Probabilistic Latent Semantic Analysis
arXiv:1301.6705
Abstract
Probabilistic Latent Semantic Analysis is a novel statistical technique for the analysis of two-mode and co-occurrence data, which has applications in information retrieval and filtering, natural language processing, machine learning from text, and in related areas. Compared to standard Latent Semantic Analysis which stems from linear algebra and performs a Singular Value Decomposition of co-occurrence tables, the proposed method is based on a mixture decomposition derived from a latent class model. This results in a more principled approach which has a solid foundation in statistics. In order to avoid overfitting, we propose a widely applicable generalization of maximum likelihood model fitting by tempered EM. Our approach yields substantial and consistent improvements over Latent Semantic Analysis in a number of experiments.
Appears in Proceedings of the Fifteenth Conference on Uncertainty in Artificial Intelligence (UAI1999)
References in corpus (1)
Cited by in corpus (128)
- A Survey on Distributed Machine Learning
- Probabilistic Models for Unified Collaborative and Content-Based Recommendation in Sparse-Data Environments
- Continuous Time Dynamic Topic Models
- A Comprehensive Survey on Transfer Learning
- Quantum Aspects of Semantic Analysis and Symbolic Artificial Intelligence
- Selective Exposure shapes the Facebook News Diet
- Uncovering latent jet substructure
- Visualizing Topics with Multi-Word Expressions
- Image as Data: Automated Visual Content Analysis for Political Science
- Nonparametric Divergence Estimation with Applications to Machine Learning on Distributions
- Learning Topic Models - Going beyond SVD
- Incorporating Side Information in Probabilistic Matrix Factorization with Gaussian Processes
- Expectation-Propogation for the Generative Aspect Model
- Discovering Attribute Shades of Meaning with the Crowd
- Incorporating Side Information in Probabilistic Matrix Factorization with Gaussian Processes
- Exploiting Social Annotation for Automatic Resource Discovery
- Topic2Vec: Learning Distributed Representations of Topics
- Spectral Learning on Matrices and Tensors
- Confusion2Vec: Towards Enriching Vector Space Word Representations with Representational Ambiguities
- Machine Learning Markets
- Quantum Theory and Conceptuality: Matter, Stories, Semantics and Space-Time
- On the Generalization Error Bounds of Neural Networks under Diversity-Inducing Mutual Angular Regularization
- How Many Topics? Stability Analysis for Topic Models
- Rank-frequency relation for Chinese characters
- KATE: K-Competitive Autoencoder for Text
- Explaining Zipf's Law via Mental Lexicon
- JNET: Learning User Representations via Joint Network Embedding and Topic Embedding
- Word embeddings for topic modeling: an application to the estimation of the economic policy uncertainty index
- Kernels on Sample Sets via Nonparametric Divergence Estimates
- Recommender systems in industrial contexts
- vGraph: A Generative Model for Joint Community Detection and Node Representation Learning
- Tensorial Mixture Models
- Conditional Density Estimation by Penalized Likelihood Model Selection and Applications
- Sampling-Decomposable Generative Adversarial Recommender
- Learning Nonlinear Mixtures: Identifiability and Algorithm
- Author Name Disambiguation in Bibliographic Databases: A Survey
- Mixed membership analysis of high-throughput interaction studies: Relational data
- Coherent structure identification in turbulent channel flow using Latent Dirichlet Allocation
- A Tutorial on Probabilistic Latent Semantic Analysis
- GENO -- GENeric Optimization for Classical Machine Learning
- Machine Learning with World Knowledge: The Position and Survey
- KNET: A General Framework for Learning Word Embedding using Morphological Knowledge
- Matching Algorithms: Fundamentals, Applications and Challenges
- TraLFM: Latent Factor Modeling of Traffic Trajectory Data
- Two-Level Transformer and Auxiliary Coherence Modeling for Improved Text Segmentation
- Robust Spectral Inference for Joint Stochastic Matrix Factorization
- Deep Functional Dictionaries: Learning Consistent Semantic Structures on 3D Models from Functions
- Latent Variable Modeling with Diversity-Inducing Mutual Angular Regularization
- Relation Strength-Aware Clustering of Heterogeneous Information Networks with Incomplete Attributes
- An Analysis of Lemmatization on Topic Models of Morphologically Rich Language
- Nonparametric Bayesian Negative Binomial Factor Analysis
- Using Access Data for Paper Recommendations on ArXiv.org
- Caching Policy for Cache-enabled D2D Communications by Learning User Preference
- Ordering-sensitive and Semantic-aware Topic Modeling
- Recommender systems inspired by the structure of quantum theory
- Neural Topic Model via Optimal Transport
- Bayesian Transfer Learning: An Overview of Probabilistic Graphical Models for Transfer Learning
- Learning the Experts for Online Sequence Prediction
- Local Music Event Recommendation with Long Tail Artists
- Factorized Topic Models
- Inferring Discussion Topics about Exploitation of Vulnerabilities from Underground Hacking Forums
- A New Geometric Approach to Latent Topic Modeling and Discovery
- Feature extraction using Latent Dirichlet Allocation and Neural Networks: A case study on movie synopses
- Familia: An Open-Source Toolkit for Industrial Topic Modeling
- Sparse Lifting of Dense Vectors: Unifying Word and Sentence Representations
- Auto-Encoding Variational Bayes for Inferring Topics and Visualization
- Generalized Topic Modeling
- Learning Arbitrary Statistical Mixtures of Discrete Distributions
- Conversational Structure Aware and Context Sensitive Topic Model for Online Discussions
- AI supported Topic Modeling using KNIME-Workflows
- Mixed Membership Word Embeddings for Computational Social Science
- Caching Policy Optimization for D2D Communications by Learning User Preference
- Probabilistic Latent Semantic Analysis (PLSA) untuk Klasifikasi Dokumen Teks Berbahasa Indonesia
- Learning Mixtures of Arbitrary Distributions over Large Discrete Domains
- A Thermodynamical Approach for Probability Estimation
- Modeling Social Annotation: a Bayesian Approach
- Kullback-Leibler Principal Component for Tensors is not NP-hard
- A Latent Variable Model Approach to PMI-based Word Embeddings
- Discriminative Relational Topic Models
- Latent Regression Bayesian Network for Data Representation
- Noise Benefits in Expectation-Maximization Algorithms
- VSEC-LDA: Boosting Topic Modeling with Embedded Vocabulary Selection
- Comparison Latent Semantic and WordNet Approach for Semantic Similarity Calculation
- Topic Modeling for Classification of Clinical Reports
- Transforming Graph Representations for Statistical Relational Learning
- Construction of Community Web Directories based on Web usage Data
- Approximate Maximum A Posteriori Inference with Entropic Priors
- Automatic Text Summarization Approaches to Speed up Topic Model Learning Process
- Message-Passing Inference on a Factor Graph for Collaborative Filtering
- Top-N recommendations from expressive recommender systems
- Teaching a Massive Open Online Course on Natural Language Processing
- Estimating the Effective Topics of Articles and journals Abstract Using LDA And K-Means Clustering Algorithm
- ZenLDA: An Efficient and Scalable Topic Model Training System on Distributed Data-Parallel Platform
- Mixing syntagmatic and paradigmatic information for concept detection
- Effective FAQ Retrieval and Question Matching With Unsupervised Knowledge Injection
- Nonnegative Restricted Boltzmann Machines for Parts-based Representations Discovery and Predictive Model Stabilization
- Engineering Deep Representations for Modeling Aesthetic Perception
- Statistical Latent Space Approach for Mixed Data Modelling and Applications
- Prior-aware Dual Decomposition: Document-specific Topic Inference for Spectral Topic Models
- Less is More: Learning Prominent and Diverse Topics for Data Summarization
- The Universal Recommender
- Exact marginal inference in Latent Dirichlet Allocation
- On collapsed representation of hierarchical Completely Random Measures
- Hierarchical Bayesian Models with Factorization for Content-Based Recommendation
- Interpretable Low-Rank Document Representations with Label-Dependent Sparsity Patterns
- Factored Latent Analysis for far-field tracking data
- The Deep Latent Position Topic Model for Clustering and Representation of Networks with Textual Edges
- Topic Diffusion Discovery Based on Deep Non-negative Autoencoder
- Topic Model Robustness to Automatic Speech Recognition Errors in Podcast Transcripts
- Multi-GPU Distributed Parallel Bayesian Differential Topic Modelling
- A Concern Analysis of FOMC Statements Comparing The Great Recession and The COVID-19 Pandemic
- Streaming Social Event Detection and Evolution Discovery in Heterogeneous Information Networks
- Few-shot Learning for Topic Modeling
- The Sparse Hausdorff Moment Problem, with Application to Topic Models
- Context-theoretic Semantics for Natural Language: an Algebraic Framework
- Linear-Sample Learning of Low-Rank Distributions
- Lifelong Neural Topic Learning in Contextualized Autoregressive Topic Models of Language via Informative Transfers
- Naive Dictionary On Musical Corpora: From Knowledge Representation To Pattern Recognition
- Learning Fast Matching Models from Weak Annotations
- Comparative Analysis of Content-based Personalized Microblog Recommendations [Experiments and Analysis]
- Relating Zipf's law to textual information
- Un duel probabiliste pour départager deux présidents (LIA @ DEFT'2005)
- Centroid estimation based on symmetric KL divergence for Multinomial text classification problem
- A cost-reducing partial labeling estimator in text classification problem
- The Latent Bernoulli-Gauss Model for Data Analysis
- Making Sense of Unstructured Text Data
- A Context-theoretic Framework for Compositionality in Distributional Semantics
- Conceptualization Topic Modeling