ABSTRACT
Open-retrieval question answering systems are generally trained and tested on large datasets in well-established domains. However, low-resource settings such as new and emerging domains would especially benefit from reliable question answering systems. Furthermore, multilingual and cross-lingual resources in emergent domains are scarce, leading to few or no such systems. In this paper, we demonstrate a cross-lingual open-retrieval question answering system for the emergent domain of COVID-19. Our system adopts a corpus of scientific articles to ensure that retrieved documents are reliable. To address the scarcity of cross-lingual training data in emergent domains, we present a method utilizing automatic translation, alignment, and filtering to produce English-to-all datasets. We show that a deep semantic retriever greatly benefits from training on our English-to-all data and significantly outperforms a BM25 baseline in the cross-lingual setting. We illustrate the capabilities of our system with examples and release all code necessary to train and deploy such a system1 © 2023 Association for Computational Linguistics.
ABSTRACT
The COVID-19 pandemic has led to a surge in scientific publications, some of which have bypassed the usual peer-review processes, leading to an increase in unsupported claims being referenced. Therefore, the need for references in scientific articles is increasingly being questioned. The practice of relying solely on quantitative measures, such as impact factor, is also considered inadequate by many experts. This can lead to researchers choosing research ideas that are likely to generate favourable metrics instead of interesting and important topics. Evaluating the quality and scientific value of articles requires a rethinking of current approaches, with a move away from purely quantitative methods. Artificial intelligence (AI)-based tools are making scientific writing easier and less time-consuming, which is likely to further increase the number of scientific publications, potentially leading to higher quality articles. AI tools for searching, analysing, synthesizing, evaluating and writing scientific literature are increasingly being developed. These tools deeply analyse the content of articles, consider their scientific impact, and prioritize the retrieved literature based on this information, presenting it in simple visual graphs. They also help authors to quickly and easily analyse and synthesize knowledge from the literature, prepare summaries of key information, aid in organizing references, and improve manuscript language. The language model ChatGPT has already greatly changed the way people communicate with computers, bringing it closer to human communication. However, while AI tools are helpful, they must be used carefully and ethically. In summary, AI has already changed the way we write articles, and its use in scientific publishing will continue to enhance and streamline the process.
ABSTRACT
The massification of technologies, the implementation of 5G and the Internet of Things (IoT), allow implementing systems that contain virtual or augmented reality or implementation of both. In this sense, the covid 19 pandemic in the last years, has also affected people's behavior and leaned to shop without leaving their homes. VR, RA, and/or MR techniques are currently widely used for medicine, education, and entertainment, among others. In this study, we combine both elements to analyze the literature on e-commerce and the use of VR, AR, and/or RM. Searching and analyzing recent scientific articles were defined, and virtual reality is the most used, followed by the mixture of RV and RA, the above to improve the shopping experience, providing the customer with a more authentic and immersive environment. In future works, we will expect to expand this study, including how to evaluate the shopping experience and relate it to the customer experience. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.
ABSTRACT
We present COVID-QA, a Question Answering dataset consisting of 2,019 question/answer pairs annotated by volunteer biomedical experts on scientific articles related to COVID-19. To evaluate the dataset we compared a RoBERTa base model fine-tuned on SQuAD with the same model trained on SQuAD and our COVID-QA dataset. We found that the additional training on this domain-specific data leads to significant gains in performance. Both the trained model and the annotated dataset have been open-sourced at: https://github.com/deepset-ai/COVID-QA. © ACL 2020.All right reserved.
ABSTRACT
In this paper, we present an information retrieval system on a corpus of scientific articles related to COVID-19. We build a similarity network on the articles where similarity is determined via shared citations and biological domain-specific sentence embeddings. Ego-splitting community detection on the article network is employed to cluster the articles and then the queries are matched with the clusters. Extractive summarization using BERT and PageRank methods is used to provide responses to the query. We also provide a Question-Answer bot on a small set of intents to demonstrate the efficacy of our model for an information extraction module. © ACL 2020.All right reserved.
ABSTRACT
PurposeSearching, identifying and analysing the scientific literature on "corporate communication” published in scientific journals during the twenty-first century (2000–2021) and indexed in the Scopus database, as well as its possible relationship with COVID-19.Design/methodology/approachA systematic bibliographic search was carried out in Scopus and a subsequent analysis of the literature, based on variables such as year of publication, authorship, original language of the text, most used terms and concepts, journal titles, keywords and possible allusions to COVID-19 or the pandemic.Findings2023 results were initially identified, but after applying the filters that limited the results in time (2000–2021) and discriminated—according to the type of document—the results only to scientific articles, the sample finally analysed was 1,280 articles relating to "corporate communication”. It was found that these were mainly published in journals such as Corporate Communications and Journal of Communication Management, in English, and with an accentuated thematic dispersion, but mostly related to public relations, advertising and communication in general.Originality/valueThere is an article published in 2012, before the COVID-19 pandemic, in the Italian journal Igiene e sanità publica, which already established the relevance of researching the challenges and solutions to communication risks in health crisis situations.
ABSTRACT
The vast amount of COVID-19 research literature has made it difficult for medical experts, clinical scientists, and researchers to keep up with the latest research findings. We present two datasets for COVID-19 in this work: (1) first, we create a dataset from the up-to-date scientific publications on COVID-19, and (2) second, we build a gold-standard dataset of question-answering pairs annotated by volunteer biomedical experts on COVID-19 related scientific articles. We develop a question-answering (QA) pipeline that uses the first dataset to provide answers related to COVID-19 questions;we fine-tune MPNet (a Transformer model) on our gold-standard dataset and use it in the QA pipeline to enhance its reading capability. We also use this gold-standard dataset to evaluate the QA pipeline. The proposed MPNet version on the gold-standard dataset outperformed previous datasets and models, achieving an Exact Match/Fl score of 69.72/78.50 %, respectively © 2022 IEEE.
ABSTRACT
Purpose Searching, identifying and analysing the scientific literature on "corporate communication" published in scientific journals during the twenty-first century (2000-2021) and indexed in the Scopus database, as well as its possible relationship with COVID-19. Design/methodology/approach A systematic bibliographic search was carried out in Scopus and a subsequent analysis of the literature, based on variables such as year of publication, authorship, original language of the text, most used terms and concepts, journal titles, keywords and possible allusions to COVID-19 or the pandemic. Findings 2023 results were initially identified, but after applying the filters that limited the results in time (2000-2021) and discriminated-according to the type of document-the results only to scientific articles, the sample finally analysed was 1,280 articles relating to "corporate communication". It was found that these were mainly published in journals such as Corporate Communications and Journal of Communication Management, in English, and with an accentuated thematic dispersion, but mostly related to public relations, advertising and communication in general. Originality/value There is an article published in 2012, before the COVID-19 pandemic, in the Italian journal Igiene e sanita publica, which already established the relevance of researching the challenges and solutions to communication risks in health crisis situations.
ABSTRACT
The goal of this study is to find the best pedagogical idea for learning during the Covid-19 pandemic. The writing method in this article is the Systematic Literature Review method which aims to describe, study, and analyze students' pandemic pedagogy due to the impact of the Covid-19 pandemic in the digital transformation era. The selection of sources based on several criteria, namely: 1) literature must be directly related to local wisdom, character education, and the 2013 curriculum;(2) search for related literature originating from the results of research reports, national journals, international journals, relevant books, scientific articles, and scientific data related to the study of this article;(3) limitation of the year of publication of the literature in the last two years (2020-2021). The findings of the research indicate that, during the Covid-19 pandemic, the growth of digital transformation in the online learning system accelerated in Indonesia. However, this online learning brings various negative impacts on the pedagogical aspects of students in elementary schools. During the Covid-19, teachers must comprehend and use pandemic pedagogy while conducting online learning for primary school pupils. © 2021 ACM.
ABSTRACT
In this work, we focus on ive summarization methods for assisting medical researchers in effectively managing information. Particularly, we introduce a COVID-19-related summarization dataset (COVID-SUM) and propose a novel Keyword-aware Attention ive Summarization (KAAS) model. The KAAS model consists of two encoders and one decoder. As for the encoders, one is a standard article encoder built on transformer layers, while the other one is a hierarchical keyword encoder that first encodes the words in a keyword using BiLSTM, and then passes the keyword representations to a transformer layer to connect the keywords in an example. Additionally, a decoder with keyword-focused attention is utilized to further direct the decoding process to generate comprehensive summaries of the scientific articles. We benchmark several summarization methods on the new COVID-SUM dataset and release this dataset in the hope to promote advances to summarization in the COVID-19 medical area (https://github.com/ccip-author/COVID-SUM/releases ). Furthermore, we evaluate the KAAS on COVID-SUM, ArXiv, and PubMed datasets. Experimental results demonstrate that KAAS outperforms several state-of-the-art models on these datasets. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.
ABSTRACT
The advent of the COVID-19 pandemic caused by the Sars-CoV2 virus has caused serious damage in different areas. This has prompted thousands of researchers from different disciplines (biology, medicine, artificial intelligence, economics, etc.) to publish a very large number of scientific articles in a very short period, to answer questions related to this pandemic. This abundance of literature, however, raised another problem. It has indeed become extremely difficult for a researcher or a decision-maker to stay up to date with the latest scientific advances or to locate scientific articles related to a specific aspect of this pandemic. In this paper, we present an intelligent tool based on Machine learning, which automatically organizes a large dataset of Covid-19 related scientific literature and visualizes them in a way that helps these people navigating easily through this dataset and locating the sought documents easily. The documents are first pre-processed and transformed into numerical features. Then, those features are passed through a deep denoising autoencoder followed by Uniform Manifold Approximation and Projection technique (UMAP) to reduce their dimensionality into a 2D space. The projected data are then clustered with Agglomerative Clustering Algorithm. This is followed by a topic modeling step which we performed using Latent Dirichlet Allocation (LDA), in order to assign a label to each cluster. Finally, the documents are visualized to the user in an interactive interface that we developed. The experiments we conducted proved that our tool is efficient and useful. © 2021 IEEE.
ABSTRACT
The scientific literature on Covid-10 has seen unprecedented growth, being published so rapidly as to question its quality and the peer review process. This research analyzes the characteristics of the publications on Covid-19 with the greatest impact, mainly considering their content and the quality and level of evidence of the studies. The Web of Science Core Collection was searched for articles containing the terms "Covid-19" and "SARS-CoV-2," and the 100 most cited articles published in 2020 were selected. The data extracted included bibliographic data, journal submission, acceptance, and publication dates, the main topics covered, the type of study, and the level of evidence according to the SIGN scale, as well as the existence of corrections. Half of the articles were published in three journals, most of them in the early months of 2020. The most frequent types of studies were case series, narrative reviews, and expert opinions, with only one randomized controlled clinical trial. The articles focused mainly on the clinical characteristics and complications of patients, diagnostic and treatment methods, as well as the epidemiology and characteristics of the virus. The design of these studies reflects a low level of evidence, and data and scientific quality may be affected by how quickly they are published and the peer review process is performed.
ABSTRACT
Creating domain-specific glossaries that are both time-consuming and requires domain expertise. An effective and efficient automatic process will facilitate the glossary generation and its downstream applications for better decision making. In this project, we aim to build a domain-specific glossary from a large text corpus. We form the task as a knowledge graph construction problem with minimum supervision. We adapt both supervised pre-trained models and unsupervised methods for extracting relations for terms appear in the large corpus of scientific articles. We then utilize an off-the-shelf graph database to construct and store the knowledge graph. Furthermore, we develop an interactive Web-based tool for visualizing, exploring and querying the constructed knowledge graph. The project is sourced and funded by AI4DM initiative from the Office of National Intelligence (ONI) and the Defence Science and Technology (DST) Group, Australia. Although the fund requires the usage of a dataset of COVID-19 related literature collection, the solution to be presented in this paper is generic and could be easilt applied to any domain. © 2021 IEEE.
ABSTRACT
The COVID-19 pandemic is a kind of global disaster caused by the new coronavirus-19, the SARS-CoV-2 virus. Since the first eruption of this pandemic, which adversely affected the world in many ways, a large number of publications have been presented to the world of science. In this article, possible publication ethical dilemmas related to scientific articles increasing in number during the COVID-19 pandemic were tried to be reminded through two examples of articles.