Search

Automatic Text Summarization (ATS) involves estimating the salience of information and creating coherent summaries that include all relevant and important information from the original text. Extensive research has been carried out on ATS since 1958, gradually evolving from simple to advanced techniques, including machine learning-based, neural network-based, and deep learning-based techniques. Progress has been made in both extractive and abstractive methods throughout this development. Despite numerous surveys on ATS, there remains a notable absence of a comprehensive literature review encompassing the latest advancements in deep learning techniques for text summarization. Therefore, this paper provides a Systematic Literature Review (SLR) of deep learning-based text summarization in both types (extractive and abstractive) between 2014 and 2023. To the best of our knowledge, this is the first SLR that offers a comprehensive overview of extractive and abstractive text summarization techniques based on Deep Learning models. According to the defined inclusion and exclusion criteria, 73 deep learning-based text summarization studies are selected for further investigation. The structure of the review is organized as follows. Firstly, it identifies and examines the deep learning models employed in both extractive and abstractive text summarization. Then, the input text's representation methods are identified and discussed clearly. Next, training strategies used in supervised extractive summarization techniques are identified. Furthermore, mechanisms that improve the abstractive summarization process are identified. Additionally, the most commonly used datasets and their advantages and disadvantages are discussed. The most commonly used evaluation metrics are also identified. Finally, the challenges and possible solutions to guide future research in the field are discussed. • Analyze the latest deep learning-based text summarization techniques. • Introduce a new taxonomy of deep learning models for text summarization. • Identify methods for representing input text clearly. • Identify training strategies for supervised extractive summarization techniques. • Identify the mechanisms used in abstractive summarization techniques. [ABSTRACT FROM AUTHOR]

Natural Language Processing (NLP) is the computerized approach to analyzing text using both structured and unstructured data. NLP is a simple, empirically powerful, and reliable approach. It achieves state-of-the-art performance in language processing tasks like Semantic Search (SS), Machine Translation (MT), Text Summarization (TS), Sentiment Analyzer (SA), Named Entity Recognition (NER) and Emotion Detection (ED). NLP is expected to be the technology of the future, based on current technology deployment and adoption. The primary question is: What does NLP have to offer in terms of reality, and what are the prospects? There are several problems to be addressed with this developing method, as it must be compatible with future technology. In this paper, the benefits, challenges and limitations of this innovative paradigm along with the areas open to do research are shown. [ABSTRACT FROM AUTHOR]

Text summarization is a subtask of natural language processing referring to the automatic creation of a concise and fluent summary that captures the main ideas and topics from one or multiple documents. Earlier literature surveys focus on extractive approaches, which rank the top-n most important sentences in the input document and then combine them to form a summary. As argued in the literature, the summaries of these approaches do not have the same lexical flow or coherence as summaries that are manually produced by humans. Newer surveys elaborate abstractive approaches, which generate a summary with potentially new phrases and sentences compared to the input document. Generally speaking, contrary to the extractive approaches, the abstractive ones create summaries that are more similar to those produced by humans. However, these approaches still lack the contextual representation needed to form fluent summaries. Recent advancements in deep learning and pretrained language models led to the improvement of many natural language processing tasks, including abstractive summarization. Overall, these surveys do not present a comprehensive evaluation framework that assesses the aforementioned approaches. Taking the above into account, the contribution of this survey is fourfold: (i) we provide a comprehensive survey of the state-of-the-art approaches in text summarization; (ii) we conduct a comparative evaluation of these approaches, using well-known datasets from the related literature, as well as popular evaluation scores such as ROUGE-1, ROUGE-2, ROUGE-L, ROUGE-LSUM, BLEU-1, BLEU-2 and SACREBLEU; (iii) we report on insights gained on various aspects of the text summarization process, including existing approaches, datasets and evaluation methods, and we outline a set of open issues and future research directions; (iv) we upload the datasets and the code used in our experiments in a public repository, aiming to increase the reproducibility of this work and facilitate future research in the field. [ABSTRACT FROM AUTHOR]

Copyright of System Research & Information Technologies / Sistemnì Doslìdžennâ ta Ìnformacìjnì Tehnologìï is the property of Institute for the Applied System Analysis at the NTUU KPI and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Radiological imaging is a globally prevalent diagnostic method, yet the free text contained in radiology reports is not frequently used for secondary purposes. Natural Language Processing can provide structured data retrieved from these reports. This paper provides a summary of the current state of research on Large Language Model (LLM) based approaches for information extraction (IE) from radiology reports. We conduct a scoping review that follows the PRISMA-ScR guideline. Queries of five databases were conducted on August 1st 2023. Among the 34 studies that met inclusion criteria, only pre-transformer and encoder-based models are described. External validation shows a general performance decrease, although LLMs might improve generalizability of IE approaches. Reports related to CT and MRI examinations, as well as thoracic reports, prevail. Most common challenges reported are missing validation on external data and augmentation of the described methods. Different reporting granularities affect the comparability and transparency of approaches. [ABSTRACT FROM AUTHOR]

Multiple-choice test generation is one of the most complex NLP problems, especially in languages other than English, where there is a lack of prior research. After a review of the literature, it has been verified that some methods like the usage of rule-based systems or primitive neural networks have led to the application of a recent architecture, the Transformer architecture, in the tasks of Answer Extraction (AE) and Question Generation (QG). Thereby, this study is centred in searching and developing better models for the AE and QG tasks in Spanish, using an answer-aware methodology. For this purpose, three multilingual models (mT5-base, mT0-base and BLOOMZ-560 M) have been fine-tuned using three different datasets: a translation to Spanish of the SQuAD dataset; SQAC, which is a dataset in Spanish; and their union (SQuAD + SQAC), which shows slightly better results. Regarding the models, the performance of mT5-base has been compared with that found in two newer models, mT0-base and BLOOMZ-560 M. These models were fine-tuned for multiple tasks in literature, including AE and QG, but, in general, the best results are obtained from the mT5 models trained in our study with the SQuAD + SQAC dataset. Nonetheless, some other good results are obtained from mT5 models trained only with the SQAC dataset. For their evaluation, the widely used BLEU1-4, METEOR and ROUGE-L metrics have been obtained, where mT5 outperforms some similar research works. Besides, CIDEr, SARI, GLEU, WER and the cosine similarity metrics have been calculated to present a benchmark within the AE and QG problems for future work. [ABSTRACT FROM AUTHOR]

Background: Systematically screening published literature to determine the relevant publications to synthesize in a review is a time-consuming and difficult task. Large language models (LLMs) are an emerging technology with promising capabilities for the automation of language-related tasks that may be useful for such a purpose. Methods: LLMs were used as part of an automated system to evaluate the relevance of publications to a certain topic based on defined criteria and based on the title and abstract of each publication. A Python script was created to generate structured prompts consisting of text strings for instruction, title, abstract, and relevant criteria to be provided to an LLM. The relevance of a publication was evaluated by the LLM on a Likert scale (low relevance to high relevance). By specifying a threshold, different classifiers for inclusion/exclusion of publications could then be defined. The approach was used with four different openly available LLMs on ten published data sets of biomedical literature reviews and on a newly human-created data set for a hypothetical new systematic literature review. Results: The performance of the classifiers varied depending on the LLM being used and on the data set analyzed. Regarding sensitivity/specificity, the classifiers yielded 94.48%/31.78% for the FlanT5 model, 97.58%/19.12% for the OpenHermes-NeuralChat model, 81.93%/75.19% for the Mixtral model and 97.58%/38.34% for the Platypus 2 model on the ten published data sets. The same classifiers yielded 100% sensitivity at a specificity of 12.58%, 4.54%, 62.47%, and 24.74% on the newly created data set. Changing the standard settings of the approach (minor adaption of instruction prompt and/or changing the range of the Likert scale from 1–5 to 1–10) had a considerable impact on the performance. Conclusions: LLMs can be used to evaluate the relevance of scientific publications to a certain review topic and classifiers based on such an approach show some promising results. To date, little is known about how well such systems would perform if used prospectively when conducting systematic literature reviews and what further implications this might have. However, it is likely that in the future researchers will increasingly use LLMs for evaluating and classifying scientific publications. [ABSTRACT FROM AUTHOR]

The increasing volume of scientific publications has created a need for more efficient and effective literature review processes. Bibliometric analysis is a quantitative approach to analysing bibliographic data extracted from research studies to identify publishing patterns and trends within specific knowledge domains. Science mapping is a widespread technique in bibliometric analysis that enables researchers to reveal the structure of their respective fields and identify dominant themes. However, there is still a lack of clarity and transparency in describing the science mapping process, which can hinder continued refinement and improvement of this critical field of research. This study provides a comprehensive overview of science mapping in bibliometric analysis based on published review studies from prestigious international journals. It outlines the science mapping mechanism and explores challenges and opportunities, focusing on incorporating text mining approaches to support the analytical literature review process. The study sheds light on previously unexplored mechanisms in the literature of bibliometric analysis, revealing gaps in existing research. The study contributes to the growing body of research on bibliometric analysis by highlighting the need for continuous improvement and the deployment of text mining techniques to support the analysis of scientific publication data. This study offers valuable insights for researchers, policymakers, and practitioners seeking to enhance their understanding of science mapping and bibliometric analysis. [ABSTRACT FROM AUTHOR]

In recent years, large language models (LLMs) have come into view as one of the most transformative developments in the technical domain, influencing diverse sectors ranging from natural language processing (NLP) to creative arts. Their rise signifies an unprecedented convergence of computational prowess, sophisticated algorithms, and expansive datasets, pushing the boundaries of what was once thought to be achievable. Such a profound impact mandates a thorough exploration of the LLMs' evolutionary trajectory. Consequently, this article conducts a literature review of the most impactful scientific works, using the reliable Web of Science (WoS) indexing database as a data source in order to attain a thorough and quality-assured analysis. This review identifies relevant patterns, provides research insights, traces technological growth, and anticipates potential future directions. Beyond mapping the known, this study aims to highlight uncharted areas within the LLM landscape, thereby catalyzing future research endeavors. The ultimate goal is to enhance collective understanding, encourage collaboration, and guide subsequent innovations in harnessing the potential of LLMs for societal and technological advancement. [ABSTRACT FROM AUTHOR]

Medical Artificial Intelligence (MedAI) harnesses the power of medical research through AI algorithms and vast data to address healthcare challenges. The security, integrity, and credibility of MedAI tools are paramount, because human lives are at stake. Predatory research, in a culture of "publish or perish," is exploiting the "pay for publish" model to infiltrate he research literature repositories. Although, it is challenging to measure the actual predatory research induced data pollution and patient harm, ourwork shows that the breached integrity of MedAI inputs is a serious threat to trust the MedAI output. We review a wide range of research literature discussing the threats of data pollution in the research literature, feasible attacks impacting MedAI solutions, research literature-based tools, and influence on healthcare. Our contribution lies in presenting a comprehensive literature review, addressing the gap of predatory research vulnerabilities affecting MedAI solutions, and helping to develop robust MedAI solutions in the future. [ABSTRACT FROM AUTHOR]

The creation of blockchain-based software applications requires today considerable technical knowledge, particularly in software design and programming. This is regarded as a major barrier in adopting this technology in business and making it accessible to a wider audience. As a solution, low-code and no-code approaches have been proposed that require only little or no programming knowledge for creating full-fledged software applications. In this paper we extend a review of academic approaches from the discipline of model-driven engineering as well as industrial low-code and no-code development platforms for blockchains. This includes a content-based, computational analysis of relevant academic papers and the derivation of major topics. In addition, the topics were manually evaluated and refined. Based on these analyses we discuss the spectrum of approaches in this field and derive opportunities for further research. [ABSTRACT FROM AUTHOR]

Generative artificial intelligence (AI) and large language models (LLMs), exemplified by ChatGPT, are promising for revolutionizing data and information management in healthcare and medicine. However, there is scant literature guiding their integration for non-AI professionals. This study conducts a scoping literature review to address the critical need for guidance on integrating generative AI and LLMs into healthcare and medical practices. It elucidates the distinct mechanisms underpinning these technologies, such as Reinforcement Learning from Human Feedback (RLFH), including few-shot learning and chain-of-thought reasoning, which differentiates them from traditional, rule-based AI systems. It requires an inclusive, collaborative co-design process that engages all pertinent stakeholders, including clinicians and consumers, to achieve these benefits. Although global research is examining both opportunities and challenges, including ethical and legal dimensions, LLMs offer promising advancements in healthcare by enhancing data management, information retrieval, and decision-making processes. Continued innovation in data acquisition, model fine-tuning, prompt strategy development, evaluation, and system implementation is imperative for realizing the full potential of these technologies. Organizations should proactively engage with these technologies to improve healthcare quality, safety, and efficiency, adhering to ethical and legal guidelines for responsible application. [ABSTRACT FROM AUTHOR]

With the explosion of visual content on the Internet, creating captions for images has become a necessary task and an exciting topic for many researchers. Furthermore, image captioning is becoming increasingly important as the number of people utilizing social media platforms grows. While there is extensive research on English image captioning (EIC), studies focusing on image captioning in other languages, especially Arabic, are limited. There has also yet to be an attempt to survey Arabic image captioning (AIC) systematically. This research aims to systematically survey encoder-decoder EIC while considering the following aspects: visual model, language model, loss functions, datasets, evaluation metrics, model comparison, and adaptability to the Arabic language. A systematic review of the literature on EIC and AIC approaches published in the past nine years (2015–2023) from well-known databases (Google Scholar, ScienceDirect, IEEE Xplore) is undertaken. We have identified 52 primary English and Arabic studies relevant to our objectives (The number of articles on Arabic captioning is 11, and the rest are for the English language). The literature review shows that applying the English-specific models to the Arabic language is possible, with the use of a high-quality Arabic database and following the appropriate preprocessing. Moreover, we discuss some limitations and ideas to solve them as a future direction. [ABSTRACT FROM AUTHOR]

This article offers a comprehensive review of the research on Natural Language Generation (NLG) over the past two decades, especially in relation to data-to-text generation and text-to-text generation deep learning methods, as well as new applications of NLG technology. This survey aims to (a) give the latest synthesis of deep learning research on the NLG core tasks, as well as the architectures adopted in the field; (b) detail meticulously and comprehensively various NLG tasks and datasets, and draw attention to the challenges in NLG evaluation, focusing on different evaluation methods and their relationships; (c) highlight some future emphasis and relatively recent research issues that arise due to the increasing synergy between NLG and other artificial intelligence areas, such as computer vision, text, and computational creativity. [ABSTRACT FROM AUTHOR]

According to numerous reports, ChatGPT represents a significant breakthrough in the field of artificial intelligence. ChatGPT is a pre-trained AI model designed to engage in natural language conversations, utilizing sophisticated techniques from Natural Language Processing (NLP), Supervised Learning, and Reinforcement Learning to comprehend and generate text comparable to human-generated text. This article provides an overview of the training process and fundamental functionality of ChatGPT, accompanied by a preliminary review of the relevant literature. Notably, this article presents the first comprehensive literature review of this technology at the time of publication, aiming to aggregate all the available pertinent articles to facilitate further developments in the field. Ultimately, the authors aim to offer an appraisal of the technology's potential implications on existing knowledge and technology, along with potential challenges that must be addressed. [ABSTRACT FROM AUTHOR]

The fact that advanced technologies and their economic applications have generated increasing resource costs justifies the transition from a linear approach to a circular one in order to control these costs. From this perspective, this study presents how artificial intelligence can help achieve this goal. Therefore, at the beginning of this article, we begin with an introduction and brief review of the literature on the subject. Our research procedure involved the combination of qualitative and quantitative forms of research using mixed methods. In this study, we presented and analyzed five chatbot solutions used in the field of the circular economy. The analysis of these five chatbots helped us design, in the second part of this paper, the procedures for data collection, training, development, and testing of a chatbot using various natural language processing (NLP) and deep processing (DP) techniques. Additionally, we include discussions and some conclusions regarding all aspects of the subject to see how they can help us in future studies. Furthermore, our future research with this topic will have as the goal the effective construction of a chatbot dedicated to the circular economy. [ABSTRACT FROM AUTHOR]

Automatically understanding the content of medical images and delivering accurate descriptions is an emerging field of artificial intelligence that combines skills in both computer vision and natural language processing fields. Medical image captioning is involved in various applications related to diagnosis, treatment, report generation and computer-aided diagnosis to facilitate the decision making and clinical workflows. Unlike generic image captioning, medical image captioning highlights the relationships between image objects and clinical findings, which makes it a very challenging task. Although few review papers have already been published in this field, their coverage is still quite limited and only particular problems are addressed. This motivates the current paper where a rapid review protocol was adopted to review the latest achievements in automatic medical image captioning from the medical domain perspective. We aim through this review to provide the reader with an up-to-date literature in this field by summarizing the key findings and approaches in this field, including the related datasets, applications and limitations as well as highlighting the main competitions, challenges and future directions. [ABSTRACT FROM AUTHOR]

Copyright of Al-Mustansiriyah Journal of Science is the property of Republic of Iraq Ministry of Higher Education & Scientific Research (MOHESR) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Transformer architectures are highly expressive because they use self-attention mechanisms to encode long-range dependencies in the input sequences. In this paper, we present a literature review on Transformer-based (TB) models, providing a detailed overview of each model in comparison to the Transformer's standard architecture. This survey focuses on TB models used in the field of Natural Language Processing (NLP) for textual-based tasks. We begin with an overview of the fundamental concepts at the heart of the success of these models. Then, we classify them based on their architecture and training mode. We compare the advantages and disadvantages of popular techniques in terms of architectural design and experimental value. Finally, we discuss open research, directions, and potential future work to help solve current TB application challenges in NLP. [ABSTRACT FROM AUTHOR]

Engineering design has proven to be a rich context for applying artificial intelligence (AI) methods, but a categorization of such methods applied in AI-based design research works seems to be lacking. This paper presents a focused literature review of AI-based methods mapped to the different stages of the engineering design process and describes how these methods assist the design process. We surveyed 108 AI-based engineering design papers from peer-reviewed journals and conference proceedings and mapped their contribution to five stages of the engineering design process. We categorized seven AI-based methods in our dataset. Our literature study indicated that most AI-based design research works are targeted at the conceptual and preliminary design stages. Given the open-ended, ambiguous nature of these early stages, these results are unexpected. We conjecture that this is likely a result of several factors, including the iterative nature of design tasks in these stages, the availability of open design data repositories, and the inclination to use AI for processing computationally intensive tasks, like those in these stages. Our study also indicated that these methods support designers by synthesizing and/or analyzing design data, concepts, and models in the design stages. This literature review aims to provide readers with an informative mapping of different AI tools to engineering design stages and to potentially motivate engineers, design researchers, and students to understand the current state-of-the-art and identify opportunities for applying AI applications in engineering design. [ABSTRACT FROM AUTHOR]

Purpose: The purpose of this research paper is to explore ChatGPT's potential as an innovative designer tool for the future development of artificial intelligence. Specifically, this conceptual investigation aims to analyze ChatGPT's capabilities as a tool for designing and developing near about human intelligent systems for futuristic used and developed in the field of Artificial Intelligence (AI). Also with the helps of this paper, researchers are analyzed the strengths and weaknesses of ChatGPT as a tool, and identify possible areas for improvement in its development and implementation. This investigation focused on the various features and functions of ChatGPT that make it an effective designer for AI, and also valuable evaluated its limitations & potential areas for improvement. By conducting this investigation, this research paper seeks to contributed of established to the advancement of AI research and facilitated the development of more sophisticated AI tools in the future. This research paper focused on contributing to the development of more advanced and sophisticated AI systems by exploring the potential of ChatGPT as a tool for designing and developing such systems. Design/methodology/approach: In this research paper, a conceptual investigation approach as used to explore ChatGPT as a metamorphosis designer for the future of artificial intelligence. The methodology for this investigation involves comprehensive literature review of existing research on ChatGPT and its applications in the field of AI. This methodology followed by a detailed analysis of ChatGPT's architecture, including its input/output mechanisms, its training process, and its ability to generate high-quality responses to user queries. To evaluate ChatGPT's effectiveness as a designer for AI, this investigation also involved a comparative analysis of ChatGPT. This analysis helps identify ChatGPT's strengths and limitations, as well as potential areas for improvement. Overall, this research paper aims to provide a detailed conceptual investigation of ChatGPT's potential as an innovative, metamorphosis designer for the future of artificial intelligence. The use of a comprehensive methodology that content analysis, combines literature review and comparative analysis of current research and cognitive reviewed of theoretical concepts. This study also highlights the conceptual reviewed on philosophical domain of AI with the reference of ChatGPT. Findings: The findings of this research paper on ChatGPT as a morphological designer for the future of artificial intelligence are based on a conceptual investigation of the tool's potential in this area. The investigation revealed that ChatGPT's architecture and capabilities make it a highly effective tool for morphological design in AI. Specifically, its ability to generate high-quality responses to user queries, its capacity to learn and adapt to new information, and its versatility in handling various types of data make it an ideal tool for designing and developing sophisticated AI systems. The investigation also identified several potential limitations of ChatGPT as a morphological designer, such as its dependence on large amounts of data and its susceptibility to bias and errors. However, the investigation also revealed possible strategies for overcoming these limitations, such as improving the quality and diversity of the training data used by ChatGPT. Overall, the findings of this research paper suggest that ChatGPT has significant potential as a morphological designer for the future of artificial intelligence. Further research and development in this area could lead to the creation of more advanced and sophisticated AI systems. Originality/value: The originality and value of this paper lies in the exploration of ChatGPT as a morphological designer for the future of artificial intelligence. This investigation provides a unique and in-depth analysis of ChatGPT's potential as a tool for designing and developing intelligent systems, focusing specifically on its capabilities as a morphological designer. This research paper adds value to the field of AI by identifying the strengths and weaknesses of ChatGPT as a morphological designer and highlighting potential areas for improvement and further development. The investigation also contributes to the advancement of AI research by exploring the potential of ChatGPT as a tool to create more sophisticated and intelligent systems in the future. Overall, the originality and value of this research paper stems from its innovative approach to investigate the potential of ChatGPT as a morphological designer for the future of artificial intelligence. By providing a comprehensive analysis of the capabilities and limitations of tools in this area, the paper contributes to the development of more advanced and effective AI systems in the future. [ABSTRACT FROM AUTHOR]

Issues of the environmental crisis are being addressed by researchers, government, and organizations alike. GHRM is one such field that is receiving lots of research focus since it is targeted at greening the firms and making them eco-friendly. This research reviews 317 articles from the Scopus database published on green human resource management (GHRM) from 2008 to 2021. The study applies text mining, latent semantic analysis (LSA), and network analysis to explore the trends in the research field in GHRM and establish the relationship between the quantitative and qualitative literature of GHRM. The study has been carried out using KNIME and VOSviewer tools. As a result, the research identifies five recent research trends in GHRM using K-mean clustering. Future researchers can work upon these identified trends to solve environmental issues, make the environment eco-friendly, and motivate firms to implement GHRM in their practices. [ABSTRACT FROM AUTHOR]

In this work, a comprehensive review of the multi-objective grey wolf optimizer (MOGWO) is provided. In multi-objective optimization (MO), more than one objective function must be considered at the same time. To deal with such problems, a priori or a posteriori MOGWO variants have been proposed in the literature. In the a priori model, the multi-objective functions are aggregated into a single objective function by a number of weights. In the posterior model, the multi-objective formulation is maintained and MOGWO is employed to estimate the Pareto optimal solutions representing the best trade-offs between the objectives. Due to the successful performance of MOGWO, it has been widely utilized for MO. This review covers the research growth of MOGWO in terms of a number of researches, topics, top researchers, etc. Furthermore, several versions of MOGWO have been introduced and reviewed with applications in diverse fields. This work also provides a critical analysis to show the shortcomings and limitations of using the basic version of MOGWO followed by several future directions. This review paper will be a base paper for any researcher interested to implement MOGWO in its work. [ABSTRACT FROM AUTHOR]

Image captioning is the task of automatically generating sentences that describe an input image in the best way possible. The most successful techniques for automatically generating image captions have recently used attentive deep learning models. There are variations in the way deep learning models with attention are designed. In this survey, we provide a review of literature related to attentive deep learning models for image captioning. Instead of offering a comprehensive review of all prior work on deep image captioning models, we explain various types of attention mechanisms used for the task of image captioning in deep learning models. The most successful deep learning models used for image captioning follow the encoder-decoder architecture, although there are differences in the way these models employ attention mechanisms. Via analysis on performance results from different attentive deep models for image captioning, we aim at finding the most successful types of attention mechanisms in deep models for image captioning. Soft attention, bottom-up attention, and multi-head attention are the types of attention mechanism widely used in state-of-the-art attentive deep learning models for image captioning. At the current time, the best results are achieved from variants of multi-head attention with bottom-up attention. [ABSTRACT FROM AUTHOR]

By dint of the massive daily production of user-generated content (textual reviews) in E-commerce platforms, the need to automatically process it and extract different types of knowledge from it becomes a necessity. In this work, an attempt has been made to summarize some studies that aim to propose systems, which automatically mine textual reviews expressed in natural languages for the purpose of supporting customers' decision-making process in E-commerce (buying, renting, and booking). The given review is the first work of this type and it includes 44 studies (30 aspect/feature-based summarizers and 14 reputation systems) published from 2004 to 2021. First, it investigates aspect and feature-based summarizers that aim to help customers in making an informed decision toward online entities (products, movies, hotels, services ...). Second, it introduces reputation generation systems that seek to provide valuable information about online items. Finally, it provides recommendations for future research directions and open problems. [ABSTRACT FROM AUTHOR]

Due to the exponential growth of textual data and web sources, an automatic mechanism is required to identify relevant information embedded within them. The utility of Automatic Keyphrase Extraction (AKPE) cannot be overstated, given its widespread adoption in many Information Retrieval (IR), Natural Language Processing (NLP) and Text Mining (TM) applications, and its potential ability to solve difficulties related to extracting valuable information. In recent years, a wide range of AKPE techniques have been proposed. However, they are still impaired by low accuracy rates and moderate performance. This paper provides a comprehensive review of recent research efforts on the AKPE task and its related techniques. More concretely, we highlight the common process of this task, while also illustrating the various approaches used (supervised, unsupervised, and Deep Learning) and released techniques. We investigate the major challenges that such techniques face and depict the specific complexities they address. Besides, we provide a comparison study of the best performing techniques, discuss why some perform better than others and propose recommendations to improve each stage of the AKPE process. [ABSTRACT FROM AUTHOR]

Throughout an information search, a user needs to make sense of the information found to create an understanding. This requires cognitive effort that can be demanding. Building on prior sensemaking models and expanding them with ideas from learning and cognitive psychology, we examined the use of cognitive mechanisms during individual sensemaking. We conducted a qualitative user study of 15 students who searched for and made sense of information for business analysis and news writing tasks. Through the analysis of think‐aloud protocols, recordings of screen movements, intermediate work products of sensemaking, including notes and concept maps, and final reports, we observed the use of 17 data‐driven and structure‐driven mechanisms for processing new information, examining individual concepts and relationships, and detecting anomalies. These cognitive mechanisms, as the basic operators that move sensemaking forward, provide in‐depth understanding of how people process information to produce sense. Meaningful learning and sensemaking are closely related, so our findings apply to learning as well. Our results contribute to a better understanding of the sensemaking process—how people think—and this better understanding can inform the teaching of thinking skills and the design of improved sensemaking assistants and mind tools. [ABSTRACT FROM AUTHOR]

Purpose This paper aims to examine the extent to which Business Intelligence and Big Data feature within academic research in hospitality and tourism published until 2016, by identifying research gaps and future developments and designing an agenda for future research.Design/methodology/approach The study consists of a systematic quantitative literature review of academic articles indexed on the Scopus and Web of Science databases. The articles were reviewed based on the following features: research topic; conceptual and theoretical characterization; sources of data; type of data and size; data collection methods; data analysis techniques; and data reporting and visualization.Findings Findings indicate an increase in hospitality and tourism management literature applying analytical techniques to large quantities of data. However, this research field is fairly fragmented in scope and limited in methodologies and displays several gaps. A conceptual framework that helps to identify critical business problems and links the domains of business intelligence and big data to tourism and hospitality management and development is missing. Moreover, epistemological dilemmas and consequences for theory development of big data-driven knowledge are still a terra incognita. Last, despite calls for more integration of management and data science, cross-disciplinary collaborations with computer and data scientists are rather episodic and related to specific types of work and research.Research limitations/implications This work is based on academic articles published before 2017; hence, scientific outputs published after the moment of writing have not been included. A rich research agenda is designed.Originality/value This study contributes to explore in depth and systematically to what extent hospitality and tourism scholars are aware of and working intendedly on business intelligence and big data. To the best of the authors’ knowledge, it is the first systematic literature review within hospitality and tourism research dealing with business intelligence and big data. [ABSTRACT FROM AUTHOR]

Data generation has increased drastically over the past few years. Data management has also grown in importance because extracting the significant value out of a huge pile of raw data is of prime importance while making different decisions. This article reviews the concept of Big Data. The Thomson Reuters Web of Science Core Collection academic database was used to overview publications that contained “BIG DATA” keywords and were included in Web of Science Category under “Engineering”. The analysis of publications was made according to year, country, journal, authors, language and funding agency. [ABSTRACT FROM AUTHOR]

Background: There are many approaches to evaluating aging-in-place technologies. While there are standard measures for outcomes such as health and caregiver burden, which lend themselves to statistical analysis, researchers have a harder time identifying why a particular information and communication technology (ICT) intervention worked (or not). Objective: The purpose of this paper is to review a variety of methods that can help answer these deeper questions of when people will utilize an ICT for aging in place, how they use it, and most importantly why. This review is sensitive to the special context of aging in place, which necessitates an evaluation that can explore the nuances of the experiences of older adults and their caregivers with the technology in order to fully understand the potential impact of ICTs to support aging in place. Methods: The authors searched both health (PubMed) and technology (ACM Digital Library) venues, reviewing 115 relevant papers that had an emphasis on understanding the use of aging-in-place technologies. This mini-review highlights a number of popular methods used in both the health and technology fields, including qualitative methods (e.g. interviews, focus groups, contextual observations, diaries, and cultural probes) and quantitative methods (e.g. surveys, the experience sampling method, and technology logs). Results: This review highlights that a single evaluation method often is not adequate for understanding why people adopt ICTs for aging in place. The review ends with two examples of multifaceted evaluations attempting to get at these deeper issues. Conclusion: There is no proscriptive formula for evaluating the intricate nuances of technology acceptance and use in the aging-in-place context. Researchers should carefully examine a wide range of evaluation techniques to select those that will provide the richest insights for their particular project. © 2014 S. Karger AG, Basel [ABSTRACT FROM AUTHOR]

Purpose – This paper aims to report a study of researchers' preferences in selecting information from cited papers to include in a literature review, and the kinds of transformations and editing applied to the selected information. Design/methodology/approach – This is a part of a larger project to develop an automatic summarization method that emulates human literature review writing behaviour. Research questions were: how are literature reviews written – where do authors select information from, what types of information do they select and how do they transform it? What is the relationship between styles of literature review (integrative and descriptive) and each of these variables (source sections, types of information and types of transformation)? The authors analysed the literature review sections of 20 articles from the Journal of the American Society for Information Scienceand Technology, 2001-2008, to answer these questions. Referencing sentences were mapped to 279 source papers to determine the source sentences. The type of information selected, the sections of source papers where the information was taken from, and the types of editing changes made to include in the literature review were analyzed. Findings – Integrative literature reviews contain more research result information and critique, and reference more information from the results and conclusion sections of the source papers. Descriptive literature reviews contain more research method information, and reference more information from the abstract and introduction sections. The most common kind of transformation is the high-level summary, though descriptive literature reviews have more cut-pasting, especially for information taken from the abstract. The types of editing – substitutions, insertions and deletions – applied to the source sentences are identified. Practical implications – The results are useful in the teaching of literature review writing, and indicate ways for automatic summarization systems to emulate human literature review writing. Originality/value – Though there have been several studies of abstracts and abstracting, there are few studies of literature reviews and literature review writing. Little is known about how writers select information from source papers, integrate it and present it in a literature review. This paper fills some of the gaps. [ABSTRACT FROM AUTHOR]

Online review Web sites have enabled new interactions between companies and their customers. In this article we draw on interviews with users, reviewers, and establishments to explore how local review Web sites can change interactions around local places. Review Web sites such as Yelp and Tripadvisor allow customers to "previsit" establishments and areas of a city before an actual visit. The collection of a large numbers of user-generated reviews has also created a new genre of writing, with reviewers gaining considerable pleasure from passing on word of mouth and influencing others' choices. Reviews also offer a new channel of communication between establishments, customers, and competitors. We discuss how review Web sites can be designed to cater for a broader range of interactions around reviews beyond a focus on recommendations. [ABSTRACT FROM AUTHOR]

Background: A drug-drug interaction (DDI) occurs when one drug influences the level or activity of another drug. The increasing volume of the scientific literature overwhelms health care professionals trying to be kept up-to-date with all published studies on DDI. Methods: This paper describes a hybrid linguistic approach to DDI extraction that combines shallow parsing and syntactic simplification with pattern matching. Appositions and coordinate structures are interpreted based on shallow syntactic parsing provided by the UMLS MetaMap tool (MMTx). Subsequently, complex and compound sentences are broken down into clauses from which simple sentences are generated by a set of simplification rules. A pharmacist defined a set of domain-specific lexical patterns to capture the most common expressions of DDI in texts. These lexical patterns are matched with the generated sentences in order to extract DDIs. Results: We have performed different experiments to analyze the performance of the different processes. The lexical patterns achieve a reasonable precision (67.30%), but very low recall (14.07%). The inclusion of appositions and coordinate structures helps to improve the recall (25.70%), however, precision is lower (48.69%). The detection of clauses does not improve the performance. Conclusions: Information Extraction (IE) techniques can provide an interesting way of reducing the time spent by health care professionals on reviewing the literature. Nevertheless, no approach has been carried out to extract DDI from texts. To the best of our knowledge, this work proposes the first integral solution for the automatic extraction of DDI from biomedical texts. [ABSTRACT FROM AUTHOR]

This paper proposes a framework for the evaluation of user interaction with textual metadata surrogates in the search result interfaces of various types of Information Retrieval (IR) systems. Metadata surrogates are representations of the full-text documents displayed to the user as a list of retrieved results after a search has been performed in an IR system. By examining the metadata surrogates, users can make judgments about the relevance of the full-text document without having to access and evaluate the document itself, thus saving a considerable amount of time and effort. The literature review, however, reveals a lack of frameworks for the evaluation of users' interaction with metadata surrogates. The implications of such a framework would be to inform designers and researchers of IR systems about the main components of users' interaction with metadata surrogates and to facilitate the process of evaluating metadata surrogates in terms of content and presentation. [ABSTRACT FROM AUTHOR]

In this paper we propose an open source application called LDAShiny, which provides a graphical user interface to perform a review of scientific literature using the latent Dirichlet allocation algorithm and machine learning tools in an interactive and easy-to-use way. The procedures implemented are based on familiar approaches to modeling topics such as preprocessing, modeling, and postprocessing. The tool can be used by researchers or analysts who are not familiar with the R environment. We demonstrated the application by reviewing the literature published in the last three decades on the species Oreochromis niloticus. In total we reviewed 6196 abstracts of articles recorded in Scopus. LDAShiny allowed us to create the matrix of terms and documents. In the preprocessing phase it went from 530,143 unique terms to 3268. Thus, with the implemented options the number of unique terms was reduced, as well as the computational needs. The results showed that 14 topics were sufficient to describe the corpus of the example used in the demonstration. We also found that the general research topics on this species were related to growth performance, body weight, heavy metals, genetics and water quality, among others. [ABSTRACT FROM AUTHOR]

• A comprehensive introduction of rhetorical structure theory (RST). • A snapshot and some statistical data of RST-DT. • An elaboration of the classical and latest RST parsing methods. • Applications of RST, especially in expert and intelligent systems. • Comparisons with other discourse structure theories. Rhetorical structure theory (RST) is a significant theory about discourse organization. With an increasing number of research interests focus on RST, many novel parsing approaches have been proposed and motivated many brand new applications, such as chatbots and other expert and intelligent systems. However, the work on RST dates back many years and there remains a lack of comprehensive literature reviews. The aim of this study is therefore to provide a comprehensive overview of RST, parsing methods and applications. In this paper, we first give a detailed introduction to RST. Then the commonly used discourse treebank: RST-DT is elaborated. We propose a new taxonomy to divide the RST parsing methods into different categories. With a focus on the classical and latest methods that have recently been developed, we review the pros and cons of these approaches, along with the performance analysis of them. We then summarize the applications of RST across various domains. Moreover, we present a comparative study of RST with other discourse structure theories. Finally, we discuss some implications of our findings and outline future research directions in this challenging and fast-growing field. [ABSTRACT FROM AUTHOR]