{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T16:49:37Z","timestamp":1725986977183},"publisher-location":"Cham","reference-count":23,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319991320"},{"type":"electronic","value":"9783319991337"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-319-99133-7_17","type":"book-chapter","created":{"date-parts":[[2018,8,6]],"date-time":"2018-08-06T14:38:25Z","timestamp":1533566305000},"page":"207-217","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Can We Quantify Domainhood? Exploring Measures to Assess Domain-Specificity in Web Corpora"],"prefix":"10.1007","author":[{"given":"Marina","family":"Santini","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wiktor","family":"Strandqvist","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mikael","family":"Nystr\u00f6m","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marjan","family":"Alirezai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arne","family":"J\u00f6nsson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,8,7]]},"reference":[{"key":"17_CR1","unstructured":"Baroni, M., Bernardini, S.: BootCat: bootstrapping corpora and terms from the web. In: LREC (2004)"},{"issue":"3","key":"17_CR2","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1007\/s10579-009-9081-4","volume":"43","author":"M Baroni","year":"2009","unstructured":"Baroni, M., Bernardini, S., Ferraresi, A., Zanchetta, E.: The wacky wide web: a collection of very large linguistically processed web-crawled corpora. Lang. Resour. Eval. 43(3), 209\u2013226 (2009)","journal-title":"Lang. Resour. Eval."},{"issue":"4","key":"17_CR3","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1093\/llc\/8.4.243","volume":"8","author":"D Biber","year":"1993","unstructured":"Biber, D.: Representativeness in corpus design. Literary Linguist. Comput. 8(4), 243\u2013257 (1993)","journal-title":"Literary Linguist. Comput."},{"issue":"2","key":"17_CR4","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1017\/S1351324900000139","volume":"1","author":"KW Church","year":"1995","unstructured":"Church, K.W., Gale, W.A.: Poisson mixtures. Nat. Lang. Eng. 1(2), 163\u2013190 (1995)","journal-title":"Nat. Lang. Eng."},{"key":"17_CR5","unstructured":"Ciaramita, M., Baroni, M.: A figure of merit for the evaluation of web-corpus randomness. In: Proceedings of the 11th Conference of the European Chapter of the Association for Computational Linguistics (2006)"},{"key":"17_CR6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-64572-8","volume-title":"Corpus Linguistics and Statistics with R","author":"G Desagulier","year":"2017","unstructured":"Desagulier, G.: Corpus Linguistics and Statistics with R. Springer, Heidelberg (2017). https:\/\/doi.org\/10.1007\/978-3-319-64572-8"},{"issue":"1","key":"17_CR7","first-page":"61","volume":"19","author":"T Dunning","year":"1993","unstructured":"Dunning, T.: Accurate methods for the statistics of surprise and coincidence. Comput. Linguist. 19(1), 61\u201374 (1993)","journal-title":"Comput. Linguist."},{"key":"17_CR8","unstructured":"Ferraresi, A., Zanchetta, E., Baroni, M., Bernardini, S.: Introducing and evaluating ukWaC, a very large web-derived corpus of English. In: Proceedings of the 4th Web as Corpus Workshop (WAC-4) Can We Beat Google, pp. 47\u201354 (2008)"},{"key":"17_CR9","unstructured":"Fletcher, W.H.: Implementing a BNC-compare-able web corpus. Building and Exploring Web Corpora, pp. 43\u201356 (2007)"},{"key":"17_CR10","doi-asserted-by":"crossref","unstructured":"Gries, S.T.: Elementary statistical testing with R. In: Krug, M., Schl\u00fcter, J. (eds.) Research Methods in Language Variation and change (2013)","DOI":"10.1017\/CBO9780511792519.024"},{"key":"17_CR11","unstructured":"Gustafson-Capkov\u00e1, S., Hartmann, B.: Manual of the Stockholm Ume\u00e5 corpus version 2.0. Stockholm University (2006)"},{"issue":"2","key":"17_CR12","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1162\/COLI_a_00284","volume":"43","author":"A Irvine","year":"2017","unstructured":"Irvine, A., Callison-Burch, C.: A comprehensive analysis of bilingual lexicon induction. Comput. Linguist. 43(2), 273\u2013310 (2017)","journal-title":"Comput. Linguist."},{"issue":"1","key":"17_CR13","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1017\/S1351324996001246","volume":"2","author":"SM Katz","year":"1996","unstructured":"Katz, S.M.: Distribution of content words and phrases in text and language modelling. Nat. Lang. Eng. 2(1), 15\u201359 (1996)","journal-title":"Nat. Lang. Eng."},{"issue":"1","key":"17_CR14","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1075\/ijcl.6.1.05kil","volume":"6","author":"A Kilgarriff","year":"2001","unstructured":"Kilgarriff, A.: Comparing corpora. Int. J. Corpus Linguist. 6(1), 97\u2013133 (2001)","journal-title":"Int. J. Corpus Linguist."},{"key":"17_CR15","unstructured":"Kilgarriff, A.: Simple maths for keywords. In: Proceedings of the Corpus Linguistics Conference, Liverpool, UK (2009)"},{"key":"17_CR16","unstructured":"Kilgarriff, A.: Comparable corpora within and across languages, word frequency lists and the KELLY project. In: Proceedings of the 3rd Workshop on Building and Using Comparable Corpora, pp. 1\u20135 (2010)"},{"key":"17_CR17","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1007\/978-3-642-30773-7_8","volume-title":"Shall We Play the Festschrift Game?","author":"JB Pierrehumbert","year":"2012","unstructured":"Pierrehumbert, J.B.: Burstiness of verbs and derived nouns. In: Santos, D., Lind\u00e9n, K., Ng\u2019ang\u2019a, W. (eds.) Shall We Play the Festschrift Game?, pp. 99\u2013115. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-30773-7_8"},{"key":"17_CR18","doi-asserted-by":"crossref","unstructured":"Rayson, P., Garside, R.: Comparing corpora using frequency profiling. In: Proceedings of the workshop on Comparing Corpora, pp. 1\u20136. Association for Computational Linguistics (2000)","DOI":"10.3115\/1117729.1117730"},{"key":"17_CR19","doi-asserted-by":"crossref","unstructured":"Santini, M., J\u00f6nsson, A., Nystr\u00f6m, M., Alireza, M.: A web corpus for eCare: collection, lay annotation and learning-First results. In: Proceedings of the 2nd International Workshop on Language Technologies and Applications (LTA17). FedCSIS (2017)","DOI":"10.15439\/2017F531"},{"key":"17_CR20","series-title":"Text Speech and Language Technology Series","volume-title":"Essays in Honor of Adam Kilgarriff","author":"S Sharoff","year":"2017","unstructured":"Sharoff, S.: Know thy corpus! Exploring frequency distributions in large corpora. In: Diab, M., Villavicencio, A. (eds.) Essays in Honor of Adam Kilgarriff. Text Speech and Language Technology Series. Springer, Heidelberg (2017)"},{"key":"17_CR21","unstructured":"Strandqvist, W., Santini, M., Lind, L., J\u00f6nsson, A.: Towards a quality assessment of web corpora for language technology applications. In: Proceedings of TISLID18 - Languages For Digital Lives and Cultures. Ghent University, Belgium (2018)"},{"issue":"2","key":"17_CR22","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1007\/s10579-011-9141-4","volume":"45","author":"W Wong","year":"2011","unstructured":"Wong, W., Liu, W., Bennamoun, M.: Constructing specialised corpora through analysing domain representativeness of websites. Lang. Resour. Eval. 45(2), 209\u2013241 (2011)","journal-title":"Lang. Resour. Eval."},{"key":"17_CR23","doi-asserted-by":"crossref","unstructured":"Zhao, Z., Mei, Q.: Questions about questions: an empirical analysis of information needs on twitter. In: Proceedings of the 22nd International Conference on World Wide Web, pp. 1545\u20131556. ACM (2013)","DOI":"10.1145\/2488388.2488523"}],"container-title":["Communications in Computer and Information Science","Database and Expert Systems Applications"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-99133-7_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,21]],"date-time":"2019-10-21T22:09:43Z","timestamp":1571695783000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-99133-7_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319991320","9783319991337"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-99133-7_17","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2018]]}}}