Adapting Static and Contextual Representations for Policy Gradient-Based Summarization.

Considering the ever-growing volume of electronic documents made available in our daily lives, the need for an efficient tool to capture their gist increases as well. Automatic text summarization, which is a process of shortening long text and extracting valuable information, has been of great interest for decades. Due to the difficulties of semantic understanding and the requirement of large training data, the development of this research field is still challenging and worth investigating. In this paper, we propose an automated text summarization approach with the adaptation of static and contextual representations based on an extractive approach to address the research gaps. To better obtain the semantic expression of the given text, we explore the combination of static embeddings from GloVe (Global Vectors) and the contextual embeddings from BERT (Bidirectional Encoder Representations from Transformer) and GPT (Generative Pre-trained Transformer) based models. In order to reduce human annotation costs, we employ policy gradient reinforcement learning to perform unsupervised training. We conduct empirical studies on the public dataset, Gigaword. The experimental results show that our approach achieves promising performance and is competitive with various state-of-the-art approaches.

Data Twin-Driven Cyber-Physical Factory for Smart Manufacturing.

Because of the complex production processes and technology-intensive operations that take place in the aerospace and defense industry, introducing Industry 4.0 into the manufacturing processes of aircraft composite materials is inevitable. Digital Twin and Cyber-Physical Systems in Industry 4.0 are key techniques to develop digital manufacturing. Since it is very difficult to create high-fidelity virtual models, the development of digital manufacturing for aircraft manufacturers is challenging. In this study, we provide a view from a data simulation perspective and adopt machine learning approaches to simplify the high-fidelity virtual models in Digital Twin. The novel concept is called Data Twin, and the deployable service to support the simulation is known as the Data Twin Service (DTS). Relying on the DTS, we also propose a microservice software architecture, Cyber-Physical Factory (CPF), to simulate the shop floor environment. Additionally, there are two war rooms in the CPF that can be used to establish a collaborative platform: one is the Physical War Room, used to integrate real data, and the other is the Cyber War Room for handling simulation data and the results of the CPF.

An Empirical Investigation of Transfer Effects for Reinforcement Learning.

Previous studies have shown that training a reinforcement model for the sorting problem takes very long time, even for small sets of data. To study whether transfer learning could improve the training process of reinforcement learning, we employ Q-learning as the base of the reinforcement learning algorithm, apply the sorting problem as a case study, and assess the performance from two aspects, the time expense and the brain capacity. We compare the total number of training steps between nontransfer and transfer methods to study the efficiencies and evaluate their differences in brain capacity (i.e., the percentage of the updated Q-values in the Q-table). According to our experimental results, the difference in the total number of training steps will become smaller when the size of the numbers to be sorted increases. Our results also show that the brain capacities of transfer and nontransfer reinforcement learning will be similar when they both reach a similar training level.