{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,16]],"date-time":"2025-05-16T12:10:08Z","timestamp":1747397408820,"version":"3.40.3"},"publisher-location":"Cham","reference-count":20,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031099168"},{"type":"electronic","value":"9783031099175"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-09917-5_8","type":"book-chapter","created":{"date-parts":[[2022,6,30]],"date-time":"2022-06-30T19:03:14Z","timestamp":1656615794000},"page":"117-131","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Automatic Web Data API Creation via Cross-Lingual Neural Pagination Recognition"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1101-6337","authenticated-orcid":false,"given":"Chia-Hui","family":"Chang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cheng-Ju","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tzu-Ping","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,7,1]]},"reference":[{"key":"8_CR1","doi-asserted-by":"publisher","unstructured":"Arasu, A., Garcia-Molina, H.: Extracting structured data from web pages. In: Proceedings of the 2003 ACM SIGMOD International Conference on Management of Data, pp. 337\u2013348. ACM, New York (2003). https:\/\/doi.org\/10.1145\/872757.872799","DOI":"10.1145\/872757.872799"},{"key":"8_CR2","first-page":"597","volume":"7","author":"M Artetxe","year":"2018","unstructured":"Artetxe, M., Schwenk, H.: Massively multilingual sentence embeddings for zero-shot cross-lingual transfer and beyond. Trans. Assoc. Comput. Linguist. TACL 7, 597\u2013610 (2018)","journal-title":"Trans. Assoc. Comput. Linguist. TACL"},{"key":"8_CR3","unstructured":"Cantino, A.: Selector gadget. https:\/\/github.com\/cantino\/selectorgadget"},{"issue":"10","key":"8_CR4","doi-asserted-by":"publisher","first-page":"1411","DOI":"10.1109\/TKDE.2006.152","volume":"18","author":"CH Chang","year":"2006","unstructured":"Chang, C.H., Kayed, M., Girgis, M.R., Shaalan, K.F.: A survey of web information extraction systems. IEEE Trans. Knowl. Data Eng. 18(10), 1411\u20131428 (2006). https:\/\/doi.org\/10.1109\/TKDE.2006.152","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"8_CR5","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pp. 4171\u20134186. NAACL, Association for Computational Linguistics, Minneapolis, Minnesota (2019)"},{"key":"8_CR6","unstructured":"Dexi.io: Dexi.io (2015). https:\/\/www.dexi.io\/"},{"key":"8_CR7","doi-asserted-by":"publisher","first-page":"301","DOI":"10.1016\/j.knosys.2014.07.007","volume":"70","author":"E Ferrara","year":"2014","unstructured":"Ferrara, E., Meo, P.D., Fiumara, G., Baumgartner, R.: Web data extraction, applications and techniques: a survey. Knowl.-Based Syst. 70, 301\u2013323 (2014)","journal-title":"Knowl.-Based Syst."},{"key":"8_CR8","doi-asserted-by":"publisher","unstructured":"Furche, T., et al.: Diadem: thousands of websites to a single database. Proc. VLDB Endow. 7(14), 1845\u20131856 (2014). https:\/\/doi.org\/10.14778\/2733085.2733091","DOI":"10.14778\/2733085.2733091"},{"key":"8_CR9","doi-asserted-by":"publisher","unstructured":"Gottlob, G., Koch, C., Baumgartner, R., Herzog, M., Flesca, S.: The Lixto data extraction project: back and forth between theory and practice. In: Proceedings of the Twenty-Third ACM SIGMOD-SIGACT-SIGART Symposium on Principles of Database Systems, PODS 2004, pp. 1\u201312. ACM, New York (2004). https:\/\/doi.org\/10.1145\/1055558.1055560","DOI":"10.1145\/1055558.1055560"},{"key":"8_CR10","unstructured":"Import.io: Import.io (2012). https:\/\/www.import.io\/product\/"},{"key":"8_CR11","unstructured":"Korobov, M., de Prado, I., Haase, M.E.: AutoPager: Detect and classify pagination links (2020). https:\/\/github.com\/TeamHG-Memex\/autopager"},{"key":"8_CR12","doi-asserted-by":"crossref","unstructured":"Leonhardt, J., Anand, A., Khosla, M.: Boilerplate removal using a neural sequence labeling model. Association for Computing Machinery, New York, NY, USA (2020)","DOI":"10.1145\/3366424.3383547"},{"key":"8_CR13","unstructured":"Liao, Y.C.: Event Source Page Discovery via Reinforcement Learning. Master\u2019s thesis, National Central University, Taoyuan, Taiwan (2021)"},{"key":"8_CR14","doi-asserted-by":"publisher","unstructured":"Liu, B., Grossman, R., Zhai, Y.: Mining data records in web pages. In: Proceedings of the Ninth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 601\u2013606. ACM, New York (2003). https:\/\/doi.org\/10.1145\/956750.956826","DOI":"10.1145\/956750.956826"},{"key":"8_CR15","doi-asserted-by":"crossref","unstructured":"Meusel, R., Mika, P., Blanco, R.: Focused crawling for structured data. Association for Computing Machinery, New York, NY, USA (2014)","DOI":"10.1145\/2661829.2661902"},{"key":"8_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1007\/978-3-319-76941-7_13","volume-title":"Advances in Information Retrieval","author":"T Vogels","year":"2018","unstructured":"Vogels, T., Ganea, O.-E., Eickhoff, C.: Web2Text: deep structured boilerplate removal. In: Pasi, G., Piwowarski, B., Azzopardi, L., Hanbury, A. (eds.) ECIR 2018. LNCS, vol. 10772, pp. 167\u2013179. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-76941-7_13"},{"key":"8_CR17","unstructured":"Wu, T., Sgro, V.: Methods and systems for automated detection of pagination (2016). uS20160103799A1"},{"issue":"2","key":"8_CR18","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1007\/s10489-019-01499-0","volume":"50","author":"OY Yuliana","year":"2019","unstructured":"Yuliana, O.Y., Chang, C.-H.: DCADE: divide and conquer alignment with dynamic encoding for full page data extraction. Appl. Intell. 50(2), 271\u2013295 (2019). https:\/\/doi.org\/10.1007\/s10489-019-01499-0","journal-title":"Appl. Intell."},{"issue":"12","key":"8_CR19","doi-asserted-by":"publisher","first-page":"1614","DOI":"10.1109\/TKDE.2006.197","volume":"18","author":"Y Zhai","year":"2006","unstructured":"Zhai, Y., Liu, B.: Structured data extraction from the web based on partial tree alignment. IEEE Trans. Knowl. Data Eng. 18(12), 1614\u20131628 (2006). https:\/\/doi.org\/10.1109\/TKDE.2006.197","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"8_CR20","unstructured":"Zhang, X., Zhao, J., LeCun, Y.: Character-level convolutional networks for text classification. In: Proceedings of the 28th International Conference on Neural Information Processing Systems, NIPS 2015, vol. 1, pp. 649\u2013657. MIT Press, Cambridge, MA, USA (2015)"}],"container-title":["Lecture Notes in Computer Science","Web Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-09917-5_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,30]],"date-time":"2022-06-30T19:04:59Z","timestamp":1656615899000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-09917-5_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031099168","9783031099175"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-09917-5_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"1 July 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICWE","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Web Engineering","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bari","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 July 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 July 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icwe2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icwe2022.webengineering.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"81","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"23","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}