Probabilistic topic models

By David M. Blei. 2012

6,644 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Systems, Natural Language Processing, Probabilistic & Bayesian Methods

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 Information Systems

In Natural Language Processing

In Probabilistic & Bayesian Methods

Citations in the corpus

Stochastic variational inference (2012, methodology): “The main idea in a topic model is that there are a set of topics that describe the collection and each document exhibits those topics with different degrees.”
Variational Inference: A Review for Statisticians (2016, methodology): “Topic models have become a popular technique for exploratory data analysis of large collections (Blei 2012).”
Uncovering and Mitigating Algorithmic Bias through Learned Latent Structure (2019, background): “Learning the latent structure of data has a long standing history in machine learning, including ExpectationMaximization [5], topic modelling [7], latent-SVM [14], and more recently, variational autoencoders (VAE) [19, 29].”
How algorithmic confounding in recommendation systems increases homogeneity and decreases utility (2017, background): “movie genre), or they can be learned independent of time t with, for example, a topic model [6] for text or from the acoustic structure of a song [57] for music; when learned, the attribute tags can be”
Graph-Sparse LDA: A Topic Model with Structured Sparsity (2014, background): “Probabilistic topic models (Blei, Ng, and Jordan 2003; Steyvers and Griffiths 2007) were originally developed to discover latent structure in unorganized text corpora.”
Topic-based Evaluation for Conversational Bots (2018, background): “In the probabilistic topic model, a topic is deﬁned as a distribution over a ﬁxed vocabulary [3].”
Modeling Documents with Deep Boltzmann Machines (2013, background): “Non-parametric extensions of these models have also been quite successful [13, 1, 5].”
Analyst Information Discovery and Interpretation Roles: A Topic Modeling Approach (2018, neutral): “computational linguistic technique to uncover the thematic structure of linguistic data by automatically analyzing the semantic content in large collections of this data (Blei 2012).”
Nonparametric Variational Auto-Encoders for Hierarchical Representation Learning (2017, methodology): “The resulting model unifies the Bayesian nonparametric flexibility with neural inductive biases, by viewing it as a nonparametric topic model [1] on the latent code space, in which raw data examples are first transformed to compact (probabilistic) semantic vectors with deep neural networks (i.”
Autofolding for Source Code Summarization (2014, background): “A topic model [57] is a type of statistical model over documents, that represents each document as a combination of topics, which are groups of words that tend to occur together.”
A Review on Bilevel Optimization: From Classical to Evolutionary Approaches and Applications (2017, methodology): ““Topic models are algorithms for discovering the main themes that pervade a large and otherwise unstructured collection of documents” [26].”
Supervised topic models for clinical interpretability (2016, methodology): “Recently, Chen et al. (2015) developed back-propagation supervised LDA (BP-sLDA), which optimizes Eq.”
A big data exploration of the informational and normative influences on the helpfulness of online restaurant reviews (2021, result): “It would be interesting to compare the results from Leximancer to those, for example, gained with Latent Dirichlet Allocation (LDA), which is the simplest topic model (Blei, 2012), to ascertain whether and how the algorithms these programs use, differ.”