Dialogue systems are attractive natural language processing tasks and facilitate a bigger role in real-life applications. In human-computer interface systems, dialogue systems resemble an important tool. The advances in dialogue systems lead to the utilization of a broad range of data-driven machine learning techniques for efficient natural language processing.
   More recently, owing to the tremendous success of deep learning in various application domains, it has also been applied in dialogue systems. The popular categories of dialogue systems are task-oriented and conversational systems. Speech recognition, therapeutic systems, and storytelling are some promising applicative domains of dialogue systems using deep learning.
   Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Vanilla Sequence-to-sequence Models, Hierarchical Recurrent Encoder-Decoder (HRED), Memory Networks, Attention Networks, Transformer, Pointer Net and CopyNet, Deep Reinforcement Learning models, Generative Adversarial Networks (GANs) and Knowledge Graph Augmented Neural Networks are state-of-the-art deep learning frameworks utilized by dialogue systems.
   Dialogue systemsreal-world applicative tasks are Customer service agent knowledge base, Guided selling, Help desk, Website navigation, Technical support, personalized service, Training or education, Call centers, and interactive voice response.
   The possible future research directions of deep learning-enabled dialogue systems are multimodal dialogue systems, multitask dialogue systems, corpus exploration on the internet, user modeling, and dialogue generation with a long-term goal. Trending research topics on task-oriented dialogue systems are pretrained models for natural language understanding, domain transfer for natural language understanding and dialogue state trackers, tracking efficiency for dialogue state trackers, response consistency for natural language generation, end-to-end task-oriented dialogue systems and retrieval methods for task-oriented dialogue systems.
   Trending research topics on non-task-oriented dialogue systems are context awareness, response coherence, response diversity, empathetic response, controllable generation, conversation topics, interactive training, and visual dialogue. Various research studies and surveys have been conducted under the dialogue system. Such research surveys and reviews are listed below, which describe neural models in dialogue systems, categories of dialogue systems, research challenges, trending topics, evaluation methods, benchmark datasets, and future research scopes.