{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T02:52:20Z","timestamp":1781837540563,"version":"3.54.5"},"publisher-location":"Cham","reference-count":13,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032293718","type":"print"},{"value":"9783032293725","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-29372-5_14","type":"book-chapter","created":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T02:49:48Z","timestamp":1781837388000},"page":"191-198","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Visual-Aware Representation of\u00a0Web Pages for\u00a0Machine Learning Applications"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5233-0456","authenticated-orcid":false,"given":"Radek","family":"Burget","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6315-8137","authenticated-orcid":false,"given":"Radek","family":"Hranick\u00fd","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,20]]},"reference":[{"key":"14_CR1","doi-asserted-by":"crossref","unstructured":"Bevendorff, J., Gupta, R., Kiesel, J., Stein, B.: An empirical comparison of web content extraction algorithms. In: Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 2594\u20132603 (2023)","DOI":"10.1145\/3539618.3591920"},{"key":"14_CR2","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1007\/978-3-031-34444-2_21","volume-title":"Web Engineering","author":"R Burget","year":"2023","unstructured":"Burget, R.: Scraping data from web pages using SPARQL queries. In: Garrig\u00f3s, I., Murillo Rodr\u00edguez, J.M., Wimmer, M. (eds.) Web Engineering, pp. 293\u2013300. Springer Nature Switzerland, Cham (2023)"},{"key":"14_CR3","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1007\/978-3-031-34444-2_26","volume-title":"Web Engineering","author":"R Burget","year":"2023","unstructured":"Burget, R., Salem, H.: Creating searchable web page snapshots using semantic technologies. In: Garrig\u00f3s, I., Murillo Rodr\u00edguez, J.M., Wimmer, M. (eds.) Web Engineering, pp. 355\u2013358. Springer Nature Switzerland, Cham (2023)"},{"key":"14_CR4","doi-asserted-by":"publisher","first-page":"329","DOI":"10.1007\/978-3-031-25069-9_22","volume-title":"Computer Vision - ECCV 2022 Workshops","author":"A Gemelli","year":"2023","unstructured":"Gemelli, A., Biswas, S., Civitelli, E., Llad\u00f3s, J., Marinai, S.: Doc2Graph: a task agnostic document understanding framework based on graph neural networks. In: Karlinsky, L., Michaeli, T., Nishino, K. (eds.) Computer Vision - ECCV 2022 Workshops, pp. 329\u2013344. Springer Nature Switzerland, Cham (2023)"},{"key":"14_CR5","doi-asserted-by":"crossref","unstructured":"Gemelli, A., Vivoli, E., Marinai, S.: Graph neural networks and representation embedding for table extraction in pdf documents. In: 2022 26th International Conference on Pattern Recognition (ICPR), pp. 1719\u20131726 (2022)","DOI":"10.1109\/ICPR56361.2022.9956590"},{"key":"14_CR6","doi-asserted-by":"publisher","unstructured":"Gogar, T., Hubacek, O., Sedivy, J.: Deep neural networks for web page information extraction. In: 12th IFIP International Conference on Artificial Intelligence Applications and Innovations (AIAI). vol. AICT-475, pp. 154\u2013163. Thessaloniki, Greece (2016). https:\/\/doi.org\/10.1007\/978-3-319-44944-9_14","DOI":"10.1007\/978-3-319-44944-9_14"},{"key":"14_CR7","unstructured":"Hotti, A., Risuleo, R.S., Magureanu, S., Moradi, A., Lagergren, J.: The Klarna product page dataset: Web element nomination with graph neural networks and large language models. Transactions on Machine Learning Research 2024 (2024)"},{"key":"14_CR8","doi-asserted-by":"publisher","unstructured":"Kumar, A., Morabia, K., Wang, W., Chang, K., Schwing, A.: CoVA: context-aware visual attention for webpage information extraction. In: Malmasi, S., Rokhlenko, O., Ueffing, N., Guy, I., Agichtein, E., Kallumadi, S. (eds.) Proceedings of the Fifth Workshop on e-Commerce and NLP (ECNLP 5), pp. 80\u201390. Association for Computational Linguistics, Dublin, Ireland (2022). https:\/\/doi.org\/10.18653\/v1\/2022.ecnlp-1.11","DOI":"10.18653\/v1\/2022.ecnlp-1.11"},{"issue":"11","key":"14_CR9","doi-asserted-by":"publisher","first-page":"13166","DOI":"10.1609\/aaai.v37i11.26546","volume":"37","author":"Z Li","year":"2023","unstructured":"Li, Z., Shao, B., Shou, L., Gong, M., Li, G., Jiang, D.: WIERT: web information extraction via render tree. Proc. AAAI Conf. Artif. Intell. 37(11), 13166\u201313173 (2023). https:\/\/doi.org\/10.1609\/aaai.v37i11.26546","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"14_CR10","doi-asserted-by":"publisher","unstructured":"Lin, B.Y., Sheng, Y., Vo, N., Tata, S.: FreeDOM: a transferable neural architecture for structured information extraction on web documents. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 1092\u20131102. KDD \u201920, Association for Computing Machinery, New York, NY, USA (2020). https:\/\/doi.org\/10.1145\/3394486.3403153","DOI":"10.1145\/3394486.3403153"},{"key":"14_CR11","doi-asserted-by":"publisher","unstructured":"Riba, P., Dutta, A., Goldmann, L., Forn\u00e9s, A., Ramos, O., Llad\u00f3s, J.: Table detection in invoice documents by graph neural networks. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 122\u2013127 (2019). https:\/\/doi.org\/10.1109\/ICDAR.2019.00028","DOI":"10.1109\/ICDAR.2019.00028"},{"key":"14_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2026.114651","volume":"191","author":"BV Truong","year":"2026","unstructured":"Truong, B.V., Pham, P., Nguyen, L.T., Nguyen, N.T., Vo, B.: Web data analysis using a hybrid approach of DOM processing and deep learning models. Appl. Soft Comput. 191, 114651 (2026)","journal-title":"Appl. Soft Comput."},{"key":"14_CR13","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1007\/978-3-031-41734-4_4","volume-title":"Document Analysis and Recognition - ICDAR 2023","author":"J Wang","year":"2023","unstructured":"Wang, J., et al.: A graphical approach to document layout analysis. In: Fink, G.A., Jain, R., Kise, K., Zanibbi, R. (eds.) Document Analysis and Recognition - ICDAR 2023, pp. 53\u201369. Springer Nature Switzerland, Cham (2023)"}],"container-title":["Lecture Notes in Computer Science","Web Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-29372-5_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T02:49:50Z","timestamp":1781837390000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-29372-5_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032293718","9783032293725"],"references-count":13,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-29372-5_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"20 June 2026","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":"Lyon","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":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 June 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 June 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icwe2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icwe2026.webengineering.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}