{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T15:15:04Z","timestamp":1782486904696,"version":"3.54.5"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319769400","type":"print"},{"value":"9783319769417","type":"electronic"}],"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\/978-3-319-76941-7_13","type":"book-chapter","created":{"date-parts":[[2018,2,28]],"date-time":"2018-02-28T04:09:31Z","timestamp":1519790971000},"page":"167-179","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":26,"title":["Web2Text: Deep Structured Boilerplate Removal"],"prefix":"10.1007","author":[{"given":"Thijs","family":"Vogels","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Octavian-Eugen","family":"Ganea","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Carsten","family":"Eickhoff","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2018,3,1]]},"reference":[{"key":"13_CR1","unstructured":"Baroni, M., Chantree, F., Kilgarriff, A., Sharoff, S.: CleanEval: a competition for cleaning web pages. In: LREC (2008)"},{"key":"13_CR2","unstructured":"Bauer, D., Degen, J., Deng, X., Herger, P., Gasthaus, J., Giesbrecht, E., Jansen, L., Kalina, C., Kr\u00e4ger, T., M\u00e4rtin, R., Schmidt, M., Scholler, S., Steger, J., Stemle, E., Evert, S.: FIASCO: filtering the internet by automatic subtree classification, Osnabruck. In: Building and Exploring Web Corpora: Proceedings of the 3rd Web as Corpus Workshop, Incorporating CleanEval, vol. 4, pp. 111\u2013121 (2007)"},{"key":"13_CR3","doi-asserted-by":"crossref","unstructured":"Chakrabarti, D., Kumar, R., Punera, K.: Page-level template detection via isotonic smoothing. In: Proceedings of the 16th International Conference on World Wide Web, pp. 61\u201370. ACM (2007)","DOI":"10.1145\/1242572.1242582"},{"key":"13_CR4","doi-asserted-by":"crossref","unstructured":"Chakrabarti, D., Kumar, R., Punera, K.: A graph-theoretic approach to webpage segmentation. In Proceedings of the 17th International Conference on World Wide Web, pp. 377\u2013386. ACM (2008)","DOI":"10.1145\/1367497.1367549"},{"key":"13_CR5","doi-asserted-by":"crossref","unstructured":"Collins-Thompson, K., Bennett, P., Diaz, F., Clarke, C., Voorhees, E.: Overview of the TREC 2013 web track. In: Proceedings of the 22nd Text Retrieval Conference (TREC 2013) (2013)","DOI":"10.6028\/NIST.SP.500-302.web-overview"},{"issue":"9","key":"13_CR6","doi-asserted-by":"publisher","first-page":"1233","DOI":"10.1109\/TKDE.2005.138","volume":"17","author":"S Debnath","year":"2005","unstructured":"Debnath, S., Mitra, P., Pal, N., Giles, C.L.: Automatic identification of informative sections of web pages. IEEE Trans. Knowl. Data Eng. 17(9), 1233\u20131246 (2005)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"13_CR7","unstructured":"Finn, A., Kushmerick, N., Smyth, B.: Content classification for digital libraries. Unrefereed, Fact or fiction (2001)"},{"key":"13_CR8","unstructured":"Geitgey, A.: Unfluff - an automatic web page content extractor for node.js! (2014)"},{"key":"13_CR9","doi-asserted-by":"crossref","unstructured":"Gibson, J., Wellner, B., Lubar, S.: Adaptive web-page content identification. In: Proceedings of the 9th Annual ACM International Workshop on Web Information and Data Management, pp. 105\u2013112. ACM (2007)","DOI":"10.1145\/1316902.1316920"},{"key":"13_CR10","doi-asserted-by":"crossref","unstructured":"Gottron, T.: Content code blurring: a new approach to content extraction. In: 19th International Workshop on Database and Expert Systems Application, DEXA 2008, pp. 29\u201333. IEEE (2008)","DOI":"10.1109\/DEXA.2008.43"},{"key":"13_CR11","doi-asserted-by":"crossref","unstructured":"Gupta, S., Kaiser, G., Neistadt, D., Grimm, P.: DOM-based content extraction of HTML documents. In: Proceedings of the 12th International Conference on World Wide Web, pp. 207\u2013214. ACM (2003)","DOI":"10.1145\/775181.775182"},{"key":"13_CR12","unstructured":"Hedley, J.: Jsoup HTML parser (2009)"},{"key":"13_CR13","doi-asserted-by":"crossref","unstructured":"Jin, R., Hauptmann, A.G., Zhai, C.: Language model for information retrieval. In: Proceedings of the 25th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 42\u201348. ACM (2002)","DOI":"10.1145\/564376.564386"},{"key":"13_CR14","unstructured":"Kingma, D., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"13_CR15","doi-asserted-by":"crossref","unstructured":"Kohlsch\u00fctter, C.: A densitometric analysis of web template content. In: Proceedings of the 18th International Conference on World Wide Web, pp. 1165\u20131166. ACM (2009)","DOI":"10.1145\/1526709.1526909"},{"key":"13_CR16","unstructured":"Kohlsch\u00fctter, C., et al.: Boilerpipe - boilerplate removal and fulltext extraction from HTML pages. Google Code (2010)"},{"key":"13_CR17","doi-asserted-by":"crossref","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, pp. 441\u2013450. ACM (2010)","DOI":"10.1145\/1718487.1718542"},{"key":"13_CR18","doi-asserted-by":"crossref","unstructured":"Lavrenko, V., Croft, W.B.: Relevance based language models. In: Proceedings of the 24th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 120\u2013127. ACM (2001)","DOI":"10.1145\/383952.383972"},{"key":"13_CR19","doi-asserted-by":"crossref","unstructured":"Lin, S.-H., Ho, J.-M.: Discovering informative content blocks from web documents. In: Proceedings of the Eighth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 588\u2013593. ACM (2002)","DOI":"10.1145\/775047.775134"},{"key":"13_CR20","unstructured":"Spousta, M., Marek, M., Pecina, P.: Victor: the web-page cleaning tool. In: 4th Web as Corpus Workshop (WAC4)-Can We Beat Google, pp. 12\u201317 (2008)"},{"key":"13_CR21","doi-asserted-by":"crossref","unstructured":"Sun, F., Song, D., Liao, L.: DOM based content extraction via text density. In: Proceedings of the 34th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 245\u2013254. ACM (2011)","DOI":"10.1145\/2009916.2009952"},{"key":"13_CR22","doi-asserted-by":"crossref","unstructured":"Vieira, K., Da Silva, A.S., Pinto, N., De Moura, E.S., Cavalcanti, J., Freire, J.: A fast and robust method for web page template detection and removal. In: Proceedings of the 15th ACM International Conference on Information and Knowledge Management, pp. 258\u2013267. ACM (2006)","DOI":"10.1145\/1183614.1183654"},{"key":"13_CR23","doi-asserted-by":"crossref","unstructured":"Viterbi, A.J.: Error bounds for convolutional codes and an asymptotically optimum decoding algorithm. In: The Foundations of the Digital Wireless World: Selected Works of AJ Viterbi, pp. 41\u201350. World Scientific (2010)","DOI":"10.1142\/9789814287517_0004"},{"key":"13_CR24","doi-asserted-by":"crossref","unstructured":"Yi, L., Liu, B., Li, X.: Eliminating noisy information in web pages for data mining. In: Proceedings of the Ninth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 296\u2013305. ACM (2003)","DOI":"10.1145\/956750.956785"}],"container-title":["Lecture Notes in Computer Science","Advances in Information Retrieval"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-76941-7_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T16:42:42Z","timestamp":1719852162000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-76941-7_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319769400","9783319769417"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-76941-7_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"1 March 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECIR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Information Retrieval","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Grenoble","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 March 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 March 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"40","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecir2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.ecir2018.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}