Furnas, G. Deerwester, S. Dumais. S. et al. (1988): Information retrieval using a singular value decomposition model of latent semantic structure.In Proc. ACM SIGIR Conf., pages 465-480.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....allows, on the one hand, the use of di#erent words in order to describe the same object and, on the other hand, the same word to be used to describe objects that truly distinct. As a result, lexical based matching methods are at the same time incomplete and imprecise. Latent Semantic Analysis [14] tries to overcome the problems common to the lexical approach by automatically organizing text objects into a semantic structure built to be more appropriate for matching. Once a user has located a relevant document, traditional hypertext navigation usually takes place by the user following the ....

....available to any application by storing them in an open hypertext linkbase. 3. LATENT SEMANTIC ANALYSIS AS INFORMATIONRETRIEVALTECHNIQUE Latent Semantic Analysis (LSA) is a method to orga nize textual information into semantic structures which can be used to retrieve information and browsing [14]. This method has demonstrated improved performance over the traditional vector space technique; it extends the vector space model by modelling term document relationships using a reduced approximation of the column and row space computed by singular value decomposition of the term by document ....

[Article contains additional citation context not shown here]

G. W. Furnas, S. Deerwester, S. T. Dumais, T. K. Landauer, R. A. Harshman, L. A. Streeter, and K. E. Lochbaum. Information retrieval using a singular value decomposition model of latent semantic structure. In Proceedings of the Eleventh International Conference on Research & Development in Information Retrieval, pages 465--480, 1988.

....and ff i are user determined parameters (weights) In this work we set ff i = 1. 2.2.2 Latent semantic indexing (LSI) Each text (or query) is represented by an occurrence vector as in VSM. All database documents (actually their occurrence vectors) form the so called term document matrix . LSI [13] uses Singular Value Decomposition (SVD) to transform the term document matrix into a set of k (typically 100 to 300) orthogonal factors (or axes) from which the original matrix can be approximated by linear combination. Both documents and terms are represented in this space. The location of a ....

G.W. Furnas, S. Deerwester, S.T. Dumais, T.K. Landauer, R. A. Harshman, L.A. Streeter, and K.E. Lochbaum. Information retrieval using a Singular Value Decomposition Model of Latent Semantic Structure. In Intern. Conf. on Research and Development in IR, New York, 1988.

....natural language requests for technical help or advice and, using Latent Semantic Indexing (LSI) returns pointers to nearby research groups. The system constructs expertise index of research groups based on a representative collection of the technical documents they produce. In a test using EEL [20], descriptions of individual experts current projects are used as query to compare how well the system managed to predict which of the 480 Bellcore work groups an expert belonged to. ContactFinder [21,22] is an intelligent agent that monitors discussion groups and extracts contacts in some ....

G. W. Furnas, S. T. Dumais, T. K. Landauer, R. A. Harshman, L. Y. Streeter and K. E. Lochbaum. Information Retrieval using Singular Value Decomposition Model of Latent Semantic Structure, inProceedings of the

....and it may be dicult to identify and access all documents in a search engine. A possible solution is to sample documents of each search engine and use the sampled documents to compute an approximate database centroid. 3.2. Singular Value Decomposition (SVD) Singular Value Decomposition (SVD) (Furnas et al., 1988) has been used as an e ective method for document categorization (Yang and Chute, 1994) In this section, we apply this method for database categorization. We rst review the method in (Yang and Chute, 1994) for assigning a set of documents to a set of categories concepts. Note that the same ....

Furnas G, Deerwester S, Dumais S et al (1988) Information Retrieval Using a Singular Value Decomposition Model of Latent Semantic Structure. Proceedings of ACM SIGIR Conference, Grenoble, France, June 1988, pp. 465-480.

....framework of deriving multidimensional 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 ....

George W. Furnas, Scott Deerwester, Susan T. Dumais, Thomas K. Landauer, Richard A. Harshman, Lyn A. Streeter, and Karen E. Lochbaum. Information retrieval using a singular value decomposition model of latent semantic structure. In Proceedings of the ACM SIGIR, Grenoble, France, 1988.

....natural language requests for technical help or advice and, using Latent Semantic Indexing (LSI) returns pointers to nearby research groups. The system constructs expertise index of research groups based on a representative collection of the technical documents they produce. In a test using EEL (Furnas, et al. 1988), descriptions of individual experts current projects are used as query to compare how well the system managed to predict which of the 480 Bellcore work groups an expert belonged to. ContactFinder (Krulwich and Burkey 1995, 1996) is an intelligent agent that monitors discussion groups and ....

Furnas, G. W., et al. (1988). Information Retrieval using Singular Value Decomposition Model of Latent Semantic Structure. In: Proceedings of ACM SIGIR, Grenoble, France: 465 --- 480.

....of the method in Section 4. 3 Corpus based CLIR approaches 3.1 Previous Researches As we mentioned in Section 2, we use a CLIR method which relies on a parallel corpus in our bootstrapping method. One approach to corpus based CLIR is to use the Latent Semantic Indexing technique proposed by Furnas et al. 1988) on a parallel corpus to construct a language independent representation of queries and documents (Landauer and Littman, 1990) Another approach that relies on a parallel corpus has been suggested by Dunning and Davis (1993) Their method is based on the vector space model and involves the linear ....

Furnas, G. W., Deerwester, S., Dumais, S. T., Landauer, T. K., Harshman, R. A., Streeter, L. A. and Lochbaum, K. E. (1988) Information retrieval using a singular value decomposition model of latent semantic structure. In proceedings of the 11th ACM International Conference on Research and Development in Information Retrieval, pp. 465480.

....variety of things including Usenet news [11] web pages [2, 9] videos [8] movies, music [18] and books. Some systems refer a user to other people, which is essentially making recommendations about people. Who Knows and Referral Web are typical examples of systems that make referrals. Who Knows [6, 20] found people who knew something about a topic, based on a profile constructed from exemplary work documents. In a sense, documents were seen as surrogates for people s interests in a twist on standard IR models. On the other hand, Referral Web [10] used social networks to assist expertise ....

Furnas, G.W., Deerwester, S., Dumais, S.T., Landauer, T.K., Harshman, R.A., Streeter, L.A. and Lochbaum, K.E., Information retrieval using a singular value decomposition model of latent semantic structure. SIGIR'88, 465 - 480.

....database representatives. The following are research issues to be examined. 1. The experimental results obtained by us are based on term matching. In other words, if query q and document d have no term in common, then d cannot be retrieved. However, techniques such as Latent Semantic Indexing [13] may permit q and d to match after term transformation. In that case, our database representative should be based on the transformed terms, i.e. statistics such as the maximum term weights are collected on the transformed terms. When a query is submitted, its terms are transformed into a new set ....

G. Furnas, S. Deerwester, S. Dumais, T. Landauer, R. Harshman, L. Streeter and K. Lochbaum. Information Retrieval Using a Singular Value Decomposition Model of Latent Semantic Structure. ACM SIGIR Conference, 1988.

....from French to English, and vice versa. The test collection was also very small by current standards. No system was ever implemented, so it is unclear how such a system would perform in practice. Landauer and Littman [9] proposed a method for cross lingual retrieval. Latent Semantic Indexing (LSI) [6] was used to create a multidimensional indexing space for a small parallel corpus of English documents and their French translations. Their method has been successful at retrieving a query s translation. However, no reports of effectiveness on the traditional retrieval task have been reported. In ....

G.W. Furnas, S. Deerwester, S.T. Dumais, T.K. Landauer anmd R.A. Harshman, L.A. Streeter, and K.E. Lochbaum. Information retrieval using a singular value decomposition model of latent semantic structure. In Proceedings of the 11th International Conference on Research and Development in Information Retrieval, pages 465--480, 1988.

....The singular value decomposition (SVD) cf. 17] of the term by document matrix is commonly used to analyze the structure in word usage across documents. Retrieval can be performed using the k largest singular values and corresponding singular vectors, where k min(m; n) Performance data [9,10,16] indicates that singular vectors are in fact more robust indicators of meaning than individual terms. A number of software tools have been developed to perform operations such as parsing document texts, creating a term by document matrix, computing the truncated SVD of this matrix, creating the ....

G. W. Furnas, S. Deerwester, S. T. Dumais, T. K. Landauer, R. A. Harshman, L. A. Streeter, and K. E. Lochbaum. Information retrieval using a singular value decomposition model of latent semantic structure. In Proceedings of SIGIR, pages 465--480, 1988.

....These studies were promising, however the test collection was very small by current standards and it is unrealistic to manually index larger databases. Landauer and Littman (Landauer Littman 1990) have also proposed a method for cross language retrieval. Latent Semantic Indexing (LSI) (Furnas et al. 1988) was used to create a multidimensional indexing space for a parallel corpus of English documents and their French translations. Their method has been successful at the task of retrieving a query s translation, in response to that query. However the collection used was small, containing 2482 ....

Furnas, G.; Deerwester, S.; Dumais, S.; anmd R.A. Harshman, T. L.; Streeter, L.; and Lochbaum, K. 1988. Information retrieval using a singular value decomposition model of latent semantic structure. In Proceedings of the 11th International Conference on Research and Development in Information Retrieval, 465--480.

....or computed results for other retrieval techniques, notably the standard keyword vector method in SMART [25] For several information science test collections, the average precision using LSI ranged from comparable to 30 better than that obtained using standard keyword vector methods. See [5, 13, 7] for details of these evaluations. The LSI method performs best relative to standard vector methods when the queries and relevant documents do not share many words, and at high levels of recall. Term Weighting One of the common and usually effective methods for improving retrieval performance in ....

....theorem, Cayley and quadratic, although none are synonyms) Matching People Instead of Documents In a couple of applications, LSI has been used to return the best matching people instead of documents. In these applications, people were represented by articles they had written. In one application [13], known as the Bellcore Advisor, a system was developed to find local experts relevant to users queries. A query was matched to the nearest documents and project descriptions and the authors organization was returned as the most relevant internal group. In another application [10] LSI was used ....

G. W. FURNAS, S. DEERWESTER, S. T. DUMAIS, T. K. LANDAUER, R. A. HARSHMAN, L. A. STREETER, AND K. E. LOCHBAUM, Information retrieval using a singular value decomposition model of latent semantic structure, in Proceedings of SIGIR, 1988, pp. 465--480. 35

....It does not distinguish between strongly and weakly related A B pairs, it counts each A as related to only one B, it ignores relations among the A words, etc. With a deeper statistical analysis we can do much better. The technique we actually used was an extension of Latent Semantic Indexing [1, 3, 2]. In this method, a powerful mathematical computation is used to analyze and represent all the linear dependencies between word occurrences in paragraphs (or other text segments) For the two language case, this means that it tries to find the best way to use all the A words in a paragraph to ....

G. W. Furnas, S. Deerwester, S. T. Dumais, T. K. Landauer, R. A. Harshman, L. A. Streeter, and K. E. Lochbaum. Information retrieval using a Singular Value Decomposition model of latent semantic structure. In Proceedings of the 11th ACM International Conference on Research and Development in Information Retrieval, 1988.

No context found.

Furnas, G. Deerwester, S. Dumais. S. et al. (1988): Information retrieval using a singular value decomposition model of latent semantic structure.In Proc. ACM SIGIR Conf., pages 465-480.

No context found.

G. Furnas, S. Deerwester, S. Dumais, T. Landauer, R. Harshman, L. Streeter and K. Lochbaum, "Information retrieval using a singular value decomposition model of latent semantic structure," in The 11th International Conference on Research and Development in Information Retrieval, Grenoble, France: ACM Press, 1988, pp. 465--480.

No context found.

G.W. Furnas, S. Deerwester, S.T. Dumais, T.K. Landauer, R.A. Harshman, L.A. Streeter, and K.E. Lochbaum. Information retrieval using a singular value decomposition model of latent semantic structure. In The 11th International Conference on Research and Development in Information Retrieval, pages 465--480, Grenoble, France, 1988. ACM Press.

No context found.

G. W. Furmas, S. Deerwester, S. T. Dumais, T. K. Landauer, R. A. Harshman, L. A. Streeter and K. E. Lochbaum, "Information retrieval using a singular value decomposition model of latent semantic structure," Proc. of the 11th ACM SIGIR conf., pp. 465-480, 1998.

No context found.

G. W. Furnas, S. Deerwester, S. T. Dumais, T. K. Landauer, R. A. Harshman, L. A. Streeter, and K. E. Lochbaum. Information retrieval using a singular value decomposition model of latent semantic structure. In Proceedings of the Eleventh International Conference on Research & Development in Information Retrieval, pages 465 -- 480, 1988.

No context found.

G. W. Furmas, S. Deerwester, S. T. Dumais, T. K. Landauer, R. A. Harshman, L. A. Streeter and K. E. Lochbaum, "Information retrieval using a singular value decomposition model of latent semantic structure," Proc. of the 11th ACM SIGIR conf., pp. 465-480, 1998.

No context found.

G.W. Furnas, S. Deerwester, S.T. Dumais, T.K. Landauer, R.A. Harshman, L.A. Streeter, and K.E. Lochbaum. Information retrieval using a singular value decomposition model of latent semantic structure. In Proceedings of the 11th Conference on Research and Development in IR, pages 465--480. ACM/SIGIR, June 1989.

No context found.

G. Furnas, S. Deerwester, S. Dumais, T. Landauer, R. Harshman, L. Streeter and K. Lochbaum. Information Retrieval Using a Singular Value Decomposition Model of Latent Semantic Structure. ACM SIGIR Conference, 1988.

No context found.

George W. Furnas, Scott Deerwester, Susan T. Dumais, Thomas K. Landauer, Richard A. Harshman, Lynn A. Streeter, and Laren E. Lochbaum. Information retrieval using a singular value decomposition model of latent semantic structure. In SIGIR '88, Grenoble, France, 1988.

No context found.

George Furnas, Scott Deerwester, Susan Dumais, Thomas Landauer, Richard Harshman, Lynn Streeter, and Karen Lochbaum. Information retrieval using a singular value decomposition model of latent semantic structure. In Proceedings of ACM SIGIR International Conference on Research and Development in Information Retrieval, pages 465--480, 1988.

No context found.

G.W. Furnas, S. Deerwester, S.T. Dumais, T.K. Landauer anmd R.A. Harshman, L.A. Streeter, and K.E. Lochbaum. Information retrieval using a singular value decomposition model of latent semantic structure. In Proceedings of the 11th International Conference on Research and Development in Information Retrieval, pages 465--480, 1988.

First 50 documents

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