Neural Relational Topic Models for Scientific Article Analysis

Bai, Haoli; Chen, Zhuangbin; Lyu, Michael R.; King, Irwin; Xu, Zenglin

doi:10.1145/3269206.3271696

Cited by 45 publications

(24 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Topic Models. Well-known topic models, e.g., probabilistic latent semantic analysis (pLSA) (Hofmann, 1999) and latent Dirichlet allocation (LDA) (Blei et al, 2003), have shown advantages in capturing effective semantic representations, and proven beneficial to varying downstream applications, such as summarization (Haghighi and Vanderwende, 2009) and recommendation (Zeng et al, 2018;Bai et al, 2018). For short text data, topic model variants have been proposed to reduce the effects of sparsity issues on topic modeling, such as biterm topic model (BTM) (Yan et al, 2013) and LeadLDA (Li et al, 2016b).…”

Section: Related Workmentioning

confidence: 99%

Topic Memory Networks for Short Text Classification

Zeng¹,

Li²,

Yan³

et al. 2018

Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

Self Cite

120

View full text Add to dashboard Cite

Many classification models work poorly on short texts due to data sparsity. To address this issue, we propose topic memory networks for short text classification with a novel topic memory mechanism to encode latent topic representations indicative of class labels. Different from most prior work that focuses on extending features with external knowledge or pre-trained topics, our model jointly explores topic inference and text classification with memory networks in an end-to-end manner. Experimental results on four benchmark datasets show that our model outperforms state-of-the-art models on short text classification, meanwhile generates coherent topics. * This work was mainly conducted when Jichuan Zeng was an intern in Tencent AI Lab. † Jing Li is the corresponding author. Training instances R1: [SuperBowl] I'll do anything to see the Steelers win. R2: [New.Music.Live] Please give wristbands, she have major Bieber Fever. Test instance S: [New.Music.Live] I will do anything for wristbands, gonna tweet till I win.

show abstract

Section: Related Workmentioning

confidence: 99%

Topic Memory Networks for Short Text Classification

Zeng¹,

Li²,

Yan³

et al. 2018

Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

Self Cite

120

View full text Add to dashboard Cite

show abstract

“…Research collaborations in scientific community have been extensively studied to understand team dynamics in social networks [2]. Co-authorship data provide a means to analyse research collaborations.…”

Section: Collaborations In a Co-authorship Networkmentioning

confidence: 99%

NHP: Neural Hypergraph Link Prediction

Yadati

Ray

Nimishakavi

et al. 2020

Proceedings of the 29th ACM International Conference on Information &Amp; Knowledge Management

View full text Add to dashboard Cite

Link prediction in simple graphs is a fundamental problem in which new links between vertices are predicted based on the observed structure of the graph. However, in many real-world applications, there is need to model relationships among vertices which go beyond pairwise associations. For example, in a chemical reaction, relationship among the reactants and products is inherently higherorder. Additionally, there is need to represent the direction from reactants to products. Hypergraphs provide a natural way to represent such complex higher-order relationships. Graph Convolutional Networks (GCN) have recently emerged as a powerful deep learning-based approach for link prediction over simple graphs. However, their suitability for link prediction in hypergraphs is underexplored-we fill this gap in this paper and propose Neural Hyperlink Predictor (NHP). NHP adapts GCNs for link prediction in hypergraphs. We propose two variants of NHP-NHP-U and NHP-D-for link prediction over undirected and directed hypergraphs, respectively. To the best of our knowledge, NHP-D is the first ever method for link prediction over directed hypergraphs. An important feature of NHP is that it can also be used for hyperlinks in which dissimilar vertices interact (e.g. acids reacting with bases). Another attractive feature of NHP is that it can be used to predict unseen hyperlinks at test time (inductive hyperlink prediction). Through extensive experiments on multiple real-world datasets, we show NHP's effectiveness. CCS CONCEPTS • Computing methodologies → Neural networks; Unsupervised learning.

show abstract

“…PLANE (Le and Lauw 2014) extracts topics and 2D visualization coordinates simultaneously. NRTM (Bai et al 2018) extends VAE to document networks, outperforming another model RDL (Wang, Shi, and Yeung 2017) that extends DAE. These models capture only the first-order neighborhood.…”

Section: Related Workmentioning

confidence: 99%

“…We compare our models with several categories of baseline models as listed below. Following(Chen and Zaki 2017;Bai et al 2018), the activation functions for AE, DAE, CAE, KSAE, and NRTM are sigmoid, while those for VAE and KATE are tanh (hidden) and sigmoid (output) respectively. We use validation set to choose the best hyperparameters.…”

mentioning

confidence: 99%

Topic Modeling on Document Networks with Adjacent-Encoder

Zhang

Lauw

2020

AAAI

View full text Add to dashboard Cite

Oftentimes documents are linked to one another in a network structure,e.g., academic papers cite other papers, Web pages link to other pages. In this paper we propose a holistic topic model to learn meaningful and unified low-dimensional representations for networked documents that seek to preserve both textual content and network structure. On the basis of reconstructing not only the input document but also its adjacent neighbors, we develop two neural encoder architectures. Adjacent-Encoder, or AdjEnc, induces competition among documents for topic propagation, and reconstruction among neighbors for semantic capture. Adjacent-Encoder-X, or AdjEnc-X, extends this to also encode the network structure in addition to document content. We evaluate our models on real-world document networks quantitatively and qualitatively, outperforming comparable baselines comprehensively.

show abstract

Neural Relational Topic Models for Scientific Article Analysis

Cited by 45 publications

References 19 publications

Topic Memory Networks for Short Text Classification

Topic Memory Networks for Short Text Classification

NHP: Neural Hypergraph Link Prediction

Topic Modeling on Document Networks with Adjacent-Encoder

Contact Info

Product

Resources

About