{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:17:25Z","timestamp":1750220245914,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":17,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,4,25]],"date-time":"2022-04-25T00:00:00Z","timestamp":1650844800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Spanish MCIN\/AEI","award":["PID2019-104735RB-C41"],"award-info":[{"award-number":["PID2019-104735RB-C41"]}]},{"name":"EU Horizon 2020 research and innovation programme","award":["952215 (TAILOR)"],"award-info":[{"award-number":["952215 (TAILOR)"]}]},{"DOI":"10.13039\/501100003359","name":"Generalitat Valenciana","doi-asserted-by":"publisher","award":["Prometeo\/2019\/098 (DeepTrust)"],"award-info":[{"award-number":["Prometeo\/2019\/098 (DeepTrust)"]}],"id":[{"id":"10.13039\/501100003359","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,4,25]]},"DOI":"10.1145\/3487553.3524242","type":"proceedings-article","created":{"date-parts":[[2022,8,16]],"date-time":"2022-08-16T22:41:30Z","timestamp":1660689690000},"page":"205-209","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["HybEx: A Hybrid Tool for Template Extraction"],"prefix":"10.1145","author":[{"given":"Juli\u00e1n","family":"Alarte","sequence":"first","affiliation":[{"name":"Universitat Polit\u00e8cnica de Val\u00e8ncia, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Josep","family":"Silva","sequence":"additional","affiliation":[{"name":"VRAIN, Universitat Polit\u00e8cnica de Val\u00e8ncia, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,8,16]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/2740908.2742835"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3451168"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3316810"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/511446.511522"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/1062745.1062763"},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of the 2nd International Conference on Internet Technologies and Applications (ITA\u201907)","author":"Gottron Thomas","year":"2007","unstructured":"Thomas Gottron . 2007 . Evaluating content extraction on HTML documents . In Proceedings of the 2nd International Conference on Internet Technologies and Applications (ITA\u201907) . 123\u2013132. Thomas Gottron. 2007. Evaluating content extraction on HTML documents. In Proceedings of the 2nd International Conference on Internet Technologies and Applications (ITA\u201907). 123\u2013132."},{"volume-title":"Boilerplate Removal Using a Neural Sequence Labeling Model","author":"Leonhardt Jurek","key":"e_1_3_2_1_7_1","unstructured":"Jurek Leonhardt , Avishek Anand , and Megha Khosla . 2020. Boilerplate Removal Using a Neural Sequence Labeling Model . Association for Computing Machinery , New York, NY, USA , 226\u2013229. https:\/\/doi.org\/10.1145\/3366424.3383547 10.1145\/3366424.3383547 Jurek Leonhardt, Avishek Anand, and Megha Khosla. 2020. Boilerplate Removal Using a Neural Sequence Labeling Model. Association for Computing Machinery, New York, NY, USA, 226\u2013229. https:\/\/doi.org\/10.1145\/3366424.3383547"},{"key":"e_1_3_2_1_8_1","volume-title":"Proceeding of the International Conference on Computer Networks, Big Data and IoT (ICCBI -","author":"S.","year":"2018","unstructured":"Sangita\u00a0 S. Modi and Sudhir\u00a0B. Jagtap. 2020. Multimodal Web Content Mining to Filter Non-learning Sites Using NLP . In Proceeding of the International Conference on Computer Networks, Big Data and IoT (ICCBI - 2018 ), A.Pasumpon Pandian, Tomonobu Senjyu, Syed Mohammed\u00a0Shamsul Islam, and Haoxiang Wang (Eds.). Springer International Publishing, Cham, 23\u201330. Sangita\u00a0S. Modi and Sudhir\u00a0B. Jagtap. 2020. Multimodal Web Content Mining to Filter Non-learning Sites Using NLP. In Proceeding of the International Conference on Computer Networks, Big Data and IoT (ICCBI - 2018), A.Pasumpon Pandian, Tomonobu Senjyu, Syed Mohammed\u00a0Shamsul Islam, and Haoxiang Wang (Eds.). Springer International Publishing, Cham, 23\u201330."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/988672.988740"},{"key":"e_1_3_2_1_10_1","volume-title":"A hybrid approach for content extraction with text density and visual importance of DOM nodes. Knowledge and Information Systems 42, 1 (01","author":"Song Dandan","year":"2015","unstructured":"Dandan Song , Fei Sun , and Lejian Liao . 2015. A hybrid approach for content extraction with text density and visual importance of DOM nodes. Knowledge and Information Systems 42, 1 (01 Jan 2015 ), 75\u201396. https:\/\/doi.org\/10.1007\/s10115-013-0687-x 10.1007\/s10115-013-0687-x Dandan Song, Fei Sun, and Lejian Liao. 2015. A hybrid approach for content extraction with text density and visual importance of DOM nodes. Knowledge and Information Systems 42, 1 (01 Jan 2015), 75\u201396. https:\/\/doi.org\/10.1007\/s10115-013-0687-x"},{"key":"e_1_3_2_1_11_1","volume-title":"Learning Web Content Extraction with DOM Features. In 2018 IEEE 14th International Conference on Intelligent Computer Communication and Processing (ICCP). 5\u201311","author":"Utiu Nichita","year":"2018","unstructured":"Nichita Utiu and Vlad-Sebastian Ionescu . 2018 . Learning Web Content Extraction with DOM Features. In 2018 IEEE 14th International Conference on Intelligent Computer Communication and Processing (ICCP). 5\u201311 . https:\/\/doi.org\/10.1109\/ICCP.2018.8516632 10.1109\/ICCP.2018.8516632 Nichita Utiu and Vlad-Sebastian Ionescu. 2018. Learning Web Content Extraction with DOM Features. In 2018 IEEE 14th International Conference on Intelligent Computer Communication and Processing (ICCP). 5\u201311. https:\/\/doi.org\/10.1109\/ICCP.2018.8516632"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2013.02.005"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/1183614.1183654"},{"key":"e_1_3_2_1_14_1","unstructured":"Thijs Vogels Octavian-Eugen Ganea and Carsten Eickhoff. 2018. Web2Text: Deep Structured Boilerplate Removal. CoRR abs\/1801.02607(2018). arxiv:1801.02607http:\/\/arxiv.org\/abs\/1801.02607  Thijs Vogels Octavian-Eugen Ganea and Carsten Eickhoff. 2018. Web2Text: Deep Structured Boilerplate Removal. CoRR abs\/1801.02607(2018). arxiv:1801.02607http:\/\/arxiv.org\/abs\/1801.02607"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/956750.956785"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9534308"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1624\/3\/032023"}],"event":{"name":"WWW '22: The ACM Web Conference 2022","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"],"location":"Virtual Event, Lyon France","acronym":"WWW '22"},"container-title":["Companion Proceedings of the Web Conference 2022"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3487553.3524242","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3487553.3524242","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:30:33Z","timestamp":1750188633000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3487553.3524242"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,25]]},"references-count":17,"alternative-id":["10.1145\/3487553.3524242","10.1145\/3487553"],"URL":"https:\/\/doi.org\/10.1145\/3487553.3524242","relation":{},"subject":[],"published":{"date-parts":[[2022,4,25]]},"assertion":[{"value":"2022-08-16","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}