Review
Computer Science, Artificial Intelligence
Silvia Casola, Alberto Lavelli
Summary: This paper surveys Natural Language Processing (NLP) approaches in summarizing, simplifying, and generating patent text. It highlights the challenges posed by the unique characteristics of patents to the current state of NLP research, presents previous work and its evolution critically, and draws attention to areas where further research is needed. To the best of the authors' knowledge, this is the first survey of generative approaches in the patent domain.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Mathematics
Samiha Fadloun, Khadidja Bennamane, Souham Meshoul, Mahmood Hosseini, Kheireddine Choutri
Summary: This paper proposes a novel approach that combines information visualization and machine learning analyses to automate the retrieval of information elements from complex terms of service. The approach involves creating a dataset and utilizing machine learning models for classification and text summarization. The results demonstrate the promising potential of the approach.
Article
Computer Science, Information Systems
Jeong-Wook Kim, Gi-Wan Hong, Hangbae Chang
Summary: Phishing crime is a serious global issue, with voice phishing targeting financial institutions over the telephone as the predominant form of attack. A study successfully converted phishing sound source files to text files through voice recognition, indicating that document data textualized by voice recognition can be used to judge voice phishing.
HUMAN-CENTRIC COMPUTING AND INFORMATION SCIENCES
(2021)
Article
Computer Science, Information Systems
Yuliy Iliev, Galina Ilieva
Summary: The rapid development of information technology and ubiquitous computing has transformed electronic devices from isolated islands of data and control to interconnected parts of intelligent systems. These network-based systems have advanced features, including IoT sensors and actuators, multiple connectivity options, and multimodal user interfaces, enabling remote monitoring and management. To develop a smart home system human machine interface with speech recognition, a new IoT-fog-cloud framework using natural language processing (NLP) methods is proposed. The framework adds utterance to command transformation to existing cloud-based speech-to-text and text-to-speech services, providing flexibility for different automation systems and languages.
Article
Multidisciplinary Sciences
Maarten Sap, Anna Jafarpour, Yejin Choi, Noah A. Smith, James W. Pennebaker, Eric Horvitz
Summary: This study introduces the measure of "sequentiality" to quantify the differences between autobiographical and imagined stories. By comparing the probability of a sentence with and without its preceding story context, the study finds that imagined stories have higher sequentiality than autobiographical stories, and the sequentiality of autobiographical stories increases when retold several months later. Additionally, the study reveals that lower sequentiality is associated with higher proportions of major events.
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA
(2022)
Article
Psychology, Multidisciplinary
Carly Fox, Sharad Jones, Sandra Laing Gillam, Megan Israelsen-Augenstein, Sarah Schwartz, Ronald Bradley Gillam
Summary: The study developed the LLUNA system for automatically evaluating six aspects of literate language in narratives, showing strong inter-rater reliability with expert scorers and surpassing reliability levels of non-expert scorers in four aspects. The system has potential for automating scoring of literate language in language sample analysis and narrative samples for assessment and progress-monitoring purposes.
FRONTIERS IN PSYCHOLOGY
(2022)
Article
Computer Science, Information Systems
Deepa Anand, Rupali Wagh
Summary: The availability of legal judgment documents in digital form opens up opportunities for information extraction and application. This paper proposes generic techniques using neural network for summarizing Indian legal judgment documents. The proposed approaches do not rely on handcrafted features or domain-specific knowledge, making them suitable for other domains as well.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2022)
Article
Construction & Building Technology
Sangyun Shin, Raja R. A. Issa
Summary: Voice is a convenient means for communication, and this study developed a BIMASR framework that allows for natural language input into BIM software using human voice. This framework transforms the BIM operating environment to be user-oriented, enhancing BIM interaction and use in dynamic environments.
JOURNAL OF CONSTRUCTION ENGINEERING AND MANAGEMENT
(2021)
Article
Computer Science, Information Systems
Mohammad Bani-Almarjeh, Mohamad-Bassam Kurdy
Summary: Recently, research has shown that Transformer model architecture and pre-trained Transformer-based language models perform well in natural language understanding and text generation. However, there is limited research in using these models for text generation in Arabic. This study aims to evaluate and compare different model architectures and pre-trained language models for Arabic abstractive summarization. Results show that Transformer-based models significantly outperform traditional RNN-based models and using less data. AraT5, a encoder-decoder pre-trained Transformer, is found to be more suitable for summarizing Arabic text compared to the AraBERT-initialized BERT2BERT model. Additionally, both AraT5 and AraGPT2 perform better than AraBERT in summarizing out-of-domain text.
INFORMATION PROCESSING & MANAGEMENT
(2023)
Review
Chemistry, Multidisciplinary
Nikolaos Giarelis, Charalampos Mastrokostas, Nikos Karacapilidis
Summary: Text summarization is the automatic creation of a concise and fluent summary capturing the main ideas and topics from one or multiple documents. Extractive approaches rank and combine important sentences, while abstractive approaches generate summaries with new phrases and sentences. However, both approaches lack the contextual representation needed for fluent summaries. This survey provides a comprehensive evaluation framework, including a survey of state-of-the-art approaches, a comparative evaluation using popular evaluation scores, insights on various aspects of summarization, and the release of datasets and code for reproducibility.
APPLIED SCIENCES-BASEL
(2023)
Article
Computer Science, Software Engineering
Rafael Henkin, Cagatay Turkay
Summary: This article describes two studies aiming to identify characteristics of data and charts that are relevant in supporting data analysis through language and visualization interaction. The studies reveal that participants use a variety of vocabulary to describe scatterplots, but specific concepts are preferred for higher levels of correlation.
IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS
(2022)
Article
Computer Science, Artificial Intelligence
Bing Ma, Hai Zhuge
Summary: This paper proposes a method to represent texts using common words and measure the similarity of text classes. It also introduces a bottom-up text clustering approach to construct class trees. Experimental results show that this method outperforms other algorithms in terms of classification accuracy and class tree structure. Additionally, a document summarization approach based on this method achieves good performance.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
Sonja Tilly, Markus Ebner, Giacomo Livan
Summary: This study introduces a new method in incorporating emotions from global newspapers into macroeconomic forecasts, significantly improving forecast results by focusing on the correlation between emotions and predictive variables. By utilizing emotion scores from GDELT, the effectiveness of the model is demonstrated.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Computer Science, Software Engineering
Lucas E. Resck, Jean R. Ponciano, Luis Gustavo Nonato, Jorge Poco
Summary: To reduce the number of pending cases and conflicting rulings in the Brazilian Judiciary, the National Congress allowed the Brazilian Supreme Court (STF) to create binding precedents (BPs). LegalVis is proposed as a web-based visual analytics system to assist in analyzing legal documents that cite or potentially cite a BP. Its interactive visual components provide a comprehensive exploration of data, allowing temporal patterns, filtering and grouping of relevant documents, and interpretation of model outputs.
IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS
(2023)
Article
Computer Science, Hardware & Architecture
Ahmet Toprak, Metin Turan
Summary: Many enterprise systems require extensive manual verification for document-intensive processes. To address this challenge, a general automatic or semi-automatic document verification system is proposed. In this research, a document verification model based on entities within financial documents is experimented, achieving a high accuracy rate of 88.80% and a short verification time of 2.48 s.
JOURNAL OF SUPERCOMPUTING
(2023)
Article
Computer Science, Software Engineering
Chris Bryan, Kwan-Liu Ma, Jonathan Woodring
IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS
(2017)
Article
Computer Science, Software Engineering
Chris Bryan, Gregory Guterman, Kwan-Liu Ma, Harris Lewin, Denis Larkin, Jaebum Kim, Jian Ma, Marta Farre
IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS
(2017)
Article
Computer Science, Software Engineering
Shenyu Xu, Chris Bryan, Jianping Kelvin Li, Jian Zhao, Kwan-Liu Ma
COMPUTER GRAPHICS FORUM
(2018)
Article
Computer Science, Software Engineering
Xumeng Wang, Wei Chen, Jia-Kai Chou, Chris Bryan, Huihua Guan, Wenlong Chen, Rusheng Pan, Kwan-Liu Ma
IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS
(2019)
Article
Computer Science, Software Engineering
Xumeng Wang, Chris Bryan, Yiran Li, Rusheng Pan, Yanling Liu, Wei Chen, Kwan-Liu Ma
Summary: The article introduces a solution to combat inference attacks by using a three-stage approach empowered within a visual interface, which depicts underlying inference behaviors via a Bayesian Network.
IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Aditi Mishra, Utkarsh Soni, Jinbin Huang, Chris Bryan
Summary: This paper introduces a visual analytics interface called PolicyExplainer, which allows users to directly query the reasoning behind the actions of a reinforcement learning agent. By visualizing the agent's states, policy, and rewards, PolicyExplainer provides explanations for the agent's decisions, promoting trust and understanding.
2022 IEEE 15TH PACIFIC VISUALIZATION SYMPOSIUM (PACIFICVIS 2022)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Aditi Mishra, Shashank Ginjpalli, Chris Bryan
Summary: News Kaleidoscope is a visual analytics system designed to investigate coverage diversity in event reporting. By combining backend language processing techniques with a coordinated visualization interface, News Kaleidoscope offers a tailored analytic workflow for non-experts to conduct a detailed and nuanced analysis of news coverage diversity. User studies demonstrate that News Kaleidoscope supports an effective, task-driven workflow for analyzing news coverage diversity for both journalism experts and novices, with journalism expertise influencing the user's insights and takeaways.
2022 IEEE 15TH PACIFIC VISUALIZATION SYMPOSIUM (PACIFICVIS 2022)
(2022)
Proceedings Paper
Computer Science, Software Engineering
Anjana Arunkumar, Shashank Ginjpalli, Chris Bryan
Summary: The study conducted two crowdsourced user studies to investigate how visual features of alluvial diagrams impact their consumption, and found that the importance of multiple visual features in contributing to alluvial diagram complexity depends on the type of complexity being modeled.
2021 IEEE VISUALIZATION CONFERENCE - SHORT PAPERS (VIS 2021)
(2021)
Article
Computer Science, Information Systems
Chris Bryan, Aditi Mishra, Hidekazu Shidara, Kwan-Liu Ma
VISUAL INFORMATICS
(2020)
Proceedings Paper
Computer Science, Information Systems
Jia-Kai Chou, Chris Bryan, Jing Li, Kwan-Liu Ma
2018 IEEE SYMPOSIUM ON VISUALIZATION FOR CYBER SECURITY (VIZSEC 2018)
(2018)
Proceedings Paper
Computer Science, Artificial Intelligence
Jia-Kai Chou, Chris Bryan, Kwan-Liu Ma
2017 IEEE PACIFIC VISUALIZATION SYMPOSIUM (PACIFICVIS)
(2017)
Proceedings Paper
Computer Science, Information Systems
Jacqueline Chu, Chris Bryan, Min Shih, Leonardo Ferrer, Kwan-Liu Ma
PROCEEDINGS OF THE 8TH ACM MULTIMEDIA SYSTEMS CONFERENCE (MMSYS'17)
(2017)