{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T18:50:37Z","timestamp":1775069437256,"version":"3.50.1"},"publisher-location":"Cham","reference-count":20,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319097602","type":"print"},{"value":"9783319097619","type":"electronic"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014]]},"DOI":"10.1007\/978-3-319-09761-9_22","type":"book-chapter","created":{"date-parts":[[2014,9,26]],"date-time":"2014-09-26T15:43:22Z","timestamp":1411746202000},"page":"201-206","source":"Crossref","is-referenced-by-count":4,"title":["brWaC: A WaCky Corpus for Brazilian Portuguese"],"prefix":"10.1007","author":[{"given":"Rodrigo","family":"Boos","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kassius","family":"Prestes","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aline","family":"Villavicencio","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muntsa","family":"Padr\u00f3","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"22_CR1","unstructured":"Ramisch, C., Villavicencio, A., Boitet, C.: Multiword expressions in the wild? the mwetoolkit comes in handy. In: Proc. of the 23rd COLING - Demonstrations, Beijing, China. The Coling 2010 Organizing Committee (August 2010)"},{"key":"22_CR2","unstructured":"Tsvetkov, Y., Wintner, S.: Extraction of multi-word expressions from small parallel corpora. In: Coling 2010: Posters, Beijing, China, Coling 2010 (August 2010)"},{"key":"22_CR3","unstructured":"Korhonen, A., Krymolowski, Y., Briscoe, E.J.: A large subcategorization lexicon for natural language processing applications. In: Proceedings of the 5th LREC, Genova, Italy (2006)"},{"key":"22_CR4","doi-asserted-by":"crossref","unstructured":"Lin, D.: Automatic retrieval and clustering of similar words. In: Proceedings of the 36th ACL and 17th International COLING (1998)","DOI":"10.3115\/980432.980696"},{"issue":"4","key":"22_CR5","doi-asserted-by":"publisher","first-page":"673","DOI":"10.1162\/coli_a_00016","volume":"36","author":"M. Baroni","year":"2010","unstructured":"Baroni, M., Lenci, A.: Distributional memory: A general framework for corpus-based semantics. Computational Linguistics\u00a036(4), 673\u2013721 (2010)","journal-title":"Computational Linguistics"},{"issue":"3","key":"22_CR6","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. Language Resources and Evaluation\u00a043(3), 209\u2013226 (2009)","journal-title":"Language Resources and Evaluation"},{"key":"22_CR7","doi-asserted-by":"crossref","unstructured":"Talvensaari, T., Pirkola, A., J\u00e4rvelin, K., Juhola, M., Laurikkala, J.: Focused web crawling in the acquisition of comparable corpora. Inf. Retr.\u00a011(5) (October 2008)","DOI":"10.1007\/s10791-008-9058-8"},{"key":"22_CR8","first-page":"25","volume-title":"Proceedings of the First Workshop on Multilingual Modeling, MM 2012","author":"R. Granada","year":"2012","unstructured":"Granada, R., Lopes, L., Ramisch, C., Trojahn, C., Vieira, R., Villavicencio, A.: A comparable corpus based on aligned multilingual ontologies. In: Proceedings of the First Workshop on Multilingual Modeling, MM 2012, pp. 25\u201331. Association for Computational Linguistics, Stroudsburg (2012)"},{"key":"22_CR9","first-page":"201","volume-title":"COLING","author":"L. Barbosa","year":"2012","unstructured":"Barbosa, L., Sridhar, V.K.R., Yarmohammadi, M., Bangalore, S.: Harvesting parallel text in multiple languages with limited supervision. In: Kay, M., Boitet, C. (eds.) COLING, pp. 201\u2013214. Indian Institute of Technology, Bombay (2012)"},{"key":"22_CR10","unstructured":"Ferraresi, A., Bernardini, S., Picci, G., Baroni, M.: Web corpora for bilingual lexicography: A pilot study of english\/french collocation extraction and translation. In: Using Corpora in Contrastive and Translation Studies. Cambridge Scholars Publishing, Newcastle (2010)"},{"key":"22_CR11","doi-asserted-by":"crossref","unstructured":"Ljube\u0161i\u0107, N., Erjavec, T.: hrwac and slwac: Compiling web corpora for croatian and slovene. In: Proceedings of 14th International Conference on Text, Speech and Dialogue, TSD (2011)","DOI":"10.1007\/978-3-642-23538-2_50"},{"key":"22_CR12","unstructured":"Ljube\u0161i\u0107, N., Toral, A.: caWaC \u2013 a web corpus of Catalan. In: Proceedings of LREC 2014 (May 2014)"},{"key":"22_CR13","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1017\/S1351324906004505","volume":"13","author":"J. Nivre","year":"2007","unstructured":"Nivre, J., Hall, J., Nilsson, J., Chanev, A., Eryi\u01e7it, G., K\u00fcbler, S., Marinov, S., Marsi, E.: Maltparser: A language-independent system for data-driven dependency parsing. Natural Language Engineering\u00a013, 95\u2013135 (2007)","journal-title":"Natural Language Engineering"},{"key":"22_CR14","doi-asserted-by":"crossref","first-page":"441","DOI":"10.1145\/1718487.1718542","volume-title":"Proceedings of the Third ACM International Conference on Web Search and Data Mining, WSDM 2010","author":"C. Kohlsch\u00fctter","year":"2010","unstructured":"Kohlsch\u00fctter, C., Fankhauser, P., Nejdl, W.: Boilerplate detection using shallow text features. In: Proceedings of the Third ACM International Conference on Web Search and Data Mining, WSDM 2010, pp. 441\u2013450. ACM, New York (2010)"},{"key":"22_CR15","unstructured":"Pomik\u00e1lek, J.: Removing Boilerplate and Duplicate Content from Web Corpora. PhD en informatique, Masarykova univerzita, Fakulta informatiky (2011)"},{"issue":"8-13","key":"22_CR16","doi-asserted-by":"publisher","first-page":"1157","DOI":"10.1016\/S0169-7552(97)00031-7","volume":"29","author":"A.Z. Broder","year":"1997","unstructured":"Broder, A.Z., Glassman, S.C., Manasse, M.S., Zweig, G.: Syntactic clustering of the web. Comput. Netw. ISDN Syst.\u00a029(8-13), 1157\u20131166 (1997)","journal-title":"Comput. Netw. ISDN Syst."},{"key":"22_CR17","unstructured":"Schmid, H.: Probabilistic part-of-speech tagging using decision trees (1994)"},{"key":"22_CR18","unstructured":"Shuyo, N.: Language detection library for java (2010)"},{"key":"22_CR19","unstructured":"Bick, E.: The Parsing System Palavras. Automatic Grammatical Analysis of Portuguese in a Constraint Grammar Famework. PhD thesis, Aarhus University (2002)"},{"key":"22_CR20","unstructured":"Boos, R., Prestes, K., Villavicencio, A.: Identification of multiword expressions in the brwac. In: Proceedings of LREC 2014 (May 2014)"}],"container-title":["Lecture Notes in Computer Science","Computational Processing of the Portuguese Language"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-09761-9_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,18]],"date-time":"2022-04-18T01:09:31Z","timestamp":1650244171000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-09761-9_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014]]},"ISBN":["9783319097602","9783319097619"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-09761-9_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014]]}}}