Labels:text | screenshot | font | menu | document OCR: AUTHORS P. Mars. "Agents that Roduct Work and Information Overload ?; Coinig; ACM, Vol. 37, No. 7. July 1994, pp. 30.40. Bag of Word's + Selecting Memory- based 'header information: keywords D. Mladanic, Personal Web Watcher, Implementation and Design; Tech - Report IJS-DP, 7472, Camegie Mellon Univ ., Pittsburgh: . 996; http://www.t.s.cmo:golf Bab ot words, (ro) et alonhalivity Naive Bayes ,:: TextLearning/pww nearest neighbor [] Miadenic ind hy GroSeinik, "renturle Selection for Classification Based on Todos etbag of words using' Hierarchy, "wowhim Notes or Learning from Tor oid the Who, Cows utomeledge #Stop list to: Naive Bayes 1. canning and (COMALD:95), Carnegie Mellon Univ , Pittsburgl ., 1998; nigrams ( g): minimum ro vs cods rato D. Mladenic and Af Grubolik : Word Sequences as Features in Text Learning. Proc, Seventh Electrotechnical and Computer Security Conf. TERK 98), JEEE Region B. Stovenia Section IEEE. Liculjana, Slovenia ., 1998, pp: 145-148 I. Afouling rado 1 G, Ganascia, winphing an Existing Mach siel camino Algonthor to Text Categorization,"Correctionist, Statistical, and Symbole Approaches RO of words to Leaming for Natural Lanrivage Processing S: Viermier, F; R of, and G. Scheler, eds .. Springer-Verlag, Berlin, 1996, pp. 343-354 K. Whoan'yand A. McColluniti Pool- Based Active Learning for Text Class ticalion,". `Working Notes of Learning fromi Text and the Web, Conit Automated Learning'ang. Bag of words Discovery (CONALD-98); Carnegie Melloni Univ ., Pittsburgh, 1996; http://www. M Pazzini, y Muramalau, and D'Billsust e Syskill'& Webert laentifying interesting Web Sites, "Proc. 13th Nat I Conf. Artificial Intelligence ((4) 96 MAAl press, Menlo Park, Calif ., 1996, pp. 51-61. M. Passant and o.8 lisus$ teamlig and Revising Uset protesi the Icenb ication fait Den ot words of Interesting Web Sies, "Machine ( ewing 2%- Kiover Academic Publishers .: Stop list + TROF Dordrecht, The blethersads :1997,pa: 313,331; Riformalivity naive Bayes nearest neighbor, neural networks, decision trees * Sharlik and I Eliastr Rau:Building Inte getit Agents for Wes Based Tasks" Localized bab of " A Thec y Belinement Approach, " Working Notes of Learning from Tart and the Stop-list: Theory de inemeny Web, Conf Actornaled Learning and Discovery (COWALD-08), Carregis Mellon stemming networks S. Slattery and'I: Cravens toarning to Explor Dochutrent Relationships and Baj of words; Naive Bayes: Structure : The Case for Relationes Learning on the Weby. Working Notes of Learning fromi Text and the Web. Conf. Automalad Leaming and Discovery hypertextigraja (CONALD-98). Carnegie Mellon Univ ., Pittsburgh, 1999; http:/www.cs.cmt. edar- cuna diconald.shtml. 4bakış V.C.C. Compinter Science J Vol. 1, No: 4.Dec.1993. 00. 1-15, Weighting graph : Connectionist combined with H. Sorensen and M. NicEllioutt, " PSUN. A Profiliro-Systemn id' Usenet News!" CUIOM 95 inteligent Informnation Agents Workshop: 1995 algorithms E: Wiener, J.O.Pedersen and A SåNeigend :\ Neural Network Approachto; Jonit Spoling, " Bric Fourth Aan; Symp. Documentthalysis aho thromabon Stup list #: Retrieval (SDAJR 95), information Science Research Inst ., Las Vegas,31995; Icoistic cochession Hemming + in Text Categoricalich and Retrieval: Proce Seventh Alla Iln'y ACM SIGIR' Bayrol words nearest neighbor slat Cont. Research and Development'un Information, Rotnehal, ACM Press: Nowy York, 1994. pp: 13-22. Y. yang, "An Evaluation of Statistical Approaches to Text Categorization." Information Retrieval J ., May 1999.
(2000).iso/ieeei/971/1p51.gif){kind=small}
(2000).iso/ieeei/971/1p50.gif){kind=link}
(2000).iso/ieeei/971/yangf203.gif){kind=link}