Article
Multidisciplinary Sciences
Travis R. Goodwin, Dina Demner-Fushman, Kyle Lo, Lucy Lu Wang, Hoa T. Dang, Ian M. Soboroff
Summary: The COVID-19 pandemic has led to a rapid increase in the publication of information regarding its health, socio-economic, and cultural consequences. Manual management of this information is not feasible, thus the use of automatic question answering systems can efficiently highlight the key points. By utilizing various information sources and questions from different stakeholders, a dataset was developed to explore automatic question answering for multiple domains. Analysis of these questions revealed that while the information needs of experts and the public may overlap, satisfying answers often require different information sources or approaches. This dataset has the potential to support the development of question answering systems in various domains, including epidemics as well as legal or financial domains.
Review
Computer Science, Information Systems
Jorge Martinez-Gil
Summary: Many legal professionals find the abundance of information on laws at various levels to be costly, time-consuming, and prone to errors. This is due to the unstructured nature of legislation and the overwhelming amount of new laws being released. Researchers agree that an automated question-answering system can greatly impact daily legal activities and even a semi-automatic solution could reduce workload significantly by quickly processing legal resources to answer queries. This study aims to assess existing solutions to address this challenge both quantitatively and qualitatively.
COMPUTER SCIENCE REVIEW
(2023)
Article
Computer Science, Information Systems
Mariam M. Biltawi, Sara Tedmori, Arafat Awajan
Summary: Question-answering (QA) systems aim to provide answers for questions by extracting or generating from text. Arabic poses challenges as a language with limited research despite a large number of native speakers. Some QA systems have been developed for Arabic text, which can be further analyzed in different components such as question analysis and information retrieval.
Article
Computer Science, Artificial Intelligence
Gianni Costa, Riccardo Ortale
Summary: In this paper, two model-based approaches are proposed for recommending repliers in question-answering communities, with the focus on tags to avoid processing large amounts of text messages. The first approach routes questions to answerers based on their expertise in the corresponding topics marked by question tags. The second approach takes into account the repliers' answering propensity. Experimental results demonstrate the superiority of our approaches in recommendation effectiveness.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Mathematics
Kaiyi Tu, Mingyue Jiang, Zuohua Ding
Summary: This paper introduces the use of metamorphic testing technique to evaluate QA systems, studying textual QA and visual QA systems and identifying relevant metamorphic relations. Experimental results reveal the capabilities and strengths/weaknesses of the four QA systems from various aspects.
Article
Computer Science, Information Systems
Yi-Hui Chen, Eric Jui-Lin Lu, Ying-Yen Lin
Summary: The study introduces a low-cost SPARQL generator called Light-QAWizard, which utilizes multi-label classification to reduce query cost significantly. By integrating the results of a template classifier, Light-QAWizard generates corresponding query grammars that outperformed all other models with nearly half the query cost.
Article
Computer Science, Artificial Intelligence
Yiyi Zhou, Rongrong Ji, Xiaoshuai Sun, Jinsong Su, Deyu Meng, Yue Gao, Chunhua Shen
Summary: This article introduces a new VQA learning paradigm called FG-A1C, which addresses the challenge of massive training cost in VQA by fine-grained design of the learning method. The experiments demonstrate significant benefits of this approach in terms of training efficiency and model accuracy.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Article
Computer Science, Information Systems
Soroosh Sorkhani, Roohollah Etemadi, Amin Bigdeli, Morteza Zihayat, Ebrahim Bagheri
Summary: This paper addresses the problem of question routing in Community Question Answering (CQA) platforms using a learning to rank approach. The study introduces 74 features classified into content-based and social-based categories and shows that these features significantly improve question routing.
INFORMATION SCIENCES
(2022)
Article
Computer Science, Artificial Intelligence
Fengshi Jing, Hao Ren, Weibin Cheng, Xin Wang, Qingpeng Zhang
Summary: In a community question-answering (CQA) system, the best answer for a specific question plays a key role in improving service quality. Existing approaches to answer selection in CQA systems have limitations in incorporating both expertise and authority of the respondents. In this study, a new model called KAAS is proposed to enhance performance by considering both expertise and authority, utilizing domain knowledge, and integrating social network information.
KNOWLEDGE-BASED SYSTEMS
(2022)
Review
Computer Science, Artificial Intelligence
Leona Cilar Budler, Lucija Gosak, Gregor Stiglic
Summary: The use of conversational agents in health care is increasing globally, but their effectiveness is not well-understood. This advanced review aimed to assess the use and effectiveness of conversational agents in various health care fields. Most of the reviewed articles reported the effectiveness, while less information was available on the use. The study findings provide evidence-based knowledge about artificial intelligence-based question-answering systems in health care.
WILEY INTERDISCIPLINARY REVIEWS-DATA MINING AND KNOWLEDGE DISCOVERY
(2023)
Article
Computer Science, Artificial Intelligence
Somayyeh Behmanesh, Alireza Talebpour, Mehrnoush Shamsfard, Mohammad Mahdi Jafari
Summary: Recent AI studies have focused on developing question answering systems for automatic responses to natural language questions. Knowledge-based open domain question answering systems can accurately generate answers to questions in various fields. However, these systems require further development to scale answer retrieval and question interpretation. Deep learning methods are being used in this research area. Existing knowledge-based question answering systems use manually curated knowledge bases or knowledge bases automatically extracted from unstructured texts, or a combination of both. Limited access to knowledge bases in open domain question answering systems limits their expandability. Systems that use curated knowledge bases have high precision but limited coverage, while systems that use extracted knowledge bases have higher coverage but lower precision. To improve precision over extracted knowledge bases, a solution for enhancing relation span detection in questions is proposed in this paper. A dataset with 16,675 simple questions and answers based on Reverb triples is introduced. A method based on a fine-tuned BERT model is proposed for relation span detection in questions, resulting in a precision of 99.65%.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Education, Scientific Disciplines
Ivry Zagury-Orly, Steven J. Durning
Summary: This article discusses the challenges of holding closed-book examinations in medical education during the coronavirus pandemic, and proposes the potential of open-book exams as an alternative. The article calls on medical educators to seize the current opportunity to explore the impact of open-book exams on teaching and assessment.
Article
Automation & Control Systems
Binbin Jin, Enhong Chen, Hongke Zhao, Zhenya Huang, Qi Liu, Hengshu Zhu, Shui Yu
Summary: In this paper, a unified model EARNN is proposed for answer selection and ranking tasks in CQA. The model leverages both Q&A semantics and multifacet domain effects, with attention mechanisms designed to capture deep effects of topics and a time-sensitive ranking function to model timeliness in CQA. A question-dependent pairwise learning strategy is also developed to effectively train the model, and experimental results on a real-world dataset from Quora validate its effectiveness and interpretability.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Gouthaman Kv, Anurag Mittal
Summary: Generalizing beyond the experiences is important for developing robust machine learning systems. Current Visual Question Answering (VQA) models heavily rely on language-priors from the train set, leading to poor performance on Out-of-Distribution (OOD) test sets. This paper investigates the role of the sequence model architecture in the performance of VQA models on OOD datasets. A novel Graph attention network (GAT)-based question-encoder is proposed to mitigate the over-dependency on language biases and improve the OOD performance in VQA.
PATTERN RECOGNITION
(2022)
Article
Computer Science, Artificial Intelligence
Khalid Nassiri, Moulay Akhloufi
Summary: This paper reviews studies related to the use of transformer models in the implementation of question-answering systems. It focuses on the attention and transformer models, explores the latest research trends in textual QA datasets, evaluates the models' performance using various metrics, and highlights solutions to simplify the implementation of Transformer models.
APPLIED INTELLIGENCE
(2023)
Article
Neurosciences
David A. Buckley, Elaine M. Jennings, Nikita N. Burke, Michelle Roche, Veronica McInerney, Jonathan D. Wren, David P. Finn, Patrick C. McHugh
MOLECULAR NEUROBIOLOGY
(2018)
Article
Cell Biology
Sathyaseelan S. Deepa, Gavin Pharaoh, Michael Kinter, Vivian Diaz, Wilson C. Fok, Kaitlyn Riddle, Daniel Pulliam, Shauna Hill, Kathleen E. Fischer, Vanessa Soto, Constantin Georgescu, Jonathan D. Wren, Carlo Viscomi, Arlan Richardson, Holly Van Remmen
Article
Biochemistry & Molecular Biology
Chao Huang, Chenying Fu, Jonathan D. Wren, Xuejun Wang, Feng Zhang, Yanhui H. Zhang, Samuel A. Connel, Taosheng Chen, Xin A. Zhang
CELLULAR AND MOLECULAR LIFE SCIENCES
(2018)
Article
Biochemistry & Molecular Biology
Jonathan D. Wren
Article
Immunology
Elizabeth Gensterblum, Paul Renauer, Patrick Coit, Faith M. Strickland, Nathan C. Kilian, Shaylynn Miller, Mikhail Ognenovski, Jonathan D. Wren, Pei-Suen Tsou, Emily E. Lewis, Kathleen Maksimowicz-McKinnon, W. Joseph McCune, Bruce C. Richardson, Amr H. Sawalha
JOURNAL OF AUTOIMMUNITY
(2018)
Review
Cardiac & Cardiovascular Systems
Zoltan Ungvari, Stefano Tarantini, Tamas Kiss, Jonathan D. Wren, Cory B. Giles, Courtney T. Griffin, Walter Lee Murfee, Pal Pacher, Anna Csiszar
NATURE REVIEWS CARDIOLOGY
(2018)
Article
Cell & Tissue Engineering
Evan Fields, Jonathan D. Wren, Constantin Georgescu, John R. Daum, Gary J. Gorbsky
STEM CELL RESEARCH
(2018)
Article
Immunology
Michelle L. Ratliff, Joshua Garton, Lori Garman, M. David Barron, Constantin Georgescu, Kathryn A. White, Eliza Chakravarty, Jonathan D. Wren, Courtney G. Montgomery, Judith A. James, Carol F. Webb
JOURNAL OF AUTOIMMUNITY
(2019)
Article
Biochemistry & Molecular Biology
Nicholas Kinney, Kyle Titus-Glover, Jonathan D. Wren, Robin T. Varghese, Pawel Michalak, Han Liao, Ramu Anandakrishnan, Arichanah Pulenthiran, Lin Kang, Harold R. Garner
NUCLEIC ACIDS RESEARCH
(2019)
Editorial Material
Biochemical Research Methods
Jonathan D. Wren, Alfonso Valencia, Janet Kelso
Article
Cell Biology
Hem Sapkota, Jonathan D. Wren, Gary J. Gorbsky
JOURNAL OF CELL SCIENCE
(2020)
Article
Medicine, Research & Experimental
Joshua M. Corbin, Constantin Georgescu, Jonathan D. Wren, Chao Xu, Adam S. Asch, Maria J. Ruiz-Echevarria
Summary: Resistance to anti-androgen therapy in prostate cancer is often driven by genetic and epigenetic aberrations in androgen receptor and coregulatory genes. Specific small RNAs can downregulate essential genes, leading to potent androgen signaling inhibition and cell death. Targeting TMEFF2 with short hairpin/small interfering RNAs may be a novel therapeutic strategy for prostate cancer.
MOLECULAR THERAPY-NUCLEIC ACIDS
(2021)
Article
Immunology
Liangyue Qian, Sandra Bajana, Constantin Georgescu, Vincent Peng, Hong-Cheng Wang, Indra Adrianto, Marco Colonna, Jose Alberola-Ila, Jonathan D. Wren, Xiao-Hong Sun
JOURNAL OF EXPERIMENTAL MEDICINE
(2019)
Article
Biochemical Research Methods
Constantin Georgescu, Jonathan D. Wren
Meeting Abstract
Rheumatology
Michelle L. Joachims, Kerry M. Leehan, Mikhail G. Dozmorov, Zijian Pan, Astrid Rasmussen, Lida Radfar, David M. Lewis, Donald U. Stone, Kiely Grundahl, R. Hal Scofield, Christopher J. Lessard, Jonathan Wren, Kathy L. Sivils, Jacen Maier-Moore, A. Darise Farris
CLINICAL AND EXPERIMENTAL RHEUMATOLOGY
(2018)
