Abstract
This paper proposes a new variational autoencoder (VAE) for topic models. The variational inference (VI) for Bayesian models approximates the true posterior distribution by maximizing a lower bound of the log marginal likelihood of observations. We can implement VI as VAE by using a neural network called encoder to obtain parameters of approximate posterior. Our contribution is three-fold. First, we marginalize out per-document topic probabilities by following the proposal by Mimno et al. This marginalizing out has not been considered in the existing VAE proposals for topic modeling to the best of our knowledge. Second, after marginalizing out topic probabilities, we need to approximate the posterior probabilities of token-wise topic assignments. However, this posterior is categorical and thus cannot be approximated by continuous distributions like Gaussian. Therefore, we adopt the Gumbel-softmax trick. Third, while we can sample token-wise topic assignments with the Gumbel-softmax trick, we should consider document-wide contextual information for a better approximation. Therefore, we feed to our encoder network a concatenation of token-wise information and document-wide information, where the former is implemented as word embedding and the latter as the document-wide mean of word embeddings. The experimental results showed that our VAE improved the existing VAE proposals for a half of the data sets in terms of perplexity or of normalized pairwise mutual information (NPMI).
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Blei, D.M., Ng, A.Y., Jordan, M.I.: Latent Dirichlet allocation. J. Mach. Learn. Res. 3, 993–1022 (2003)
Bouma, G.: Normalized (Pointwise) Mutual information in collocation extraction. In: Proceedings of the Biennial GSCL Conference From Form to Meaning: Processing Texts Automatically, vol. 2009, pp. 31–40 (2009)
Dieng, A.B., Wang, C., Gao, J., Paisley, J.W.: TopicRNN: a recurrent neural network with long-range semantic dependency. CoRR abs/1611.01702 (2016). http://arxiv.org/abs/1611.01702
Goodfellow, I.J., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, vol. 27 (NIPS), pp. 2672–2680 (2014)
Griffiths, T.L., Steyvers, M.: Finding scientific topics. Proc. Nat. Acad. Sci. 101(suppl 1), 5228–5235 (2004)
Hoffman, M.D., Blei, D.M., Bach, F.R.: Online learning for latent Dirichlet allocation. Adv. Neural Inf. Process. Syst. (NIPS) 23, 856–864 (2010)
Jang, E., Gu, S., Poole, B.: Categorical reparameterization with Gumbel-softmax. CoRR abs/1611.01144 (2016), http://arxiv.org/abs/1611.01144
Kim, Y., Wiseman, S., Miller, A.C., Sontag, D., Rush, A.M.: Semi-amortized variational autoencoders. In: Proceedings of the 35th International Conference on Machine Learning (ICML), pp. 2683–2692 (2018)
Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. CoRR abs/1412.6980 (2014). http://arxiv.org/abs/1412.6980
Kingma, D.P., Welling, M.: Auto-encoding variational Bayes. CoRR abs/1312.6114 (2013). http://arxiv.org/abs/1312.6114
Masada, T., Takasu, A.: Adversarial learning for topic models. In: Proceedings of the 14th International Conference on Advanced Data Mining and Applications (ADMA), pp. 292–302 (2018)
Mescheder, L.M., Nowozin, S., Geiger, A.: Adversarial variational Bayes: unifying variational autoencoders and generative adversarial networks. In: Proceedings of the 34th International Conference on Machine Learning (ICML), pp. 2391–2400 (2017)
Miao, Y., Grefenstette, E., Blunsom, P.: Discovering discrete latent topics with neural variational inference. In: Proceedings of the 34th International Conference on Machine Learning (ICML), pp. 2410–2419 (2017)
Miao, Y., Yu, L., Blunsom, P.: Neural variational inference for text processing. In: Proceedings of the 33rd International Conference on Machine Learning (ICML), pp. 1727–1736 (2016)
Mimno, D., Hoffman, M.D., Blei, D.M.: Sparse stochastic inference for latent Dirichlet allocation. In: Proceedings of the 29th International Conference on Machine Learning (ICML), pp. 1515–1522 (2012)
Mnih, A., Hinton, G.E.: A scalable hierarchical distributed language model. Adv. Neural Inf. Process. Syst. (NIPS) 21, 1081–1088 (2008)
Press, O., Wolf, L.: Using the output embedding to improve language models. CoRR abs/1608.05859 (2016). http://arxiv.org/abs/1608.05859
Rezende, D.J., Mohamed, S., Wierstra, D.: Stochastic backpropagation and approximate inference in deep generative models. In: Proceedings of the 31st International Conference on Machine Learning (ICML), pp. II-1278-II-1286 (2014)
Roeder, G., Wu, Y., Duvenaud, D.K.: Sticking the landing: simple, lower-variance gradient estimators for variational inference. Adv. Neural Inf. Process. Syst. (NIPS) 30, 6928–6937 (2017)
Salimans, T., Knowles, D.A.: Fixed-form variational posterior approximation through stochastic linear regression. CoRR abs/1206.6679 (2012). http://arxiv.org/abs/1206.6679
Sønderby, C.K., Raiko, T., Maaløe, L., Sønderby, S.K., Winther, O.: Ladder variational autoencoders. Adv. Neural Inf. Process. Syst. (NIPS) 29, 3738–3746 (2016)
Srivastava, A., Sutton, C.: Autoencoding variational inference for topic models. CoRR abs/1703.01488 (2017). http://arxiv.org/abs/1703.01488
Teh, Y.W., Newman, D., Welling, M.: A collapsed variational Bayesian inference algorithm for latent Dirichlet allocation. Adv. Neural Inf. Process. Syst. (NIPS) 19, 1353–1360 (2006)
Titsias, M.K., Lázaro-Gredilla, M.: Doubly stochastic variational Bayes for non-conjugate inference. In: Proceedings of the 31st International Conference on Machine Learning (ICML), pp. II-1971-II-1980 (2014)
Tokui, S., Sato, I.: Reparameterization trick for discrete variables. CoRR abs/1611.01239 (2016). http://arxiv.org/abs/1611.01239
Wang, W., et al.: Topic compositional neural language model. In: Proceedings of the 21st International Conference on Artificial Intelligence and Statistics (AISTATS), pp. 356–365 (2018)
Acknowledgment
This work was supported by JSPS KAKENHI Grant Number JP18K11440.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Masada, T. (2020). Context-Dependent Token-Wise Variational Autoencoder for Topic Modeling. In: Brambilla, M., Cappiello, C., Ow, S. (eds) Current Trends in Web Engineering. ICWE 2019. Lecture Notes in Computer Science(), vol 11609. Springer, Cham. https://doi.org/10.1007/978-3-030-51253-8_6
Download citation
DOI: https://doi.org/10.1007/978-3-030-51253-8_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-51252-1
Online ISBN: 978-3-030-51253-8
eBook Packages: Computer ScienceComputer Science (R0)