(Enter summary)
Abstract: The representation of documents and queries as vectors in a high-dimensional space is well-established in information retrieval [1]. This paper proposes to represent the semantics of words and contexts in a text as vectors. The dimensions of the space are words and the initial vectors are determined by the words occurring close to the entity to be represented which implies that the space has several thousand dimensions (words). This makes the vector representations (which are dense) too... (Update)
Cited by: More
Assessing the Impact of Sparsification on LSI Performance - Kontostathis, Pottenger.. (2004)
(Correct)
Identification of Critical Values in Latent Semantic.. - Kontostathis, Pottenger, ..
(Correct)
A (Acronyms) - Zahariev (2004)
(Correct)
Active bibliography (related documents): More All
0.0: An Overview of Corpus-Based Statistics-Oriented (CBSO).. - Su, Chiang, Chang (1996)
(Correct)
0.0: Computational Tools and Resources for Linguistic Studies - Hsu, Chang, Su
(Correct)
0.0: Statistical Models for Deep-structure Disambiguation - Chiang, Su (1996)
(Correct)
Similar documents based on text: More All
0.4: Table Of - Ab Le Of
(Correct)
0.2: Distributional Part-of-Speech Tagging - Schütze (1995)
(Correct)
0.2: Customizing a Lexicon to Better Suit a Computational Task - Hearst, Schütze (1996)
(Correct)
Related documents from co-citation: More All
6: LSI Meets TREC: A Status Report
- Dumais - 1993
5: Indexing by Latent Semantic Analysis (context) - Deerweester, Dumais et al. - 1990
4: Computer Methods for Mathematical Computations (context) - Forsythe, Malcolm et al. - 1977
BibTeX entry: (Update)
Hinrich Schutze. 1992. Dimensions of meaning. In Proceedings of Supercomputing, pages 787--796, Minneapolis. http://citeseer.ist.psu.edu/23424.html More
@inproceedings{ schutze92dimensions,
author = "Hinrich Schutze",
title = "Dimensions of meaning",
booktitle = "Proceedings of Supercomputing '92, Minneapolis.",
pages = "787--796",
year = "1992",
url = "citeseer.ist.psu.edu/23424.html" }
Citations (may not include all citations):
1256
Introduction to modern information retrieval (context) - Salton, McGill - 1983 ACM
568
Indexing by latent semantic analysis
- Deerwester, Dumais et al. - 1990 DBLP
550
Parallel Distributed Processing (context) - Rumelhart, McClelland et al. - 1986 ACM
329
Principal Component Analysis (context) - Jolliffe - 1986 ACM
153
AutoClass: A Bayesian classification system (context) - Cheeseman, Kelly et al. - 1988 DBLP
148
Word-sense disambiguation using statistical models of Roget'..
- Yarowsky - 1992 ACM
146
Building Large Knowledge-Based Systems (context) - Lenat, Guha - 1989
103
Scatter-gather: A cluster-based approach to browsing large d..
- Cutting, Karger et al. - 1992
65
Word-sense disambiguation using statistical methods
- Brown, Pietra et al. - 1991
43
Word association norms, mutual information and lexicography
- Church, Hanks - 1989 DBLP
39
Methods for Statistical Data Analysis of Multivariate Observ.. (context) - Gnanadesikan - 1977
20
Using bilingual materials to develop word sense disambiguati.. (context) - Gale, Church et al. - 1992
The graph only includes citing articles where the year of publication is known.
Documents on the same site (http://www.cs.duke.edu/~mlittman/courses/cps370-97/): More
Stochastic Attribute-Value Grammars - Abney (1997)
(Correct)
Text Segmentation Using Exponential Models - Beeferman, Berger, Lafferty (1997)
(Correct)
Grammatical Trigrams: A Probabilistic Model of Link Grammar - Lafferty, Sleator, Temperley (1992)
(Correct)
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