ATM: Adversarial-neural Topic Model

Wang, Rui; Zhou, Deyu; He, Yulan

doi:10.1016/j.ipm.2019.102098

Cited by 72 publications

(38 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To be best of our knowledge, W-LDA is the first topic model based on the WAE framework. Recently, Adversarial Topic model (ATM) (Wang et al, 2018) proposes using GAN with Dirichlet prior to learn topics. The generator takes in samples from Dirichlet distribution and maps to a document-word distribution layer to form the fake samples.…”

Section: Related Workmentioning

confidence: 99%

Topic Modeling with Wasserstein Autoencoders

Feng¹,

Ding²,

Nallapati³

et al. 2019

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

View full text Add to dashboard Cite

We propose a novel neural topic model in the Wasserstein autoencoders (WAE) framework. Unlike existing variational autoencoder based models, we directly enforce Dirichlet prior on the latent document-topic vectors. We exploit the structure of the latent space and apply a suitable kernel in minimizing the Maximum Mean Discrepancy (MMD) to perform distribution matching. We discover that MMD performs much better than the Generative Adversarial Network (GAN) in matching high dimensional Dirichlet distribution. We further discover that incorporating randomness in the encoder output during training leads to significantly more coherent topics. To measure the diversity of the produced topics, we propose a simple topic uniqueness metric. Together with the widely used coherence measure NPMI, we offer a more wholistic evaluation of topic quality. Experiments on several real datasets show that our model produces significantly better topics than existing topic models.

show abstract

Section: Related Workmentioning

confidence: 99%

Topic Modeling with Wasserstein Autoencoders

Feng¹,

Ding²,

Nallapati³

et al. 2019

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

View full text Add to dashboard Cite

show abstract

“…We evaluate the performance of proposed models on four datasets: NYTimes 2 (NYT), Grolier 3 (GRL), DBpedia ontology classification dataset (DBP) (Zhang et al, 2015) and 20 Newsgroups 4 (20NG). For NYTimes and Grolier datasets, we use the processed version of (Wang et al, 2019a). For the DBpedia dataset, we first sample 100, 000 documents from the whole training set, and then perform preprocessing including tokenization, lemmatization, removal of stopwords, and low-frequency words.…”

Section: Methodsmentioning

confidence: 99%

“…Apart from VAE-based approaches, Adversarialneural Topic Model (ATM) (Wang et al, 2019a)) was proposed to model topics with GANs. The generator of ATM projects randomly sampled topic distributions to word distributions, and is adversarially trained with a discriminator that tries to distinguish real and generated word distributions.…”

Section: Neural Topic Modelingmentioning

confidence: 99%

“…Encoder E transforms a word distribution x i ∈ R V into its corresponding topic distribution z i ∈ R K . Following (Wang et al, 2019a), we represent x i ∈ X with the normalized TF-IDF (Term Frequency-Inverse Document Frequency) representation of i-th document:…”

Section: Encoder Network Ementioning

confidence: 99%

“…Therefore, it is less capable of capturing the multi-modality which is crucial for topic modeling (Wallach et al, 2009). To overcome such limitation, Wang et al (2019a) proposed Adversarial-neural Topic Model (ATM), a topic model based on Generative Adversarial Networks (GANs) (Goodfellow et al, 2014) and sampling topics directly from the Dirichlet distribution to impose a Dirichlet prior. ATM employs a generator transforming randomly sampled topic distributions to word distributions, and an adversarially trained discriminator estimating the probability that a word distribution came from the training data rather than the generator.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Neural Topic Modeling with Cycle-Consistent Adversarial Training

Hu¹,

Wang²,

Zhou³

et al. 2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Self Cite

View full text Add to dashboard Cite

Advances on deep generative models have attracted significant research interest in neural topic modeling. The recently proposed Adversarial-neural Topic Model models topics with an adversarially trained generator network and employs Dirichlet prior to capture the semantic patterns in latent topics. It is effective in discovering coherent topics but unable to infer topic distributions for given documents or utilize available document labels. To overcome such limitations, we propose Topic Modeling with Cycle-consistent Adversarial Training (ToMCAT) and its supervised version sToMCAT. ToMCAT employs a generator network to interpret topics and an encoder network to infer document topics. Adversarial training and cycle-consistent constraints are used to encourage the generator and the encoder to produce realistic samples that coordinate with each other. sToMCAT extends ToM-CAT by incorporating document labels into the topic modeling process to help discover more coherent topics. The effectiveness of the proposed models is evaluated on unsupervised/supervised topic modeling and text classification. The experimental results show that our models can produce both coherent and informative topics, outperforming a number of competitive baselines.

show abstract

Indicators and countermeasures of modern slavery in global supply chains: Pathway to a social supply chain management framework

et al. 2022

View full text Add to dashboard Cite

Even though global supply chains are (usually unintentionally) tied to slave labor, research and practice have largely ignored the issue. This is expected to change as civil society activism and new legislation increase the risk of litigation and reputational damage to supply chain partners. To deal with and combat modern slavery in the supply chain, a theory inspired social supply chain management framework consisting of indicators and countermeasures of modern slavery in the supply chain is developed. The framework is refined in a qualitative expert interview study. The theoretical framework is then evaluated by a multimethod empirical analysis that includes a multicase study based on publicly available supply chain data from 6000 media articles and company websites as well as a quantitative empirical study based on survey data from 280 corporate sustainability experts operating in global supply networks. The results show that economic, political-legal, social, and environmental factors have a significant impact on contemporary slavery in the supply chain. The study also motivates supply chain partners to use preventative and detective measures to reduce the probability of encountering modern slavery actions in their supply chain. Theoretical and managerial implications are drawn from the findings, pointing to a holistic approach to combatting modern slavery in the supply chain.

show abstract

ATM: Adversarial-neural Topic Model

Cited by 72 publications

References 23 publications

Topic Modeling with Wasserstein Autoencoders

Topic Modeling with Wasserstein Autoencoders

Neural Topic Modeling with Cycle-Consistent Adversarial Training

Indicators and countermeasures of modern slavery in global supply chains: Pathway to a social supply chain management framework

Contact Info

Product

Resources

About