Recurrent Hierarchical Topic-Guided RNN for Language Generation

Dandan Guo, Bo Chen, Ruiying Lu, Mingyuan Zhou
Proceedings of the 37th International Conference on Machine Learning, PMLR 119:3810-3821, 2020.

Abstract

To simultaneously capture syntax and global semantics from a text corpus, we propose a new larger-context recurrent neural network (RNN) based language model, which extracts recurrent hierarchical semantic structure via a dynamic deep topic model to guide natural language generation. Moving beyond a conventional RNN-based language model that ignores long-range word dependencies and sentence order, the proposed model captures not only intra-sentence word dependencies, but also temporal transitions between sentences and inter-sentence topic dependencies. For inference, we develop a hybrid of stochastic-gradient Markov chain Monte Carlo and recurrent autoencoding variational Bayes. Experimental results on a variety of real-world text corpora demonstrate that the proposed model not only outperforms larger-context RNN-based language models, but also learns interpretable recurrent multilayer topics and generates diverse sentences and paragraphs that are syntactically correct and semantically coherent.

Cite this Paper

BibTeX
@InProceedings{pmlr-v119-guo20a, title = {Recurrent Hierarchical Topic-Guided {RNN} for Language Generation}, author = {Guo, Dandan and Chen, Bo and Lu, Ruiying and Zhou, Mingyuan}, booktitle = {Proceedings of the 37th International Conference on Machine Learning}, pages = {3810--3821}, year = {2020}, editor = {III, Hal Daumé and Singh, Aarti}, volume = {119}, series = {Proceedings of Machine Learning Research}, month = {13--18 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v119/guo20a/guo20a.pdf}, url = {https://proceedings.mlr.press/v119/guo20a.html}, abstract = {To simultaneously capture syntax and global semantics from a text corpus, we propose a new larger-context recurrent neural network (RNN) based language model, which extracts recurrent hierarchical semantic structure via a dynamic deep topic model to guide natural language generation. Moving beyond a conventional RNN-based language model that ignores long-range word dependencies and sentence order, the proposed model captures not only intra-sentence word dependencies, but also temporal transitions between sentences and inter-sentence topic dependencies. For inference, we develop a hybrid of stochastic-gradient Markov chain Monte Carlo and recurrent autoencoding variational Bayes. Experimental results on a variety of real-world text corpora demonstrate that the proposed model not only outperforms larger-context RNN-based language models, but also learns interpretable recurrent multilayer topics and generates diverse sentences and paragraphs that are syntactically correct and semantically coherent.} }
Endnote
%0 Conference Paper %T Recurrent Hierarchical Topic-Guided RNN for Language Generation %A Dandan Guo %A Bo Chen %A Ruiying Lu %A Mingyuan Zhou %B Proceedings of the 37th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2020 %E Hal Daumé III %E Aarti Singh %F pmlr-v119-guo20a %I PMLR %P 3810--3821 %U https://proceedings.mlr.press/v119/guo20a.html %V 119 %X To simultaneously capture syntax and global semantics from a text corpus, we propose a new larger-context recurrent neural network (RNN) based language model, which extracts recurrent hierarchical semantic structure via a dynamic deep topic model to guide natural language generation. Moving beyond a conventional RNN-based language model that ignores long-range word dependencies and sentence order, the proposed model captures not only intra-sentence word dependencies, but also temporal transitions between sentences and inter-sentence topic dependencies. For inference, we develop a hybrid of stochastic-gradient Markov chain Monte Carlo and recurrent autoencoding variational Bayes. Experimental results on a variety of real-world text corpora demonstrate that the proposed model not only outperforms larger-context RNN-based language models, but also learns interpretable recurrent multilayer topics and generates diverse sentences and paragraphs that are syntactically correct and semantically coherent.
APA
Guo, D., Chen, B., Lu, R. & Zhou, M.. (2020). Recurrent Hierarchical Topic-Guided RNN for Language Generation. Proceedings of the 37th International Conference on Machine Learning, in Proceedings of Machine Learning Research 119:3810-3821 Available from https://proceedings.mlr.press/v119/guo20a.html.

Related Material