Using latent semantic analysis to improve access to textual information

By Susan T. Dumais, G. Furnas, T. Landauer, S. Deerwester, Richard A. Harshman. 1988

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Is the Sample Good Enough? Comparing Data from Twitter's Streaming API with Twitter's Firehose (2013, methodology): “We set K = 100 as suggested by (Dumais et al. 1988) and use priors of α = 50/K, and η = 0.”
Multilingual Models for Compositional Distributed Semantics (2014, methodology): “This is related to topic-modelling techniques such as LSA (Dumais et al., 1988), LSI, and LDA (Blei et al.”
Searching the Web (2001, background): “Another important research direction is to study more sophisticated text analysis techniques (such as Latent Semantic Indexing [25]) and explore enhancements for these in a hyperlinked setting.”
On internal language representations in deep learning: an analysis of machine translation and speech recognition (2018, unknown): “For example, using singular value decomposition (SVD) leads to latent semantic analysis (LSA) [96].”
Portuguese Word Embeddings: Evaluating on Word Analogies and Natural Language Tasks (2017, methodology): “They can be roughly divided into two families of methods [Baroni et al. 2014]: the ﬁrst is composed of methods that work with a co-occurrence word matrix, such as Latent Semantic Analysis (LSA) [Dumais et al. 1988], Hyperspace Analogue to Language (HAL) [Lund and Burgess 1996] and Global Vectors (Gl”
Using Mechanical Turk to Create a Corpus of Arabic Summaries (2010, methodology): “: similar to Gen-Summ, but where the vector space is tranformed and reduced by applying Latent Semantic Analysis (LSA) to both document and query (Dumais et al., 1988).”
Temporal Link Prediction Using Matrix and Tensor Factorizations (2010, methodology): “Low-rank approximations based on the matrix SVD have proven to be an effective technique in many data applications; latent semantic indexing [Dumais et al. 1988] is one such example.”
The Texture Lexicon: Understanding the Categorization of Visual Texture Terms and Their Relationship to Texture Images (1997, background): “(Techniques such as latent semantic indexing [Dumais et al., 19881 can be used to circumvent some of the problems in performing database searches; for example, the use of synonymous words should lead to the same result.”
Learning Sentiment Lexicons in Spanish (2012, methodology): “Instead, we opt to implement semantic expansion using Latent Semantic Analysis (LSA) (Dumais et al., 1988) to generate concept vectors for each of the lexicon entries.”
Word Representations: A Simple and General Method for Semi-Supervised Learning (2010, background): “ˇReh˚uˇrek and Sojka (2010) describe an incremental approach to inducing LSA and LDA topic models over 270 millions word tokens with a vocabulary of 315K word types.”
Higher-order Web link analysis using multilinear algebra (2005, methodology): “For example, SALSA is a variant on HITS that uses a stochastic iteration matrix [26].”
An Introduction to Random Indexing (2005, background): “…available, and there are numerous publications that report exceptional results in many different applications, including information retrieval (Dumais et al., 1988), word sense disambiguation (Schütze, 1993), various semantic knowledge tests (Lund et al., 1995, Karlgren & Sahlgren, 2001), and…”
Tensor Decompositions and Applications (2009, background): “The idea is to extend the concept of latent semantic indexing [75, 72, 21] in a cross-language context by using multiple translations of the same collection of documents, i.”
Bilingual Word Representations with Monolingual Quality in Mind (2015, methodology): “Current work in dimensionality reduction of word representations can be broadly grouped into three categories (Turian et al., 2010): (a) distributional representations learned from a co-occurrence matrix of words and contexts (documents, neighbor words, etc.) using techniques such as LSA (Dumais et ”