Joint latent topic models for text and citations

By Ramesh Nallapati, Amr Ahmed, Eric P. Xing, William W. Cohen. Knowledge Discovery and Data Mining, 2008

450 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/c53e501fcc1fc2e6adcae1e86287a5a6f9a88346

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

Citations in the corpus

Latent Space Model for Multi-Modal Social Data (2015, methodology): “Pairwise Link-LDA [45] combines LDA [9] and MMSB [3] to describe both the network structure and user-generated content.”
Attributed Social Network Embedding (2017, methodology): “Pairwise Link-LDA [25], [26] combined the Latent Dirichlet Allocation (LDA) and MMSB, but often failed to exploit the synergies between”
Citation recommendation: approaches and datasets (2020, unknown): “0 Michael Farber, Adam Jatowt Table 4 Approaches to global and local citation recommendation (CR). Reference Venue Local CR McNee et al. [110] CSCW’02 Strohman et al. [144] SIGIR’07 Nallapati et al. [119] KDD’08 Tang et al. [151] PAKDD’09 He et al. [72] WWW’10 X Kataria et al. [89] AAAI’10 X Bethard”
Research-paper recommender systems: a literature survey (2015, methodology): “Dataset combinations included CiteSeer and some blogs [100], CiteSeer and Web-kd [65],”
Block-LDA: Jointly Modeling Entity-Annotated Text and Entity-Entity Links (2014, methodology): “For instance, Pairwise-Link-LDA[6] combines MMSB with LDA by modeling documents using LDA and generating links between them using MMSB.”
Effective Community Search for Large Attributed Graphs (2016, methodology): “Non-attributed [22, 11] [26, 5, 4, 15, 18] Attributed [34, 21, 20, 29, 23] ACQ (This paper)”
A Neural Probabilistic Model for Context Based Citation Recommendation (2015, background): “Most citation recommendation models fall into two categories: global recommendation (McNee et al. 2002; Strohman, Croft, and Jensen 2007; Nallapati et al. 2008; Bethard and Jurafsky 2010; Kataria, Mitra, and Bhatia 2010; Kucuktunc et al. 2012; Ren et al. 2014) which recommends a list of references f”
Efficient community detection in large networks using content and links (2012, methodology): “We also find that for probabilistic-model-based methods (PCL-D , L-P-LDA and LDA) as well as K-means, their running time is at least linearin l, the desired number of output clusters, which becomes a critical drawback in face of large-scale workloads.”
A Survey of Topic Modeling in Text Mining (2015, unknown): “This model, such as LDA [10] .”
Content-Based Citation Recommendation (2018, methodology): “Prior algorithms (Huang et al., 2015, 2012; Nallapati et al., 2008; Tanner and Charniak, 2015) learn an explicit representation for each training document separately that isn’t a deterministic function of the doc-ument’s words.”
ClusCite: effective citation recommendation by information network-based clustering (2014, methodology): “Link-PLSA-LDA [18]: Link-PLSA-LDA(6) is a hybrid method that leverages both document text and citation links”
A Survey of Link Prediction in Social Networks (2011, methodology): “Probabilistic relational models [21], graphical models [40], stochastic relational models [6, 61, 20], and different variants of these are the main modeling paradigm used in these works.”
Relational Topic Models for Document Networks (2009, methodology): “For all three corpora, RTMs outperform baseline unigram, LDA, and “Mixed-Membership,” which is the model of Nallapati et al. (2008).”
Multiscale Community Blockmodel for Network Exploration (2011, methodology): “The literature contains many examples of variational approximations being applied to variants of the stochastic blockmodel (Airoldi, Blei, Fienberg and Xing, 2008 ; Xing, Fu and Song, 2010 ; Nallapati, Ahmed, Xing and Cohen, 2008 ).”
KB-LDA: Jointly Learning a Knowledge Base of Hierarchy, Relations, and Facts (2015, methodology): “KB-LDA is an extension to LDA and link-LDA (Blei et al., 2003; Erosheva et al., 2004), modeling documents as a mixed membership over entity types with additional annotated metadata, such as links (Nallapati et al., 2008; Chang and Blei, 2009).”
A survey of community search over big graphs (2019, methodology): “In [135,147], the Link-PLSA-LDA and Topic-Link LDA models jointly model vertices’ content and links based on the LDA model.”