Parameter estimation for text analysis

By Gregor Heinrich. 2009

851 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/f22d042312f5f38eddaca08d49ef805c0d8f1cdc

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

A dirichlet multinomial mixture model-based approach for short text clustering (2014, unknown): “With similar techniques of [9],”
4-dimensional local spatio-temporal features for human activity recognition (2011, methodology): “Gibbs sampling is a Markov chain Monte Carlo (MCMC) method, which often yields a relatively efficient algorithm for approximate estimation and inference in high-dimensional models such as LDA [16].”
A Brief Survey of Text Mining: Classification, Clustering and Extraction Techniques (2017, background): “For a theoretical overview on Gibbs sampling see [23, 64].”
On-line LDA: Adaptive Topic Models for Mining Text Streams with Applications to Topic Detection and Tracking (2008, background): “Perplexity is a canonical measure of goodness that is used in language modeling to measure the likelihood of a held-out test data to be generated from the underlying (learned) distributions of the model [8].”
Latent Dirichlet Allocation (2009, result): “We can also directly compare the soft clustering result with the priori categorization([4]).”
News Verification by Exploiting Conflicting Social Viewpoints in Microblogs (2016, methodology): “The distance between two topic-viewpoints is computed as the Jensen-Shannon Distance ( D JS ) (Heinrich 2005) of their probability distributions.”
Advances in Variational Inference (2017, unknown): “approaches rely on sampling [22], [61], [151].”
Dissecting Climate Risks: Are they Reflected in Stock Prices? (2021, methodology): “We summarize the main idea behind this method by following the approach in Heinrich (2009) and Thorsrud (2016).”
BTM: Topic Modeling over Short Texts (2014, background): “Meanwhile, by breaking each document into biterms, and assigning a topic for every biterm, BTM allows a document (with multiple biterms) be able to exhibit multiple topics, which surmounts the defect of mixture of unigrams.”
Scaling Politically Meaningful Dimensions Using Texts and Votes (2014, methodology): “The LDA portion of the model is identical in specification and implementation to previous MCMC implementations (Griffiths and Steyvers 2004; Heinrich 2009); however we change some notation for compatibility with the notation of the voting model.”
Topic Modeling Using Latent Dirichlet allocation (2021, background): “They are also known as admixture because its segments are itself mixture of other segments [46].”
Automatic Keyphrase Extraction via Topic Decomposition (2010, methodology): “Given the topics of the document d and a word w , We have used various methods to compute similarity including cosine similarity, predictive likelihood and KL-divergence (Heinrich, 2005), among which cosine similarity performs the best on both datasets.”
Learning cross-modality similarity for multinomial data (2011, methodology): “For an excellent discussion about Gibbs sampling for LDA-like probabilistic models, we refer the reader to [8].”
A biterm topic model for short texts (2013, background): “For memory cost, LDA has to maintain the counters nz|b, nw|z, and the topic assignment z for each word occurrences[15], in total of (|D|K +MK + |D|l) variables.”
Learning to classify short and sparse text & web with hidden topics from large-scale data collections (2008, methodology): “However, it has been pointed out that LDA is more complete than pLSA in such a way that it follows a full generation process for document collection [8, 19, 21].”
Integrated visual vocabulary in latent Dirichlet allocation–based scene classification for IKONOS image (2014, background): “s 1⁄4 ffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffi 1 N XN ði;jÞ1⁄41 ðpij − μÞ3 3 uut : (14) Kusumaningrum et al.”