Hu","year":"2013"},{"key":"10.1016\/j.csl.2017.01.012_bib0030","series-title":"Proceedings of the Eighteenth International Conference on Machine Learning","first-page":"282","article-title":"Conditional random fields: probabilistic models for segmenting and labeling sequence data","author":"Lafferty","year":"2001"},{"key":"10.1016\/j.csl.2017.01.012_bib0031","first-page":"361","article-title":"RCV1: a new benchmark collection for text categorization research","volume":"5","author":"Lewis","year":"2004","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.csl.2017.01.012_bib0032","series-title":"Proceedings of the Forty-ninth Annual Meeting of the Association for Computational Linguistics: Human Language Technologies (HLT-ACL)","first-page":"359","article-title":"Recognizing named entities in Tweets","author":"Liu","year":"2011"},{"key":"10.1016\/j.csl.2017.01.012_bib0033","article-title":"Named entity recognition: adapting to microblogging","author":"Locke","year":"2009","journal-title":"University of Colorado"},{"key":"10.1016\/j.csl.2017.01.012_bib0034","series-title":"Proceedings of the IEEE Tenth International Conference on Data Mining (ICDM)","first-page":"929","article-title":"Addressing concept-evolution in concept-drifting data streams","author":"Masud","year":"2010"},{"key":"10.1016\/j.csl.2017.01.012_bib0062","doi-asserted-by":"crossref","unstructured":"Maynard, D., Bontcheva, K., Augenstein, I., 2016. Natural language processing for the semantic web. Synthesis Lectures on the Semantic Web: Theory and Technology. Morgan & Claypool.","DOI":"10.2200\/S00741ED1V01Y201611WBE015"},{"key":"10.1016\/j.csl.2017.01.012_bib0035","series-title":"Proceedings of the 2003 Recent Advances in Natural Language Processing. Bulgaria","article-title":"Towards a semantic extraction of named entities","author":"Maynard","year":"2003"},{"key":"10.1016\/j.csl.2017.01.012_bib0036","series-title":"Proceedings of the Nineteenth Conference on Neural Information Processing Systems (NIPS). Vancouver, BC","first-page":"171","article-title":"Subsequence kernels for relation extraction","author":"Mooney","year":"2005"},{"issue":"1","key":"10.1016\/j.csl.2017.01.012_bib0037","first-page":"1","article-title":"A survey of named entity recognition and classification","volume":"30","author":"Nadeau","year":"2007","journal-title":"J. Linguist. Invest."},{"key":"10.1016\/j.csl.2017.01.012_bib0038","series-title":"Proceedings of the Twelfth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","first-page":"680","article-title":"Statistical entity-topic models","author":"Newman","year":"2006"},{"key":"10.1016\/j.csl.2017.01.012_bib0039","unstructured":"Okazaki, N., 2007. CRFsuite: a fast implementation of Conditional Random Fields (CRFs). http:\/\/www.chokkan.org\/software\/crfsuite\/."},{"key":"10.1016\/j.csl.2017.01.012_bib0040","series-title":"Proceedings of the Fifth Conference on Applied Natural Language Processing","first-page":"190","article-title":"A statistical profile of the named entity task","author":"Palmer","year":"1997"},{"issue":"2","key":"10.1016\/j.csl.2017.01.012_bib0041","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1215\/00031283-3130324","article-title":"Audience-modulated variation in online social media","volume":"90","author":"Pavalanathan","year":"2015","journal-title":"Am. Speech"},{"key":"10.1016\/j.csl.2017.01.012_bib0042","series-title":"Proceedings of the Sixth Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis","first-page":"92","article-title":"Personality traits on Twitter\u2013or\u2013How to get 1,500 personality tests in a week","author":"Plank","year":"2015"},{"key":"10.1016\/j.csl.2017.01.012_sbref0041","series-title":"Proceedings of the 2014 International Conference on Computational Linguistics (COLING","first-page":"1783","article-title":"Adapting taggers to Twitter with not-so-distant supervision","author":"Plank","year":"2014"},{"issue":"9","key":"10.1016\/j.csl.2017.01.012_bib0044","doi-asserted-by":"crossref","first-page":"e0138717","DOI":"10.1371\/journal.pone.0138717","article-title":"Studying user income through language, behaviour and affect in social media","volume":"10","author":"Preo\u0163iuc-Pietro","year":"2015","journal-title":"PloS One"},{"key":"10.1016\/j.csl.2017.01.012_bib0045","series-title":"Proceedings of the Thirteenth Conference on Computational Natural Language Learning (CoNLL-2009)","first-page":"147","article-title":"Design challenges and misconceptions in named entity recognition","author":"Ratinov","year":"2009"},{"key":"10.1016\/j.csl.2017.01.012_bib0046","series-title":"Proceedings of the NAACL HLT 2013 Workshop on Creating Speech and Language Data with Amazon\u2019s Mechanical Turk","first-page":"627","article-title":"The life and death of discourse entities: identifying singleton mentions","author":"Recasens","year":"2013"},{"key":"10.1016\/j.csl.2017.01.012_bib0047","series-title":"Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing (EMNLP)","first-page":"1524","article-title":"Named entity recognition in tweets: an experimental study","author":"Ritter","year":"2011"},{"key":"10.1016\/j.csl.2017.01.012_bib0048","series-title":"Proceedings of the 2013 Workshops on World Wide Web Conference (WWW)","article-title":"Making sense of microposts (#MSM2013): big things come in small packages","author":"Rowe","year":"2013"},{"key":"10.1016\/j.csl.2017.01.012_bib0049","series-title":"Proceedings of the Twenty-fourth International Conference on World Wide Web Companion","first-page":"1551","article-title":"#Microposts2015 \u2013 5th Workshop on \u2018Making Sense of Microposts\u2019: Big things come in small packages","author":"Rowe","year":"2015"},{"key":"10.1016\/j.csl.2017.01.012_bib0050","series-title":"Proceedings of the Second International Conference on Human Language Technology Research","first-page":"52","article-title":"Experiments in multidocument summarization","author":"Schiffman","year":"2002"},{"key":"10.1016\/j.csl.2017.01.012_bib0051","series-title":"Proceedings of the Twenty-eighth International Conference on Machine Learning (ICML)","first-page":"129","article-title":"Parsing natural scenes and natural language with recursive neural networks","author":"Socher","year":"2011"},{"key":"10.1016\/j.csl.2017.01.012_bib0052","series-title":"Proceedings of the 2011 Conference on Recent Advances in Natural Language Processing","first-page":"104","article-title":"JRC-NAMES: a freely available, highly multilingual named entity resource","author":"Steinberger","year":"2011"},{"key":"10.1016\/j.csl.2017.01.012_bib0053","series-title":"Proceedings of the 2005 Conference on Human Language Technology and Empirical Methods in Natural Language Processing","first-page":"748","article-title":"Composition of conditional random fields for transfer learning","author":"Sutton","year":"2005"},{"key":"10.1016\/j.csl.2017.01.012_bib0054","series-title":"Proceedings of the Seventh Conference on Natural Language Learning at HLT-NAACL. Edmonton, Canada","first-page":"142","article-title":"Introduction to the CoNLL-2003 shared task: language-independent named entity recognition","author":"Tjong Kim Sang","year":"2003"},{"key":"10.1016\/j.csl.2017.01.012_bib0055","series-title":"Proceedings of the Seventh Annual ACM International Workshop on Web Information and Data Management","first-page":"81","article-title":"A search result clustering method using informatively named entities","author":"Toda","year":"2005"},{"key":"10.1016\/j.csl.2017.01.012_bib0056","series-title":"ACE 2005 Multilingual Training Corpus","author":"Walker","year":"2006"},{"key":"10.1016\/j.csl.2017.01.012_bib0057","series-title":"Proceedings of the Seventeenth ACM Conference on Information and Knowledge Management","first-page":"123","article-title":"Web-scale named entity recognition","author":"Whitelaw","year":"2008"},{"key":"10.1016\/j.csl.2017.01.012_bib0058","series-title":"Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing","first-page":"1523","article-title":"Domain adaptive bootstrapping for named entity recognition","author":"Wu","year":"2009"},{"key":"10.1016\/j.csl.2017.01.012_bib0059","doi-asserted-by":"crossref","unstructured":"Yang, Y., Eisenstein, J., 2017. Overcoming language variation in sentiment analysis with social attention. In: Transaction of the Association for Computational Linguistics (TACL), to appear.","DOI":"10.1162\/tacl_a_00062"}],"container-title":["Computer Speech & Language"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S088523081630002X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S088523081630002X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2019,9,18]],"date-time":"2019-09-18T13:49:27Z","timestamp":1568814567000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S088523081630002X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,7]]},"references-count":62,"alternative-id":["S088523081630002X"],"URL":"https:\/\/doi.org\/10.1016\/j.csl.2017.01.012","relation":{},"ISSN":["0885-2308"],"issn-type":[{"value":"0885-2308","type":"print"}],"subject":[],"published":{"date-parts":[[2017,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Generalisation in named entity recognition: A quantitative analysis","name":"articletitle","label":"Article Title"},{"value":"Computer Speech & Language","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.csl.2017.01.012","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2017 The Authors. Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}]}}