{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T05:03:31Z","timestamp":1725858211327},"publisher-location":"Cham","reference-count":29,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319415512"},{"type":"electronic","value":"9783319415529"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016]]},"DOI":"10.1007\/978-3-319-41552-9_31","type":"book-chapter","created":{"date-parts":[[2016,6,20]],"date-time":"2016-06-20T19:18:32Z","timestamp":1466450312000},"page":"306-318","source":"Crossref","is-referenced-by-count":2,"title":["Crawling by Readability Level"],"prefix":"10.1007","author":[{"given":"Jorge A. Wagner","family":"Filho","sequence":"first","affiliation":[]},{"given":"Rodrigo","family":"Wilkens","sequence":"additional","affiliation":[]},{"given":"Leonardo","family":"Zilio","sequence":"additional","affiliation":[]},{"given":"Marco","family":"Idiart","sequence":"additional","affiliation":[]},{"given":"Aline","family":"Villavicencio","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,6,21]]},"reference":[{"issue":"3","key":"31_CR1","doi-asserted-by":"crossref","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."},{"key":"31_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1007\/978-3-319-09761-9_22","volume-title":"Computational Processing of the Portuguese Language","author":"R Boos","year":"2014","unstructured":"Boos, R., Prestes, K., Villavicencio, A., Padr\u00f3, M.: brWaC: a wacky corpus for Brazilian Portuguese. In: Baptista, J., Mamede, N., Candeias, S., Paraboni, I., Pardo, T.A.S., Volpe Nunes, M.G. (eds.) PROPOR 2014. LNCS, vol. 8775, pp. 201\u2013206. Springer, Heidelberg (2014)"},{"key":"31_CR3","unstructured":"Callan, J., Eskenazi, M.: Combining lexical and grammatical features to improve readability measures for first and second language texts. In: Proceedings of NAACL HLT, pp. 460\u2013467 (2007)"},{"key":"31_CR4","volume-title":"Readability Revisited: The new Dale-Chall readability formula","author":"JS Chall","year":"1995","unstructured":"Chall, J.S., Dale, E.: Readability Revisited: The new Dale-Chall readability formula. Brookline Books, Cambridge (1995)"},{"issue":"2","key":"31_CR5","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1037\/h0076540","volume":"60","author":"M Coleman","year":"1975","unstructured":"Coleman, M., Liau, T.L.: A computer readability formula designed for machine scoring. J. Appl. Psychol. 60(2), 283 (1975)","journal-title":"J. Appl. Psychol."},{"key":"31_CR6","unstructured":"DuBay, W.H.: The principles of readability. Online Submission (2004)"},{"key":"31_CR7","doi-asserted-by":"crossref","unstructured":"Feng, L., Elhadad, N., Huenerfauth, M.: Cognitively motivated features for readability assessment. In: Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics, pp. 229\u2013237. Association for Computational Linguistics (2009)","DOI":"10.3115\/1609067.1609092"},{"key":"31_CR8","unstructured":"Feng, L., Jansche, M., Huenerfauth, M., Elhadad, N.: A comparison of features for automatic readability assessment. In: Proceedings of the 23rd International Conference on Computational Linguistics: Posters, COLING 2010, pp. 276\u2013284. Association for Computational Linguistics, Stroudsburg (2010). http:\/\/dl.acm.org\/citation.cfm?id=1944566.1944598"},{"key":"31_CR9","unstructured":"Ferraresi, A., Bernardini, S.: The academic web-as-corpus. In: Proceedings of the 8th Web as Corpus Workshop, pp. 53\u201362 (2013)"},{"key":"31_CR10","volume-title":"Art of Plain Talk","author":"RF Flesch","year":"1946","unstructured":"Flesch, R.F., et al.: Art of Plain Talk. Harper, New York (1946)"},{"key":"31_CR11","unstructured":"Fran\u00e7ois, T., Miltsakaki, E.: Do nlp and machine learning improve traditional readability formulas? In: Proceedings of the First Workshop on Predicting and Improving Text Readability for target reader populations, pp. 49\u201357. Association for Computational Linguistics (2012)"},{"key":"31_CR12","unstructured":"Gasperin, C., Specia, L., Pereira, T., Alu\u00edsio, S.: Learning when to simplify sentences for natural text simplification. In: Proceedings of ENIA - Brazilian Meeting on Artificial Intelligence, pp. 809\u2013818 (2009)"},{"issue":"2","key":"31_CR13","doi-asserted-by":"crossref","first-page":"193","DOI":"10.3758\/BF03195564","volume":"36","author":"AC Graesser","year":"2004","unstructured":"Graesser, A.C., McNamara, D.S., Louwerse, M.M., Cai, Z.: Coh-metrix: analysis of text on cohesion and language. Behav. Res. methods Instrum. comput. 36(2), 193\u2013202 (2004)","journal-title":"Behav. Res. methods Instrum. comput."},{"issue":"1","key":"31_CR14","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1145\/1656274.1656278","volume":"11","author":"M Hall","year":"2009","unstructured":"Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., Witten, I.H.: The weka data mining software: an update. ACM SIGKDD Explor. Newsl. 11(1), 10\u201318 (2009)","journal-title":"ACM SIGKDD Explor. Newsl."},{"issue":"1\u20132","key":"31_CR15","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1007\/s10994-005-0466-3","volume":"59","author":"N Landwehr","year":"2005","unstructured":"Landwehr, N., Hall, M., Frank, E.: Logistic model trees. Mach. Learn. 59(1\u20132), 161\u2013205 (2005)","journal-title":"Mach. Learn."},{"key":"31_CR16","unstructured":"Martins, T.B., Ghiraldelo, C.M., Nunes, M.d.G.V., de Oliveira Junior, O.N.: Readability formulas applied to textbooks in brazilian portuguese. Icmsc-Usp (1996)"},{"issue":"4","key":"31_CR17","doi-asserted-by":"crossref","first-page":"292","DOI":"10.1080\/01638530902959943","volume":"47","author":"DS McNamara","year":"2010","unstructured":"McNamara, D.S., Louwerse, M.M., McCarthy, P.M., Graesser, A.C.: Coh-metrix: capturing linguistic features of cohesion. Discourse Processes 47(4), 292\u2013330 (2010)","journal-title":"Discourse Processes"},{"key":"31_CR18","unstructured":"McNamara, D., Louwerse, M., Cai, Z., Graesser, A.: Coh-metrix version 3.0 (2013). http:\/\/cohmetrix.com . Accessed 1 Apr 2015"},{"key":"31_CR19","unstructured":"Navigli, R., Ponzetto, S.P.: Babelnet: building a very large multilingual semantic network. In: Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, pp. 216\u2013225. Association for Computational Linguistics (2010)"},{"issue":"1","key":"31_CR20","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s13173-014-0021-9","volume":"21","author":"N Neto","year":"2015","unstructured":"Neto, N., Rocha, W., Sousa, G.: An open-source rule-based syllabification tool for Brazilian Portuguese. J. Braz. Comput. Soc. 21(1), 1\u201310 (2015)","journal-title":"J. Braz. Comput. Soc."},{"issue":"1","key":"31_CR21","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1016\/j.csl.2008.04.003","volume":"23","author":"SE Petersen","year":"2009","unstructured":"Petersen, S.E., Ostendorf, M.: A machine learning approach to reading level assessment. Comput. Speech Lang. 23(1), 89\u2013106 (2009)","journal-title":"Comput. Speech Lang."},{"key":"31_CR22","unstructured":"Pomik\u00e1lek, J.: Removing boilerplate and duplicate content from web corpora. Ph.D. en informatique, Masarykova univerzita, Fakulta informatiky (2011)"},{"key":"31_CR23","unstructured":"Scarton, C., Alu\u0131sio, S.M.: Coh-metrix-port: a readability assessment tool for texts in Brazilian Portuguese. In: Proceedings of the 9th International Conference on Computational Processing of the Portuguese Language, Extended Activities Proceedings, PROPOR, vol. 10 (2010)"},{"key":"31_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"306","DOI":"10.1007\/978-3-642-16952-6_31","volume-title":"Advances in Artificial Intelligence \u2013 IBERAMIA 2010","author":"C Scarton","year":"2010","unstructured":"Scarton, C., Gasperin, C., Aluisio, S.: Revisiting the readability assessment of texts in Portuguese. In: Kuri-Morales, A., Simari, G.R. (eds.) IBERAMIA 2010. LNCS, vol. 6433, pp. 306\u2013315. Springer, Heidelberg (2010)"},{"key":"31_CR25","doi-asserted-by":"crossref","unstructured":"Schwarm, S.E., Ostendorf, M.: Reading level assessment using support vector machines and statistical language models. In: Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics, pp. 523\u2013530. Association for Computational Linguistics (2005)","DOI":"10.3115\/1219840.1219905"},{"key":"31_CR26","volume-title":"Measuring Reading Comprehension with the Lexile Framework","author":"AJ Stenner","year":"1996","unstructured":"Stenner, A.J.: Measuring Reading Comprehension with the Lexile Framework. ERIC, Washington (1996)"},{"key":"31_CR27","unstructured":"Vajjala, S., Meurers, D.: On the applicability of readability models to web texts. In: Proceedings of the 2nd Workshop on Predicting and Improving Text Readability for Target Reader Populations, p. 59 (2013)"},{"key":"31_CR28","doi-asserted-by":"crossref","unstructured":"Vajjala, S., Meurers, D.: Exploring measures of readability for spoken language: analyzing linguistic features of subtitles to identify age-specific tv programs. In: Proceedings of the 3rd Workshop on Predicting and Improving Text Readability for Target Reader Populations (PITR)@ EACL, pp. 21\u201329 (2014)","DOI":"10.3115\/v1\/W14-1203"},{"key":"31_CR29","volume-title":"Web as Corpus Toolkit: Users and Hackers Manual","author":"R Ziai","year":"2005","unstructured":"Ziai, R., Ott, N.: Web as Corpus Toolkit: Users and Hackers Manual. Lexical Computing Ltd., Brighton (2005)"}],"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\/978-3-319-41552-9_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,24]],"date-time":"2017-06-24T16:45:23Z","timestamp":1498322723000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-41552-9_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319415512","9783319415529"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-41552-9_31","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2016]]}}}