Foltz, P.W.: Using Latent Semantic Indexing for Information Filtering. Proc. of the ACM Conference on Office Information Systems. Boston, USA (1990) 40-47  Home/Search   Document Not in Database   Summary   Related Articles   Check

....the classifier was trained, the filtering system was used to filter documents from the unknown incoming stream without any further adaptation. Methods used for learning classifiers range from TF IDF (Term Frequency Inverse Document Frequency) vectors [Salton 1988] latent semantic indexing [Foltz 1990, Hull 1994, Foltz 1996] or probability theory [Lewis and Gale 1994, Lewis et al. 1996] The filtering queries may be constructed refined based on a method known as relevance feedback [Rocchio 1971] which incorporates relevant documents retrieved by the system into subsequent versions of the ....

Foltz, P.W. Using Latent Semantic Indexing for Information Filtering Proceedings of the Conference on Office Information Systems, Cambridge, MA, 1990.

....automatically answering questions, the system will allow the user to specify if the answer was satisfactory, and escalate unanswered question to a human tech support, following Ackerman s design. The system will likely use latent semantic indexing (LSI) which in theory can give better results [Foltz 1990], although [Masterton 1997] was successful using only keyphrase matching. Another interesting question is how useful the container graph hierarchy structure will be. Will multiple inheritance prove useful In what sense can this structure be considered an ontology for the domain I expect that ....

Peter W. Foltz, Using Latent Semantic Indexing for Information Filtering, in R. B. Allen (Ed.) Proceedings of the Conference on Office Information Systems, Cambridge, MA, 40-47, 1990 http://www-psych.nmsu.edu/~pfoltz/cois/filtering-cois.html

....Web , Scientific American, 284(5) pp. 34 43. 13] Bharat, K. y Henzinger, M. 1998) Improved Algorithms for Topic Distillation in a Hypedinked Environment , Proceedings of SIGIR 98, 21st ACM International Conference on Research and Development in Information Retrieval, Melbourne, Australia. [14] Billsus, D. y Pazzani, M.J. 1998) Learning Collaborative Information Filters , Proceedings of the International Conference on Machine Learning, Madison, Wisconsin, EE.UU. 15] Bray, T. Paoli, J. Sperberg McQueen, C.M. y Maler, E. 2000) Extensible Markup Language (XML) 1.0 (Second ....

....be useful if they add semantics in an analogous way as ontologies, whereas they should be able to be automatically generated and processed as keywords. Currently there are enough techniques able to be used or adapted to carry out this automatic extraction task, such as Latent Semantic Indexing s [14] or others that were already mentioned for the semi automatic generation of ontologies [10] 11] In the next section we will examine how semantics can be obtained using concepts without resorting to any ontology support. 3.2. Document Taxonomies To give meaning to a document the Semantic Web ....

[Article contains additional citation context not shown here]

P.W. Foltz, "Using Latent Semantic Indexing for Information Filtering," In Proceedings of the ACM Conference on Office Information Systems, Boston, USA, 1990, pp. 40-47.

....representations of texts and terms. Schutze s approach is essentially a neural network approach, so we will review it later in the context of other neural network research. The last method we will outline here is the Latent Semantic Indexing (LSI) approach [48] 37] 31] 85] 32] 36] [40]. This approach attempts to represent documents so that vector similarity is a better indicator of semantic relatedness than is typical in the VSM. LSI does this by mapping document vectors from the term space to a much smaller dimension space. This reduced space is intended to represent the major ....

Peter W. Foltz. Using latent semantic indexing for information filtering. In Proceedings of the Conference on Office Information Systems, 1991.

....vectors in this reduced dimension LSI space. Each new document is matched against the vector and if it is similar enough to the interest vector it is recommended to the user. Learning methods like relevance feedback can be used to improve the representation of interest vectors over time. Foltz [11] compared LSI and keyword vector methods for filtering Netnews articles, and found 12 23 advantages for LSI. Dumais and Foltz in [12] compared several different methods for representing users interests for filtering technical memoranda. The most effective method used vectors derived from known ....

P. W. FOLTZ, Using Latent Semantic Indexing for information filtering, in Proceedings of the ACM Conference on Office Information Systems (COIS), 1990, pp. 40--47.

....computation of cost benefit to the user and through some pricing mechanisms. A variety of approaches have been used to get at the semantic contents of the documents. Oval [29] is an example of a system which uses a keyword based approach to match user defined rules to incoming documents. Foltz [10] demonstrates the use of LSI for information filtering and evaluates it for filtering Netnews articles. 11] performs a similar experiment for the domain of technical reports. INFOSCOPE [9] consists of rule based agents which observe usage patterns and make suggestions to the user. The agents ....

Foltz, P. W., Using Latent Semantic Indexing for information filtering, Proceegings of the ACM Conference on Office Information Systems, ACM/SIGOIS, New York, 1990, pp. 40-47.

....the subsequent decade, occasional papers on information filtering applications appeared in the literature. While electronic mail was the original domain about which Denning had written, subsequent papers have addressed newswire articles, Internet News articles, 3 and broader network resources [10, 19, 30, 43]. The most influential paper of this period was published in the Communications of the ACM by Malone and others in 1987 [26] There they introduced three paradigms for information selection, cognitive, economic, and social , based on their work with a system they called the Information Lens. ....

....either selection or rejection of that article. These rules (e.g. select if newsgroup is rec.sewing and bobbin appears in the subject field) are learned using heuristics which can be modified by the user. Foltz applied an instance based learning technique to selection of Internet News articles [10]. He retained representations of about 100 articles from a training collection which the user designated as interesting, and then ranked new articles by the cosine between their representation and the nearest retained representation. In other words, articles were ranked most highly if they were ....

Peter W. Foltz. Using latent semantic indexing for information filtering. In Frederick H. Lochovsky and Robert B. Allen, editors, Conference on Office Information Systems, pages 40--47. ACM, April 1990. http://wwwpsych. nmsu.edu/¸pfoltz/cois/filtering-cois.html.

....and queries into a subspace in which semantic relationships from the term document matrix are preserved while term usage variations are suppressed. The span of this subspace is uniquely defined by the set of singular vectors. Foltz was the first to apply LSI to the text filtering problem [4]. He tried three cognitive filtering techniques on a small USENET news collection: closest match, average match, and clustering. Dumais has evaluated Foltz s average match technique in the first three Text REtrieval Conferences (TREC) 3] In the average match technique, the vector representation ....

P. W. Foltz. Using latent semantic indexing for information filtering. In F. H. Lochovsky and R. B. Allen, editors, Conference on Office Information Systems, pages 40--47. ACM, April 1990.

....and financial and law databases. 5.6. Conclusions Latent Semantic Indexing is a novel information retrieval model that will become more and more valuable as the amount of electronic information increases. It has been used effectively in a variety of applications, including information filtering [9] and cross language information retrieval [25] With the recent explosion in the amount of information available on the World Wide Web, the advent of electronic commerce, and the ability of LSI to find information similar to (rather than literally matching) other information, LSI has the potential ....

P. Foltz. Using latent semantic indexing for information filtering. In Proceedings of the ACM Conference on Office Information Systems (COIS), pages 40--47, 1990.

....memes. LSI was originally proposed and has been extensively studied by Susan Dumais of Bell Communications Research and her colleagues (Furnas, et.al. 1988; Deerwester, et.al. 1990; Dumais 1992, 1993) Peter Foltz investigated the use of LSI in clustering NetNews articles for information filtering (Foltz 1990). Michael Berry and co authors researched a variety of numerical approaches to efficiently perform SVD on large sparse matrices such as those found in text retrieval (Berry 1992; Berry, et.al. 1993; Berry Fierro 1995) The SVD technique decomposes the term document matrix into a left and right ....

Foltz, P.W. (1990). Using Latent Semantic Indexing for Information Filtering. Proceedings of the 5th Conference on Office Information Systems. ACM SIGOIS Bulletin vol.

....Cosine similarity measures are used to score the article against each interest in the profile so that a pointer to the article can be added to the reading list for each interest in decreasing order of similarity to that interest. Foltz reports results using LSI for filtering news articles in [6] and Foltz and Dumais apply LSI to filtering technical reports in [7] Both text translation and term vector translation use some form of automatic translation to transform each article into a common representation and then make relevance determinations on what is essentially a monolingual ....

P. W. Foltz. Using latent semantic indexing for information filtering. In F. H. Lochovsky and R. B. Allen, editors, Conference on Office Information Systems, pages 40--47. ACM, April 1990.

....The LSI analysis involves a completely automatic statistical analysis. Because no human effort is required for knowledge engineering, the LSI method is widely applicable to different domains. The LSI method can be used both for information retrieval and information filtering applications [5]. It has also been used successfully for crosslanguage retrieval [6] and as a way of suggesting new indexing terms for conventional retrieval methods. Several experiments using LSI for information filtering will be summarized. An important issue in this work is how best to represent people s ....

Peter W. Foltz. Using latent semantic indexing for information filtering. In Frederick H. Lochovsky and Robert B. Allen, editors, Conference on Office Information Systems, pages 40--47. ACM, April 1990.

....vectors in this reduced dimension LSI space. Each new document is matched against the vector and if it is similar enough to the interest vector it is recommended to the user. Learning methods like relevance feedback can be used to improve the representation of interest vectors over time. Foltz [10] compared LSI and keyword vector methods for filtering Netnews articles, and found 12 23 advantages for LSI. Dumais and Foltz in [11] compared several different methods for representing users interests for filtering technical memoranda. The most effective method used vectors derived from known ....

P. W. Foltz, Using Latent Semantic Indexing for information filtering, in Proceedings of the ACM Conference on Office Information Systems (COIS), 1990, pp. 40--47.

No context found.

Foltz, P.W.: Using Latent Semantic Indexing for Information Filtering. Proc. of the ACM Conference on Office Information Systems. Boston, USA (1990) 40-47

No context found.

P. Foltz, "Using Latent Semantic Indexing for Information Filtering." Proceedings of the ACM Conference on Office Information Systems, ACM/SIGOIS, New York, 1990.

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