William W. Cohen. Learning rules that classify e-mail. In Proceedings of the 1996 AAAI Spring Symposium on Machine Learning in Information Access (MLIA '96), Stanford, CA, USA, 1996. AAAI Press.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....structures that can help in making sense of large volumes of e mail. An active line of research has applied text indexing and classification to develop e mail interfaces that organize incoming messages into folders on specific topics, sometimes recommending further actions on the part of a user [5, 10, 14, 32, 33, 42, 51, 52, 54, 55, 56, 59, 60] in e#ect, this framework seeks to automate a kind of filing system that many users implement manually. There has also been work on developing query interfaces to fully indexed collections of e mail [8] My interest here is in exploring organizing structures based more explicitly on the role ....

W. Cohen. "Learning rules that classify e-mail." Proc. AAAI Spring Symp. Machine Learning and Information Access, 1996.

....should be filtered. As a result, there has recently been a growing interest in creating automatic systems to help users managing an extensive email flow. Examples of such systems are PEA[19] MailCat[16] Re:Agent[2] and others. Generally, the main tool for email management is text classification[15, 4, 3]. A classifier is a system that automatically classifies texts into one (or more) of a discrete set of predefined categories. For example, for email management one could benefit from a system that classifies incoming messages as junk and non junk or as important and unimportant. Most text ....

.... a definition of what makes an interesting email message, so that this definition will successfully pick interesting email from the user s inbox in the future (e.g. it will work well on examples di#erent from the ones in the training set) It is well known, both theoretically[17] and practically[4, 9], that more training data we have, the more accurate classification system we get. In general, we need hundreds or even thousands of labeled examples to produce a reasonably accurate classifier. For example, recently Microsoft has released the product Outlook Mobile Manager that can prioritize ....

William W. Cohen. Learning Rules that Classify Email. In Proc. of the AAAI Spring Simposium on Machine Learning in Information Access, 1996.

....structures that can help in making sense of large volumes of e mail. An active line of research has applied text indexing and classification to develop e mail interfaces that organize incoming messages into folders on specific topics, sometimes recommending further actions on the part of a user [4, 9, 13, 29, 30, 39, 46, 47, 49, 50, 51, 53, 54] in effect, this framework seeks to automate a kind of filing system that many users implement manually. There has also been work on developing query interfaces to fully indexed collections of e mail [7] My interest here is in exploring organizing structures based more explicitly on the role ....

W. Cohen. "Learning rules that classify e-mail." Proc. AAAI Spring Symp. Machine Learning and Information Access, 1996.

....except training examples are distributed over time: S t = y) y = f(#x) for t = 1, #. Now, f t approximates f . On line learning is important for applications in which we cannot collect all pertinent training data before applying an algorithm, and these include e mail sorting [24], calendar scheduling [25] intelligent user interfaces [8] image analysis [26] and computer intrusion detection [4] If the algorithm discards f t 1 and generates f t from S i , for i = 1, t, then it is on line batch or temporal batch with full instance memory. If the algorithm ....

W. Cohen, "Learning rules that classify e-mail," in Machine learning in information access: Papers from the 1996.

....explicit. 2 Motivation Vast amounts of documents are available on line, and classifying them into meaningful semantic categories is a rewarding and challenging task. Applications of classification techniques include browsing assistants [44, 2, 53] information filtering [41] e mail sorting [17, 52, 56], recognizing entities in ontologies [20, 48] and many more [49] While conventional information retrieval focuses primarily on information that is provided by the text that can be found in the documents, Web documents provide additional information through the way in which different documents ....

William W. Cohen. Learning rules that classify e-mail. In M.A. Hearst and H. Hirsh, editors, Proceedings of the AAAI Spring Symposium on Machine Learning in Information Access, pages 18--25. AAAI Press, 1996. Technical Report SS-96-05.

....structures that can help in making sense of large volumes of e mail. An active line of research has applied text indexing and classification to develop e mail interfaces that organize incoming messages into folders on specific topics, sometimes recommending further actions on the part of a user [4, 9, 13, 30, 31, 40, 49, 50, 52, 53, 54, 56, 57] in effect, this framework seeks to automate a kind of filing system that many users implement manually. There has also been work on developing query interfaces to fully indexed collections of e mail [7] My interest here is in exploring organizing structures based more explicitly on the role ....

W. Cohen. "Learning rules that classify e-mail." Proc. AAAI Spring Symp. Machine Learning and Information Access, 1996.

....the risk of deleting email which is not spare. So this is not a satisfactory solution. For this reason, a lot of software has been developed to recognize and filter spam email. An frequently used approach is the creation of rules to filter emails. Programs like RIPPER possess a database of rules [1]. It is difficult to adapt these rules to changes of the email content and to keep them up to date. Other spare filters [6, 13] work with algorithms developed for text classification. Although these filers delete a huge amount of spare, they only work isolated from other filters. So they cannot ....

W.W. Cohen (1996): Learning Rules that classify e-mail. Proceedings of the AAAI Spring Symposium on Machine Learning in Information Access 18-25, AAAI Press.

....of text document categorisation algorithms using the Naive Bayes, Support Vector Machines, multi layer Perceptron and k NN classifiers. Work in e mail text classification has also been undertaken by some researchers in the context of automated e mail document filtering and filing. Cohen [7] learned rule sets based on a small number of keywords in the e mail. Sahami et al. [28] focused on the more specific problem of filtering junk e mail using a Naive Bayesian classifier and incorporating domain knowledge using manually constructed domain specific attributes such as phrasal features ....

W. Cohen. "Learning rules that classify e-mail". In Proc. Machine Learning in Information Access: AAAI Spring Symposium (SS-96-05), pages 18--25, 1996.

....of text document categorisation algorithms using the Naive Bayes, Support Vector Machines, multi layer Perceptron and k NN classifiers. Work in e mail text classification has also been undertaken by some researchers in the context of automated e mail document filtering and filing. Cohen [6] learned rule sets based on a small number of keywords in the e mail. Sahami et al. [27] focused on the more specific problem of filtering junk e mail using a Naive Bayesian classifier and incorporating domain knowledge using manually constructed domain specific attributes such as phrasal features ....

W. Cohen. "Learning rules that classify e-mail". In Proc. Machine Learning in Information Access: AAAI Spring Symposium (SS-96-05), pages 18--25, 1996.

.... by building a classifier system capable of minimizing three main measures: error rate, false positive rate, and false negative rate [27] Among the techniques used for classifying spam messages, we mention the Rocchio approach (and similar approaches based on Support Vector Machines [7] Papers [4] and [13] describe two rule based systems exploiting text mining techniques for the classification of e mail correspondence. These approaches differ mainly in the preprocessing phase: in the first approach a simple boolean vector model is used; on the other side, 13] proposes a frequency based ....

W. W. Cohen. Learning Rules that classify E-mail. In Proc. of the 1996.

....on the Reuters 21578 dataset. 2.1 General classi cation A number of systems have examined di erent ways of classifying email using Machine Learning and IR approaches. Some of these systems are described below in approximate chronological order. Learning Rules that Classify E Mail, by Cohen [6]. Cohen uses the RIPPER learning algorithm that induces rules that spot keywords for classifying email. The paper compares this keyword spotting approach with an IR method, based on TF IDF weighting. Both approaches show similar accuracy, RIPPER 87 94 and TF IDF 85 94 . However, Cohen argues ....

....light of our goal of scrutability. Keyword The keyword approach induces a set of clauses in a similar way to Quinlan and Cameron Jones Foil [5] The literals considered are whether a particular word is contained in one of the : sender, subject, or body elds. In a similar way to Cohen s Ripper [6] this learner starts to induce rules for the smallest folder and then progresses to larger ones. TF IDF This approaches is an incremental learner maintaining a table of word frequencies as messages arrive. For details the reader is directed to Segal and Kephart s paper [19] DTree This is a ....

W. Cohen. Learning rules that classify e-mail. In Papers from the AAAI Spring Symposium on Machine Learning in Information Access, pages 18-25, 1996.

No context found.

W. W. Cohen. (1996). Learning Rules that Classify EMail.

No context found.

William W. Cohen. Learning rules that classify e-mail. In Proceedings of the 1996 AAAI Spring Symposium on Machine Learning in Information Access (MLIA '96), Stanford, CA, USA, 1996. AAAI Press.

No context found.

William W. Cohen. Learning rules that classify email. In Proceedings of the 1996 AAAI Spring Symposium on Machine Learning in Information Access (MLIA '96), Stanford, CA, USA, 1996. AAAI Press.

No context found.

W. Cohen. Learning rules that classify e-mail. In Proceeding of the 1996.

No context found.

W. Cohen. "Learning rules that classify e-mail." Proc. AAAI Spring Symp. Machine Learning and Information Access, 1996.

No context found.

W. Cohen. Learning rules that classify email. In Proceedings of the IEEE Spring Symposium on Machine Learning for Information Access, 1996.

No context found.

W. W. Cohen. Learning rules that classify e-mail. In M. Hearst and H. Hirsh, editors, Proceedings of the AAAI Spring Symposium on Machine Learning in Information Access, pages 18--25. AAAI Press, 1996. Technical Report SS-96-05.

No context found.

William Cohen. Learning Rules that Classify E-mail. AAAI Spring Symposium on Machine Learning in Information Access, 1996.

No context found.

W. Cohen. Learning rules that classify e-mail. In Proceeding of the 1996.

No context found.

W.W. Cohen, Learning rules that classify e-mail, in: Proc. of the 1996.

No context found.

William W. Cohen. Learning rules that classify email. In Proceedings of the 1996 AAAI Spring Symposium on Machine Learning in Information Access (MLIA '96), Stanford, CA, USA, 1996. AAAI Press.

No context found.

Cohen, W.W. Learning Rules that Classify E-Mail. Proceedings of the AAAI Spring Symposium on Machine Learning in Information Access, Stanford, California, 1996.

No context found.

Cohen W.W. Learning Rules that Classify E-mail. In Proceedings of the 1996.

No context found.

Cohen, W.W. Learning Rules that Classify E-Mail. Proceedings of the AAA/Spring Symposium on Machine Learning in Information Access, Stanford, California, 1996.

First 50 documents  Next 50

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC