We consider incorporating topic information into the sequence-to-sequence framework to generate informative and interesting responses for chatbots. To this end, we propose a topic aware sequence-to-sequence (TA-Seq2Seq) model. The model utilizes topics to simulate prior knowledge of human that guides them to form informative and interesting responses in conversation, and leverages the topic inf...

Medical services play a pivotal role in people’s lives and the national economy. Although number of healthcare facilities is currently growing every year, there are still major problems terms access pressure on flow people. Therefore, an urgent need for complementary medical to alleviate patients their psychological burden enable them receive timely advice. This article designs implements Q&amp...

This paper presents the solution to problem of summarizing Kazakh texts. The text summarization is considered as a sequence two tasks: extracting most important sentences and simplifying received sentences. task solved using TF-IDF method neural network technology “Seq2Seq”. Problem NMT for simplification was in absence dataset training. To solve this work propose use transfer learning method. ...

This article presents an emotion-regularized conditional variational autoencoder (Emo-CVAE) model for generating emotional conversation responses. In conventional CVAE-based response generation, emotion labels are simply used as additional conditions in prior, posterior and decoder networks. Considering that styles naturally entangled with semantic contents the language space, Emo-CVAE utilizes...

A deep learning approach has been widely applied in sequence modeling problems. In terms of automatic speech recognition (ASR), its performance has significantly been improved by increasing large speech corpus and deeper neural network. Especially, recurrent neural network and deep convolutional neural network have been applied in ASR successfully. Given the arising problem of training speed, w...

Based on a Double Deep-Q Network with deep ResNet (DDQN-ResNet), this paper proposes novel method for transmission network expansion planning (TNEP). Since TNEP is large scale and mixed-integer linear programming (MILP) problem, as the optimal constraints increase, numerical calculation heuristic learning-based methods suffer from heavy computational complexities in training. Besides, due to bl...

Deep learning is one of the subsets of machine learning that is widely used in Artificial Intelligence (AI) field such as natural language processing and machine vision. The learning algorithms require optimization in multiple aspects. Generally, model-based inferences need to solve an optimized problem. In deep learning, the most important problem that can be solved by optimization is neural n...

We present a new method to approximate posterior probabilities of Bayesian Network using Deep Neural Network. Experiment results on several public Bayesian Network datasets shows that Deep Neural Network is capable of learning joint probability distribution of Bayesian Network by learning from a few observation and posterior probability distribution pairs with high accuracy. Compared with tradi...

Identifying complex behavior in human interactions for observational studies often involves the tedious process of transcribing and annotating large amounts of data. While there is significant work towards accurate transcription in Automatic Speech Recognition, automatic Natural Language Understanding of high-level human behaviors from the transcribed text is still at an early stage of developm...