The 28th International Joint Conference on Artificial Intelligence (IJCAI 2019) will take place on August 10-16, 2019, Macao, China
Title: Deep Bayesian Sequential Learning
Time: 8:30 AM -12:30 AM on August 11
Place: The Venetian Ballroom J, Convention Center, Venetian Macao Hotel Resort
Description: This tutorial addresses the advances in deep Bayesian learning for natural language with ubiquitous applications ranging from speech recognition to document summarization, text classification, text segmentation, information extraction, image caption generation, sentence generation, dialogue control, sentiment classification, recommendation system, question answering and machine translation, to name a few. Traditionally, "deep learning" is taken to be a learning process where the inference or optimization is based on the real-valued deterministic model. The "semantic structure" in words, sentences, entities, actions and documents drawn from a large vocabulary may not be well expressed or correctly optimized in mathematical logic or computer programs. The "distribution function" in discrete or continuous latent variable model for natural language may not be properly decomposed or estimated. This tutorial addresses the fundamentals of statistical models and neural networks, and focus on a series of advanced Bayesian models and deep models including hierarchical Dirichlet process, Chinese restaurant process, hierarchical Pitman-Yor process, Indian buffet process, recurrent neural network (RNN), long short-term memory, sequence-to-sequence model, variational auto-encoder (VAE), generative adversarial network (GAN), attention mechanism, memory-augmented neural network, skip neural network, stochastic neural network, predictive state neural network, policy neural network. We present how these models are connected and why they work for a variety of applications on symbolic and complex patterns in natural language. The variational inference and sampling method are formulated to tackle the optimization for complicated models. The word and sentence embeddings, clustering and co-clustering are merged with linguistic and semantic constraints. A series of case studies are presented to tackle different issues in deep Bayesian sequential learning. At last, we will point out a number of directions and outlooks for future studies.
Organization: The presentation of this tutorial is arranged into five parts. First of all, we share the current status of researches on natural language processing, statistical modeling and deep neural network and explain the key issues in deep Bayesian learning for discrete-valued observation data and latent semantics. Modern natural language models are introduced to address how data analysis is performed from language processing to semantic learning and memory networking. Secondly, we address a number of Bayesian models ranging from latent variable model to variational Bayesian inference, sampling method and Bayesian nonparametric learning for hierarchical, thematic and sparse topics from natural language. In the third part, a series of deep models including deep unfolding, GAN, memory network, sequence-to-sequence learning, convolutional neural network and attention network with transformer are introduced. The coffee break is arranged within this part. Next, the fourth part focuses on a variety of advanced studies which illustrate how deep Bayesian learning is developed to infer the sophisticated recurrent models for natural language understanding. In particular, the Bayesian RNN, VAE, neural variational learning, neural discrete representation, recurrent ladder network, stochastic neural network, Markov recurrent neural network, reinforcement learning and sequence GAN are introduced in various deep models which open a window to more practical tasks, e.g. reading comprehension, sentence generation, dialogue system, question answering and machine translation. In the final part, we spotlight on some future directions for deep language understanding which can handle the challenges of big data, heterogeneous condition and dynamic system. In particular, deep learning, structural learning, temporal and spatial modeling, long history representation and stochastic learning are emphasized. (slides)