Block-LDA: Jointly Modeling Entity-Annotated Text and Entity-Entity Links

By Ramnath Balasubramanyan, William W. Cohen. 2014

148 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Molecular Biology

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 Molecular Biology

Citations in the corpus

Debiasing Community Detection: The Importance of Lowly Connected Nodes (2019, methodology): “In addition to CESNA, other methods have been proposed, such as Block-LDA [9], PAICAN [10], shared latent space models such as CLSM [7], and embedding-based approaches like LANE [11], which utilize node attributes in order to detect communities, or ELAINE [12], which utilizes”
Natural Language Models for Predicting Programming Comments (2013, methodology): “The LDA and link-LDA models use Gibbs sampling (Griffiths and Steyvers, 2004) for topic inference, based on the implementation of Balasubramanyan and Cohen (2011) with single or multiple entities per document, respectively.”
Discovering social circles in ego networks (2012, methodology): “Block-LDA [Balasubramanyan and Cohen 2011].”
Clustering attributed graphs: Models, measures and methods (2015, methodology): “Balasubramanyan & Cohen (2011) also address the problem of link modeling and combine two popular methods: block modeling and LDA.”
Detecting cohesive and 2-mode communities indirected and undirected networks (2014, unknown): “aselines represent the current stateof-the-art in community detection. However, we also considered other baselines, including those that make use of node features [20], network topology [39], or both [5, 31]; however experiments demonstrate that none of these alternatives outperforms CoDA. Evaluatio”
Learning to Discover Social Circles in Ego Networks (2012, methodology): “Of the eight baselines highlighted above we report the three whose overall performance was the best, namely Block-LDA [5] (which slightly outperformed mixed membership stochastic block models [2]), Low-Rank Embedding [20], and Multi-Assignment Clustering [16].”
Community Detection in Networks with Node Attributes (2013, methodology): “Based on Table I we select one algorithm from each model type: Block-LDA [4] represents soft-membership approaches, while the CODICIL [35] represents heuristics for non-overlapping communities, and the EDCAR [18] represents heuristics for ﬁnding dense subgraphs.”
Inferring Networks of Substitutable and Complementary Products (2015, methodology): “More specifically, our work builds on topic models for networks: Block-LDA [1], topic-link LDA [18], and relational topic models [7] all attempt to identify topics that explain the links in document networks.”
KB-LDA: Jointly Learning a Knowledge Base of Hierarchy, Relations, and Facts (2015, unknown): “It is a generalization of Block-LDA (Balasubramanyan and Cohen, 2011), however, KBLDA models two link components, and the input links have a meaningful semantic correspondence to a KB structure (hierarchical and relational).”