Latent semantic analysis

By Susan T. Dumais. 2004

1,077 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Natural Language Processing, Representation & Self-Supervised Learning

How researchers see this paper

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

In Artificial Intelligence

In Natural Language Processing

In Representation & Self-Supervised Learning

Citations in the corpus

Experience Grounds Language (2020, background): “tent Semantic Indexing/Analysis (Deerwester et al., 1988, 1990; Dumais, 2004) and later in the generative framework of Latent Dirichlet Allocation (Blei et al.”
Pre-Trained Language Models for Interactive Decision-Making (2022, background): “From nearly the earliest days of the field, natural language processing researchers observed that representations of words derived from distributional statistics in large text corpora serve as useful features for downstream tasks (Deerwester et al., 1990; Dumais, 2004).”
Recent Trends in Deep Learning Based Natural Language Processing (2017, background): “A more detailed summary of these early trends is provided in [16, 17].”
Larger-Context Language Modelling with Recurrent Neural Network (2015, background): “, 2003) or latent semantics analysis (Dumais, 2004) to extract a feature vector, whereas we learn the whole model, including the context vector extraction, end-to-end.”
Text feature extraction based on deep learning: a review (2017, methodology): “It is defined as the amount of information that a certain feature item is able to provide for the whole classification, taking no account of the entropy of any features but the difference value of entropy of the feature [17].”
An Overview of Low-Rank Matrix Recovery From Incomplete Observations (2016, methodology): “cal techniques such as principal component analysis [15], [16] as well as modern approaches to multi-task learning [17], [18] and natural language processing [19], [20]; • quantum state tomography: a pure quantum state of N ions can be described by a 2 × 2 matrix with rank one [21].”
Lift: Multi-Label Learning with Label-Specific Features (2011, methodology): “Note that better choice other than k-means can be adopted by taking into account peculiarities of the data set, e.g. clustering algorithm based on LSA or PLSA [11] is a popular choice for text data sets with sparse feature representation. let r j i denote the rank of the j-th algorithm on the i-th d”
Extracting semantic representations from word co-occurrence statistics: stop-lists, stemming, and SVD (2012, methodology): “Moreover, raw vectors of the type used in the present study have previously been shown to perform much better for our purposes than the LSA vectors after SVD-based dimensional reduction (Bullinaria & Levy, 2007), so it is not obvious whether SVD will be able to provide any further improvements in th”
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].”
Recent Trends in Deep Learning Based Natural Language Processing [Review Article] (2018, neutral): “early trends is provided in [16], [17].”
A Neural Architecture Mimicking Humans End-to-End for Natural Language Inference (2016, background): “Many vector representations for words have been proposed, including the well known latent semantic indexing [Dumais, 2004].”
A comprehensive review and comparison of different computational methods for protein remote homology detection (2018, methodology): “Based on these similarities, some techniques from NLP are applied to protein remote homology detection, such as latent semantic analysis [91, 92] and word correlation matrices [93].”
Overview and comparative study of dimensionality reduction techniques for high dimensional data (2020, neutral): “LSA can also be applied for text [77] , images and videos [1] and to identify medical records [86] .”