Indexing by Latent Semantic Analysis

By T. Landauer, S. Deerwester, Susan T. Dumais, G. Furnas, Richard A. Harshman. 1990

Subfields: 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 Natural Language Processing

In Representation & Self-Supervised Learning

Citations in the corpus

GloVe: Global Vectors for Word Representation (2014, methodology): “While methods like LSA ef-ﬁciently leverage statistical information, they do relatively poorly on the word analogy task, indicating a sub-optimal vector space structure.”
Experience Grounds Language (2020, background): “However, the most successful vector representations came from Latent Semantic Indexing/Analysis (Deerwester et al., 1988, 1990; Du-mais, 2004), which represents words by their co-occurrence with other words.”
Representation Learning Using Multi-Task Deep Neural Networks for Semantic Classification and Information Retrieval (2015, methodology): “Traditional techniques include LSA (Deerwester et al., 1990), ESA (Gabrilovich and Markovitch, 2007), PCA (Karhunen, 1998), and non-linear kernel variants (Schölkopf et al.”
Transfer Learning in Natural Language Processing (2019, methodology): “In particular, we will review unsupervised approaches which aim to model the dataset itself, briefly presenting non-neural approaches (Deerwester et al., 1990; Brown et al., 1993; Blei et al., 2003) before detailing deep neural network approaches like auto-encoding/skip-thoughts models (Dai and Le, ”
Revisiting LSTM Networks for Semi-Supervised Text Classification via Mixed Objective Function (2019, background): “Later, better word representations were introduced, such as latent semantic analysis (Deerwester et al. 1990), skipgram (Mikolov et al.”
Enriching Word Vectors with Subword Information (2016, methodology): “These representations are typically derived from large unlabeled corpora using co-occurrence statistics (Deerwester et al., 1990; Schütze, 1992; Lund and Burgess, 1996).”
Efficient and Robust Approximate Nearest Neighbor Search Using Hierarchical Navigable Small World Graphs (2016, background): “parametric machine learning algorithms, image features matching in large-scale databases [1] and semantic document retrieval [2].”
Poly-encoders: Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring (2019, methodology): “, 1975), LSI (Deerwester et al., 1990), supervised embeddings (Bai et al.”
Maximum inner-product search using cone trees (2012, background): “However, in certain setting [11], the documents are represented as (not necessarily normalized) vectors and the inner-product between these vectors represent the similarity between the documents.”
The Web Is Your Oyster - Knowledge-Intensive NLP against a Very Large Web Corpus (2021, background): “DPR (Karpukhin et al., 2020) is a dense model which embeds queries and documents into a latent, real-valued vector space of a much lower dimensionality—an idea originating from the Latent Semantic Analysis (Deerwester et al., 1990).”
Unsupervised Dense Information Retrieval with Contrastive Learning (2021, background): “This led to the introduction of latent semantic analysis (Deerwester et al., 1990), in which documents are represented as low dimensional dense vectors.”
Pretrained Transformers for Text Ranking: BERT and Beyond (2020, background): “r search, directly incorporating dense vector representations. In fact, attempts to do away with retrieval based on sparse vector representations date back to latent semantic analysis from the 1990s [Deerwester et al., 1990]. A more recent example is the work of Nakamura et al. [2019]: in a standard”
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).”
FastText.zip: Compressing text classification models (2016, background): “Text classiﬁcation is a problem that has its roots in many applications such as web search, information retrieval and document classiﬁcation (Deerwester et al., 1990; Pang & Lee, 2008).”
Bag of Tricks for Efficient Text Classification (2016, background): “Text classiﬁcation is an important task in Natural Language Processing with many applications, such as web search, information retrieval, ranking and document classiﬁcation (Deerwester et al., 1990; Pang and Lee, 2008).”
Character-Aware Neural Language Models (2015, methodology): “Word embeddings obtained through NLMs exhibit the property whereby semantically close words are likewise close in the induced vector space (as is the case with non-neural techniques such as Latent Semantic Analysis (Deerwester et al. 1990)).”
Fusion of Detected Objects in Text for Visual Question Answering (2019, background): “It has long been understood that the meaning of a word is systematically and predictably linked to the context in which it occurs (e.g., Firth 1957; Harris 1954; Deerwester et al. 1990; Mikolov et al. 2013).”
From Frequency to Meaning: Vector Space Models of Semantics (2010, methodology): “Deerwester et al. (1990) observed that we can shift the focus to measuring word similarity, instead of document similarity, by looking at row vectors in the term–document matrix, instead of column vectors. Deerwester et al. (1990) were inspired by the term–document matrix of Salton et al. (1975), bu”