Yi Guo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yi Guo has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Nan Cao
College of Design and Innovation, Tongji University, Shanghai, China
4 shared publications - Qing Chen
Intelligent Big Data Visualization Lab, Tongji University, Shanghai, China
4 shared publications - Danqing Shi
Aalto University, Helsinki, Finland
3 shared publications - Daniel Weiskopf
University of Stuttgart Germany
2 shared publications - Yanqiu Wu
Tongji University, Shanghai, China
2 shared publications - Haoyang Li
Renmin University of China, Beijing, China
1 shared publication
Latest Publications
- Top Cited PapersOpen Access
- 9 January 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Interactive Intelligent Systems
- Vol. 16 (1) , 1-26
Urania: Visualizing Data Analysis Pipelines for Natural Language-Based Data Exploration
Exploratory Data Analysis (EDA) is an essential yet tedious process for examining a new dataset. To facilitate it, Natural Language Interfaces (NLIs) can help people intuitively explore the dataset via data-oriented questions. However, existing NLIs primarily focus on providing accurate answers to questions, with few offering explanations or presentations of the data analysis pipeline used to uncover the answer. Such presentations are crucial for EDA as they enhance the interpretability and reliability of the answer, while also helping users understand the analysis process and derive insights. To fill this gap, we introduce Urania, a natural language interactive system that can visualize the data analysis pipelines used to resolve input questions. It integrates a NLI that allows users to explore data via questions, and a novel data-aware question decomposition algorithm that resolves each input question into a data analysis pipeline. This pipeline is visualized in the form of a datamation, with animated presentations of analysis operations and their corresponding data changes. Through two quantitative experiments and expert interviews, we demonstrated that our data-aware question decomposition algorithm shows competitive performance compared to existing techniques in terms of execution accuracy, and that Urania can help people explore datasets better. In the end, we discuss the observations from the studies and the potential future works.
- 9 January 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Interactive Intelligent Systems
- Vol. 16 (1) , 1-26
Top Cited PapersOpen AccessUrania: Visualizing Data Analysis Pipelines for Natural Language-Based Data Exploration
Exploratory Data Analysis (EDA) is an essential yet tedious process for examining a new dataset. To facilitate it, Natural Language Interfaces (NLIs) can help people intuitively explore the dataset via data-oriented questions. However, existing NLIs primarily focus on providing accurate answers to questions, with few offering explanations or presentations of the data analysis pipeline used to uncover the answer. Such presentations are crucial for EDA as they enhance the interpretability and reliability of the answer, while also helping users understand the analysis process and derive insights. To fill this gap, we introduce Urania, a natural language interactive system that can visualize the data analysis pipelines used to resolve input questions. It integrates a NLI that allows users to explore data via questions, and a novel data-aware question decomposition algorithm that resolves each input question into a data analysis pipeline. This pipeline is visualized in the form of a datamation, with animated presentations of analysis operations and their corresponding data changes. Through two quantitative experiments and expert interviews, we demonstrated that our data-aware question decomposition algorithm shows competitive performance compared to existing techniques in terms of execution accuracy, and that Urania can help people explore datasets better. In the end, we discuss the observations from the studies and the potential future works.
- Open Access
- 22 April 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Interactive Intelligent Systems
- Vol. 14 (2) , 1-24
Talk2Data: A Natural Language Interface for Exploratory Visual Analysis via Question Decomposition
Through a natural language interface (NLI) for exploratory visual analysis, users can directly “ask” analytical questions about the given tabular data. This process greatly improves user experience and lowers the technical barriers of data analysis. Existing techniques focus on generating a visualization from a concrete question. However, complex questions, requiring multiple data queries and visualizations to answer, are frequently asked in data exploration and analysis, which cannot be easily solved with the existing techniques. To address this issue, in this article, we introduce Talk2Data, a natural language interface for exploratory visual analysis that supports answering complex questions. It leverages an advanced deep-learning model to resolve complex questions into a series of simple questions that could gradually elaborate on the users’ requirements. To present answers, we design a set of annotated and captioned visualizations to represent the answers in a form that supports interpretation and narration. We conducted an ablation study and a controlled user study to evaluate the Talk2Data’s effectiveness and usefulness.
- 22 April 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Interactive Intelligent Systems
- Vol. 14 (2) , 1-24
Open AccessTalk2Data: A Natural Language Interface for Exploratory Visual Analysis via Question Decomposition
Through a natural language interface (NLI) for exploratory visual analysis, users can directly “ask” analytical questions about the given tabular data. This process greatly improves user experience and lowers the technical barriers of data analysis. Existing techniques focus on generating a visualization from a concrete question. However, complex questions, requiring multiple data queries and visualizations to answer, are frequently asked in data exploration and analysis, which cannot be easily solved with the existing techniques. To address this issue, in this article, we introduce Talk2Data, a natural language interface for exploratory visual analysis that supports answering complex questions. It leverages an advanced deep-learning model to resolve complex questions into a series of simple questions that could gradually elaborate on the users’ requirements. To present answers, we design a set of annotated and captioned visualizations to represent the answers in a form that supports interpretation and narration. We conducted an ablation study and a controlled user study to evaluate the Talk2Data’s effectiveness and usefulness.
- 29 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 31 (4) , 2167-2181
Chart2Vec: A Universal Embedding of Context-Aware Visualizations
The advances in AI-enabled techniques have accelerated the creation and automation of visualizations in the past decade. However, presenting visualizations in a descriptive and generative format remains a challenge. Moreover, current visualization embedding methods focus on standalone visualizations, neglecting the importance of contextual information for multi-view visualizations. To address this issue, we propose a new representation model, Chart2Vec, to learn a universal embedding of visualizations with context-aware information. Chart2Vec aims to support a wide range of downstream visualization tasks such as recommendation and storytelling. Our model considers both structural and semantic information of visualizations in declarative specifications. To enhance the context-aware capability, Chart2Vec employs multi-task learning on both supervised and unsupervised tasks concerning the cooccurrence of visualizations. We evaluate our method through an ablation study, a user study, and a quantitative comparison. The results verified the consistency of our embedding method with human cognition and showed its advantages over existing methods.
- 29 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 31 (4) , 2167-2181
Chart2Vec: A Universal Embedding of Context-Aware Visualizations
The advances in AI-enabled techniques have accelerated the creation and automation of visualizations in the past decade. However, presenting visualizations in a descriptive and generative format remains a challenge. Moreover, current visualization embedding methods focus on standalone visualizations, neglecting the importance of contextual information for multi-view visualizations. To address this issue, we propose a new representation model, Chart2Vec, to learn a universal embedding of visualizations with context-aware information. Chart2Vec aims to support a wide range of downstream visualization tasks such as recommendation and storytelling. Our model considers both structural and semantic information of visualizations in declarative specifications. To enhance the context-aware capability, Chart2Vec employs multi-task learning on both supervised and unsupervised tasks concerning the cooccurrence of visualizations. We evaluate our method through an ablation study, a user study, and a quantitative comparison. The results verified the consistency of our embedding method with human cognition and showed its advantages over existing methods.
- Open Access
- 28 August 2023
- Published by MDPI AG in Applied Sciences
- Vol. 13 (17) , 9709
Datamator: An Authoring Tool for Creating Datamations via Data Query Decomposition
Datamation is designed to animate an analysis pipeline step by step, serving as an intuitive and efficient method for interpreting data analysis outcomes and facilitating easy sharing with others. However, the creation of a datamation is a difficult task that demands expertise in diverse skills. To simplify this task, we introduce Datamator, a language-oriented authoring tool developed to support datamation generation. In this system, we develop a data query analyzer that enables users to generate an initial datamation effortlessly by inputting a data question in natural language. Then, the datamation is displayed in an interactive editor that affords users the ability to both edit the analysis progression and delve into the specifics of each step undertaken. Notably, the Datamator incorporates a novel calibration network that is able to optimize the outputs of the query decomposition network using a small amount of user feedback. To demonstrate the effectiveness of Datamator, we conduct a series of evaluations including performance validation, a controlled user study, and expert interviews.
- 28 August 2023
- Published by MDPI AG in Applied Sciences
- Vol. 13 (17) , 9709
Open AccessDatamator: An Authoring Tool for Creating Datamations via Data Query Decomposition
Datamation is designed to animate an analysis pipeline step by step, serving as an intuitive and efficient method for interpreting data analysis outcomes and facilitating easy sharing with others. However, the creation of a datamation is a difficult task that demands expertise in diverse skills. To simplify this task, we introduce Datamator, a language-oriented authoring tool developed to support datamation generation. In this system, we develop a data query analyzer that enables users to generate an initial datamation effortlessly by inputting a data question in natural language. Then, the datamation is displayed in an interactive editor that affords users the ability to both edit the analysis progression and delve into the specifics of each step undertaken. Notably, the Datamator incorporates a novel calibration network that is able to optimize the outputs of the query decomposition network using a small amount of user feedback. To demonstrate the effectiveness of Datamator, we conduct a series of evaluations including performance validation, a controlled user study, and expert interviews.