{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T16:42:26Z","timestamp":1791996146351,"version":"4.4.0"},"reference-count":57,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2005,6,1]],"date-time":"2005-06-01T00:00:00Z","timestamp":1117584000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["World Wide Web"],"published-print":{"date-parts":[[2005,6]]},"DOI":"10.1007\/s11280-004-4873-3","type":"journal-article","created":{"date-parts":[[2005,2,28]],"date-time":"2005-02-28T18:41:36Z","timestamp":1109616096000},"page":"179-224","source":"Crossref","is-referenced-by-count":59,"title":["Automating Content Extraction of HTML Documents"],"prefix":"10.1007","volume":"8","author":[{"given":"Suhit","family":"Gupta","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gail E.","family":"Kaiser","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peter","family":"Grimm","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael F.","family":"Chiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Justin","family":"Starren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","reference":[{"key":"CR1","volume-title":"Statistics and Sources for Professionals","author":"American Foundation for the Blind","year":"2000","unstructured":"American Foundation for the Blind, Statistics and Sources for Professionals, American Foundation for the Blind: New York, 2000."},{"key":"CR2","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1016\/S0169-7552(98)00110-X","volume":"30","author":"S. Brin","year":"1998","unstructured":"S. Brin and L. Page, ?The anatomy of a large-scale hypertextual web search engine,? Computer Networks and ISDN Systems 30, 1998, 107?117.","journal-title":"Computer Networks and ISDN Systems"},{"key":"CR3","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1145\/129875.129877","volume":"35","author":"C. Brown","year":"1992","unstructured":"C. Brown, ?Assistive technology computers and personal with disabilities,? Communications of the ACM 35, 1992, 36?45.","journal-title":"Communications of the ACM"},{"key":"CR4","doi-asserted-by":"crossref","unstructured":"M. H. Brown and R. A. Shillner, ?A new paradigm for browsing the Web,? in Proc. of Human Factors in Computing Systems (CHI?95 Conference Companion), 1995.","DOI":"10.1145\/223355.223694"},{"key":"CR5","doi-asserted-by":"crossref","unstructured":"O. Buyukkokten, H. Garcia-Molina, and A. Paepcke, ?Accordion summarization for end-game browsing on PDAs and cellular phones,? in Proc. of Conference on Human Factors in Computing Systems (CHI?01), 2001.","DOI":"10.1145\/365024.365102"},{"key":"CR6","doi-asserted-by":"crossref","unstructured":"O. Buyukkokten, H. Garcia-Molina, and A. Paepcke, ?Seeing the whole in parts: text summarization for Web browsing on handheld devices,? in Proc. of 10th Internat. World-Wide Web Conference, 2001.","DOI":"10.1145\/371920.372178"},{"key":"CR7","unstructured":"O. Buyukkokten, H. Garcia-Molina, and A. Paepcke, ?Text summarization for Web browsing on handheld devices,? in Proc. of 10th Internat. World-Wide Web Conference, 2001."},{"key":"CR8","doi-asserted-by":"crossref","unstructured":"Y. Chen, W. Y. Ma, and H. J. Zhang, ?Detecting Web page structure for adaptive viewing on small form factor devices,? in Proc. WWW?03, Budapest, Hungary, May 2003.","DOI":"10.1145\/775152.775184"},{"key":"CR9","unstructured":"M. Chiang, ?World Wide Web accessibility by visually disabled patients: Problems and solutions,? Final Report for CS6125 WHIM, Columbia University?s Computer Science Department."},{"key":"CR10","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1145\/379537.379550","volume":"8","author":"W. Chisolm","year":"2001","unstructured":"W. Chisolm, G. Vanderheiden, and I. Jacobs, ?Web content accessibility guidelines 1.0,? Interactions 8, 2001, 35?54.","journal-title":"Interactions"},{"key":"CR11","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1145\/208143.208161","volume":"2","author":"W. K. Edwards","year":"1995","unstructured":"W. K. Edwards, E. D. Mynatt, and K. Stockton, ?Access to graphical interfaces for blind users,? Interactions 2, 1995, 54?67.","journal-title":"Interactions"},{"key":"CR12","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/5657.001.0001","volume-title":"Protocol Analysis: Verbal Reports as Data","author":"K. A. Ericsson","year":"1993","unstructured":"K. A. Ericsson and H. A. Simon, Protocol Analysis: Verbal Reports as Data, MIT Press: Cambridge, MA, 1993."},{"key":"CR13","unstructured":"A. Finn, N. Kushmerick, and B. Smyth, ?Fact or fiction: content classification for digital libraries,? in Proc. of Joint DELOS?NSF Workshop on Personalisation and Recommender Systems in Digital Libraries (Dublin), 2001."},{"key":"CR14","unstructured":"S. Hanzlik, ?Gorilla design studios presents: the hosts file,? Gorilla Design Studios, August 31, 2002, http:\/\/accs-net.com\/hosts\/"},{"key":"CR15","unstructured":"http:\/\/sourceforge.net\/projects\/wpar"},{"key":"CR16","unstructured":"http:\/\/www-3.ibm.com\/able\/solution_offerings\/hpr.html"},{"key":"CR17","unstructured":"http:\/\/www.apache.org\/"},{"key":"CR18","unstructured":"http:\/\/www.apache.org\/~andyc\/neko\/doc\/html\/"},{"key":"CR19","unstructured":"http:\/\/www.avantbrowser.com"},{"key":"CR20","unstructured":"http:\/\/www.bitstream.com\/wireless"},{"key":"CR21","unstructured":"http:\/\/www.bitstream.com\/wireless\/server\/workflow.html"},{"key":"CR22","unstructured":"http:\/\/www.dolphinuk.co.uk\/products\/hal.htm"},{"key":"CR23","unstructured":"http:\/\/www.eclipse.org\/articles\/Article-Accessibility\/accessibility.html"},{"key":"CR24","unstructured":"http:\/\/www.eclipse.org\/articles\/Article-SWT-Design-1\/SWT-Design-1.html"},{"key":"CR25","unstructured":"http:\/\/www.gnu.org\/software\/gcc\/java\/"},{"key":"CR26","unstructured":"http:\/\/www.greenlightwireless.net\/services\/default.asp"},{"key":"CR27","unstructured":"http:\/\/www.junkbusters.com"},{"key":"CR28","unstructured":"http:\/\/www.microsoft.com\/enable\/"},{"key":"CR29","unstructured":"http:\/\/www.microsoft.com\/technet\/treeview\/default.asp?url=\/technet\/prodtechnol\/winxppro\/reader_overview.asp"},{"key":"CR30","unstructured":"http:\/\/www.mozilla.org"},{"key":"CR31","unstructured":"http:\/\/www.openxml.org"},{"key":"CR32","unstructured":"http:\/\/www.opera.com"},{"key":"CR33","unstructured":"http:\/\/www.promotiondata.com\/article.php?sid=190"},{"key":"CR34","unstructured":"http:\/\/www.webaim.org\/simulations\/screenreader"},{"key":"CR35","unstructured":"http:\/\/www.webwiper.com"},{"key":"CR36","doi-asserted-by":"crossref","unstructured":"E. Kaasinen, M. Aaltonen, J. Kolari, S. Melakoski, and T. Laakko, ?Two approaches to bringing Internet services to WAP devices,? in Proc. of 9th Internat. World-Wide Web Conference, 2000.","DOI":"10.1016\/S1389-1286(00)00041-4"},{"key":"CR37","unstructured":"M.-Y. Kan, Private communication, Columbia NLP group, 2002."},{"key":"CR38","unstructured":"M.-Y. Kan, J. L. Klavans, and K. R. McKeown, ?Linear segmentation and segment relevance,? in Proc. of 6th Internat. Workshop of Very Large Corpora (WVLC-6), 1998."},{"key":"CR39","unstructured":"K. R. McKeown, R. Barzilay, D. Evans, V. Hatzivassiloglou, M. Y. Kan, B. Schiffman, and S. Teufel, ?Columbia multi-document summarization: approach and evaluation,? in Proc. of Document Understanding Conference, 2001."},{"key":"CR40","doi-asserted-by":"crossref","unstructured":"R. L. Kline and E. P. Glinert, ?Improving GUI accessibility for people with low vision,? in Proc. of Human Factors in Computing Systems (CHI?95 Conference Companion), 1995.","DOI":"10.1145\/223904.223919"},{"key":"CR41","unstructured":"M. Kunze and D. Rosner, ?An XML-based approach for the presentation and exploitation of extracted information,? in Proc. of the 19th Internat. Conference on Computational Linguistics (Coling), 2002."},{"key":"CR42","first-page":"406","volume":"13","author":"A. W. Kushniruk","year":"1996","unstructured":"A. W. Kushniruk, D. R. Kaufman, V. L. Patel , ?Assessment of a computerized patient record system: A cognitive approach to evaluating medical technology,? MD Comput. 13, 1996, 406?415.","journal-title":"MD Comput."},{"key":"CR43","unstructured":"A. W. Kushniruk, V. L. Patel, and J. J. Cimino, ?Usability testing in medical informatics: cognitive approaches to evaluation of information systems and user interfaces,? in Proc. AMIA Sympos. 1997, pp. 218?222."},{"key":"CR44","unstructured":"A. W. Kushniruk, M. Y. Kan, K. McKeown et al., ?Usability evaluation of an experimental text summarization system and three search engines: Implications for the reengineering of health care interfaces,? in Proc. AMIA Sympos. 2002, pp. 420?424."},{"key":"CR45","unstructured":"C. Lewis, Using the ?Thinking-Aloud? method in cognitive interface design, IBM Research Report RC 9265, IBM Thomas J. Watson Research Center: Yorktown Heights, NY, 1982."},{"key":"CR46","doi-asserted-by":"crossref","unstructured":"I. Muslea, S. Minton, and C. Knoblock, ?A hierarchal approach to wrapper induction,? in Proc. of the 3rd Internat. Conference on Autonomous Agents (Agents?99), 1999.","DOI":"10.1145\/301136.301191"},{"key":"CR47","volume-title":"Usability Engineering","author":"J. Nielsen","year":"1993","unstructured":"J. Nielsen, Usability Engineering, Academic Press: New York, 1993."},{"key":"CR48","doi-asserted-by":"crossref","unstructured":"I. J. Pitt and A. D. N. Edwards, ?Improving the usability of speech-based interfaces for blind users,? in Proc. of the 2nd Annual ACM Conference on Assistive Technologies (ASSETS), 1996.","DOI":"10.1145\/228347.228367"},{"key":"CR49","unstructured":"A. F. R. Rahman, H. Alam, and R. Hartono, ?Content extraction from HTML documents,? in Proc. of the 1st Internat. Workshop on Web Document Analysis (WDA2001), 2001."},{"key":"CR50","unstructured":"A. F. R. Rahman, H. Alam, and R. Hartono, ?Understanding the flow of content in summarizing HTML documents,? in Proc. of the Internat. Workshop on Document Layout Interpretation and Its Applications, DLIA?01, September 2001."},{"key":"CR51","doi-asserted-by":"crossref","unstructured":"W. Reichl, B. Carpenter, J. Chu-Carroll, and W. Chou, ?Language modeling for content extraction in human?computer dialogues,? in Proc. of the Internat. Conference on Spoken Language Processing (ICSLP), 1998.","DOI":"10.21437\/ICSLP.1998-487"},{"key":"CR52","unstructured":"D. P. Rice, Chronic Care in America: A 21st Century Challenge, Institute for Health and Aging, University of California, San Francisco, Robert Wood Johnson Foundation: Princeton, NJ, 1996."},{"key":"CR53","volume-title":"Designing the User Interface: Strategies for Effective Human?Computer Interaction","author":"B. Schneiderman","year":"1997","unstructured":"B. Schneiderman, Designing the User Interface: Strategies for Effective Human?Computer Interaction, 3rd ed., Addison-Wesley: Reading, MA, 1997."},{"key":"CR54","doi-asserted-by":"crossref","first-page":"857","DOI":"10.1016\/S0002-9394(02)01795-6","volume":"134","author":"I. U. Scott","year":"2002","unstructured":"I. U. Scott, W. J. Feurer, and J. A. Jacko, ?Impact of graphical user interface screen features on computer task accuracy and speed in a cohort of patients with age-related macular degeneration,? Amer. J. Ophthalmol. 134, 2002, 857?862.","journal-title":"Amer. J. Ophthalmol."},{"key":"CR55","unstructured":"J. A. Shoemaker, ?Vision problems in the US: prevalence of adult vision impairment and age-related eye diseases in America,? National Eye Institute: Bethesda, MD, 2002."},{"key":"CR56","doi-asserted-by":"crossref","unstructured":"N. Wacholder, D. Evans, and J. Klavans, ?Automatic identification and organization of index terms for interactive browsing,? in Proc. of the Joint Conference on Digital Libraries?01, 2001.","DOI":"10.1145\/379437.379468"},{"key":"CR57","unstructured":"M. Welsh, ?The staged event-driven architecture for highly-concurrent server applications,? Ph.D. Qualifying Examination Proposal, UC Berkeley, December 2000, http:\/\/www.cs.berkeley.edu\/~mdw\/papers\/quals-seda.pdf"}],"container-title":["World Wide Web"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11280-004-4873-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11280-004-4873-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11280-004-4873-3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,2]],"date-time":"2023-05-02T14:32:09Z","timestamp":1683037929000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11280-004-4873-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2005,6]]},"references-count":57,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2005,6]]}},"alternative-id":["5384873"],"URL":"https:\/\/doi.org\/10.1007\/s11280-004-4873-3","relation":{},"ISSN":["1386-145X","1573-1413"],"issn-type":[{"value":"1386-145X","type":"print"},{"value":"1573-1413","type":"electronic"}],"subject":[],"published":{"date-parts":[[2005,6]]}}}