We give an overview of recent exciting achievements of deep reinforcement learning (RL). We discuss six core elements, six important mechanisms, and twelve applications. We start with background of machine learning, deep learning and reinforcement learning. Next we discuss core RL elements, including value function, in particular, Deep Q-Network (DQN), policy, reward, model, planning, and exploration. After that, we discuss important mechanisms for RL, including attention and memory, unsupervised learning, transfer learning, multi-agent RL, hierarchical RL, and learning to learn. Then we discuss various applications of RL, including games, in particular, AlphaGo, robotics, natural language processing, including dialogue systems, machine translation, and text generation, computer vision, neural architecture design, business management, finance, healthcare, Industry 4.0, smart grid, intelligent transportation systems, and computer systems. We mention topics not reviewed yet, and list a collection of RL resources. After presenting a brief summary, we close with discussions. 
Please see Deep Reinforcement Learning, arXiv:1810.06339, for a significant update.

Deep Reinforcement Learning: An Overview

Deep learning has achieved remarkable success in numerous domains with help from large amounts of big data. However, the quality of data labels is a concern because of the lack of high-quality labels in many real-world scenarios. As noisy labels severely degrade the generalization performance of deep neural networks, learning from noisy labels (robust training) is becoming an important task in modern deep learning applications. In this survey, we first describe the problem of learning with label noise from a supervised learning perspective. Next, we provide a comprehensive review of 46 state-of-the-art robust training methods, all of which are categorized into seven groups according to their methodological difference, followed by a systematic comparison of six properties used to evaluate their superiority. Subsequently, we summarize the typically used evaluation methodology, including public noisy datasets and evaluation metrics. Finally, we present several promising research directions that can serve as a guideline for future studies.

Learning from Noisy Labels with Deep Neural Networks: A Survey

Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

The goal of text ranking is to generate an ordered list of texts retrieved from a corpus in response to a query. Although the most common formulation of text ranking is search, instances of the task can also be found in many natural language processing applications. This survey provides an overview of text ranking with neural network architectures known as transformers, of which BERT is the best-known example. The combination of transformers and self-supervised pretraining has been responsible for a paradigm shift in natural language processing (NLP), information retrieval (IR), and beyond. In this survey, we provide a synthesis of existing work as a single point of entry for practitioners who wish to gain a better understanding of how to apply transformers to text ranking problems and researchers who wish to pursue work in this area. We cover a wide range of modern techniques, grouped into two high-level categories: transformer models that perform reranking in multi-stage architectures and dense retrieval techniques that perform ranking directly. There are two themes that pervade our survey: techniques for handling long documents, beyond typical sentence-by-sentence processing in NLP, and techniques for addressing the tradeoff between effectiveness (i.e., result quality) and efficiency (e.g., query latency, model and index size). Although transformer architectures and pretraining techniques are recent innovations, many aspects of how they are applied to text ranking are relatively well understood and represent mature techniques. However, there remain many open research questions, and thus in addition to laying out the foundations of pretrained transformers for text ranking, this survey also attempts to prognosticate where the field is heading.

Pretrained Transformers for Text Ranking: BERT and Beyond

Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Health literacy in the eHealth era: A systematic review of the literature

A recent “third wave” of neural network (NN) approaches now delivers state-of-the-art performance in many machine learning tasks, spanning speech recognition, computer vision, and natural language processing. Because these modern NNs often comprise multiple interconnected layers, work in this area is often referred to as deep learning. Recent years have witnessed an explosive growth of research into NN-based approaches to information retrieval (IR). A significant body of work has now been created. In this paper, we survey the current landscape of Neural IR research, paying special attention to the use of learned distributed representations of textual units. We highlight the successes of neural IR thus far, catalog obstacles to its wider adoption, and suggest potentially promising directions for future research.

/pdf/neural-information-retrieval-at-the-end-of-the-early-years-144j0hldyz.pdf

Neural information retrieval: at the end of the early years

A recent "third wave" of Neural Network (NN) approaches now delivers state-of-the-art performance in many machine learning tasks, spanning speech recognition, computer vision, and natural language processing. Because these modern NNs often comprise multiple interconnected layers, this new NN research is often referred to as deep learning. Stemming from this tide of NN work, a number of researchers have recently begun to investigate NN approaches to Information Retrieval (IR). While deep NNs have yet to achieve the same level of success in IR as seen in other areas, the recent surge of interest and work in NNs for IR suggest that this state of affairs may be quickly changing. In this work, we survey the current landscape of Neural IR research, paying special attention to the use of learned representations of queries and documents (i.e., neural embeddings). We highlight the successes of neural IR thus far, catalog obstacles to its wider adoption, and suggest potentially promising directions for future research.

Neural Information Retrieval: A Literature Review

As information and communication technologies (ICTs) are increasingly used to support and deliver health care, access to Internet-based health services is enabling consumers to play an active role in their own health care. Today, this requires consumers to have a certain degree of health literacy within the context of e-health. To understand the extent to which existing studies have addressed health literacy within the context of Internet-based services, we conducted a systematic review of the literature. We performed four rounds of selection to identify relevant publications: database selection, keyword search, screening titles and abstracts, and screening the full text. This process produced a final sample of 42 publications. The findings from our review provide insights into how health literacy has been, and should be, addressed in the e-health era.

Health literacy and internet- and mobile app-based health services: a systematic review of the literature

Purpose – Smartphones have great potential to bridge the digital divide that low-socioeconomic status (SES) Hispanics have been experiencing. However, little is known about this group’s use of smartphones for health information. The purpose of this paper is to fill the gap by exploring the context in which smartphones were used for health information. Design/methodology/approach – The authors interviewed 20 low-SES Hispanic participants using the semi-structured interview method. Participants had not obtained college degrees and had annual incomes less than $30,000, but had used their smartphones for health information. The interviews were transcribed and analyzed using the qualitative content analysis method. Findings – Being economical was an important reason for low-SES Hispanic users to use smartphones for health information. The users relied heavily on public Wi-Fi to access the internet. They searched a wide range of health topics, mostly using the mobile web rather than apps. They lacked knowledge ...

Henna Kim

Papers

Health literacy in the eHealth era: A systematic review of the literature

Neural information retrieval: at the end of the early years

Neural Information Retrieval: A Literature Review

Health literacy and internet- and mobile app-based health services: a systematic review of the literature

Health information seeking of low socioeconomic status Hispanic adults using smartphones