43-Issue 3

Permanent URI for this collection

https://diglib.eg.org/handle/10.2312/3606991

Browse

Now showing 1 - 20 of 36

Instantaneous Visual Analysis of Blood Flow in Stenoses Using Morphological Similarity
(The Eurographics Association and John Wiley & Sons Ltd., 2024) Eulzer, Pepe; Richter, Kevin; Hundertmark, Anna; Wickenhoefer, Ralph; Klingner, Carsten; Lawonn, Kai; Aigner, Wolfgang; Archambault, Daniel; Bujack, Roxana
The emergence of computational fluid dynamics (CFD) enabled the simulation of intricate transport processes, including flow in physiological structures, such as blood vessels. While these so-called hemodynamic simulations offer groundbreaking opportunities to solve problems at the clinical forefront, a successful translation of CFD to clinical decision-making is challenging. Hemodynamic simulations are intrinsically complex, time-consuming, and resource-intensive, which conflicts with the timesensitive nature of clinical workflows and the fact that hospitals usually do not have the necessary resources or infrastructure to support CFD simulations. To address these transfer challenges, we propose a novel visualization system which enables instant flow exploration without performing on-site simulation. To gain insights into the viability of the approach, we focus on hemodynamic simulations of the carotid bifurcation, which is a highly relevant arterial subtree in stroke diagnostics and prevention. We created an initial database of 120 high-resolution carotid bifurcation flow models and developed a set of similarity metrics used to place a new carotid surface model into a neighborhood of simulated cases with the highest geometric similarity. The neighborhood can be immediately explored and the flow fields analyzed.We found that if the artery models are similar enough in the regions of interest, a new simulation leads to coinciding results, allowing the user to circumvent individual flow simulations. We conclude that similarity-based visual analysis is a promising approach toward the usability of CFD in medical practice.
ProtEGOnist: Visual Analysis of Interactions in Small World Networks Using Ego-graphs
(The Eurographics Association and John Wiley & Sons Ltd., 2024) Brich, Nicolas; Harbig, Theresa A.; Witte Paz, Mathias; Nieselt, Kay; Krone, Michael; Aigner, Wolfgang; Archambault, Daniel; Bujack, Roxana
Visualizing small-world networks such as protein-protein interaction networks or social networks often leads to visual clutter and limited interpretability. To overcome these problems, we present ProtEGOnist, a visualization approach designed to explore small-world networks. ProtEGOnist visualizes networks using ego-graphs that represent local neighborhoods. Egographs are visualized in an aggregated state as a glyph where the size encodes the size of the neighborhood and in a detailed version where the original network nodes can be explored. The ego-graphs are arranged in an ego-graph network, where edges encode similarity using the Jaccard index. Our design aims to reduce visual complexity and clutter while enabling detailed exploration and facilitating the discovery of meaningful patterns. To achieve this, our approach offers a network overview using ego-graphs, a radar chart for a one-to-many ego-graph comparison and meta-data integration, and detailed ego-graph subnetworks for interactive exploration. We demonstrate the applicability of our approach on a co-author network and two different protein-protein interaction networks. A web-based prototype of ProtEGOnist can be accessed online at https://protegonist-tuevis.cs.uni-tuebingen.de/.
ChoreoVis: Planning and Assessing Formations in Dance Choreographies
(The Eurographics Association and John Wiley & Sons Ltd., 2024) Beck, Samuel; Doerr, Nina; Kurzhals, Kuno; Riedlinger, Alexander; Schmierer, Fabian; Sedlmair, Michael; Koch, Steffen; Aigner, Wolfgang; Archambault, Daniel; Bujack, Roxana
Sports visualization has developed into an active research field over the last decades. Many approaches focus on analyzing movement data recorded from unstructured situations, such as soccer. For the analysis of choreographed activities like formation dancing, however, the goal differs, as dancers follow specific formations in coordinated movement trajectories. To date, little work exists on how visual analytics methods can support such choreographed performances. To fill this gap, we introduce a new visual approach for planning and assessing dance choreographies. In terms of planning choreographies, we contribute a web application with interactive authoring tools and views for the dancers' positions and orientations, movement trajectories, poses, dance floor utilization, and movement distances. For assessing dancers' real-world movement trajectories, extracted by manual bounding box annotations, we developed a timeline showing aggregated trajectory deviations and a dance floor view for detailed trajectory comparison. Our approach was developed and evaluated in collaboration with dance instructors, showing that introducing visual analytics into this domain promises improvements in training efficiency for the future.
Improving Temporal Treemaps by Minimizing Crossings
(The Eurographics Association and John Wiley & Sons Ltd., 2024) Dobler, Alexander; Nöllenburg, Martin; Aigner, Wolfgang; Archambault, Daniel; Bujack, Roxana
Temporal trees are trees that evolve over a discrete set of time steps. Each time step is associated with a node-weighted rooted tree and consecutive trees change by adding new nodes, removing nodes, splitting nodes, merging nodes, and changing node weights. Recently, two-dimensional visualizations of temporal trees called temporal treemaps have been proposed, representing the temporal dimension on the x-axis, and visualizing the tree modifications over time as temporal edges of varying thickness. The tree hierarchy at each time step is depicted as a vertical, one-dimensional nesting relationships, similarly to standard, nontemporal treemaps. Naturally, temporal edges can cross in the visualization, decreasing readability. Heuristics were proposed to minimize such crossings in the literature, but a formal characterization and minimization of crossings in temporal treemaps was left open. In this paper, we propose two variants of defining crossings in temporal treemaps that can be combinatorially characterized. For each variant, we propose an exact optimization algorithm based on integer linear programming and heuristics based on graph drawing techniques. In an extensive experimental evaluation, we show that on the one hand the exact algorithms reduce the number of crossings by a factor of 20 on average compared to the previous algorithms. On the other hand, our new heuristics are faster by a factor of more than 100 and still reduce the number of crossings by a factor of almost three.
GerontoVis: Data Visualization at the Confluence of Aging
(The Eurographics Association and John Wiley & Sons Ltd., 2024) While, Zack; Crouser, R. Jordan; Sarvghad, Ali; Aigner, Wolfgang; Archambault, Daniel; Bujack, Roxana
Despite the explosive growth of the aging population worldwide, older adults have been largely overlooked by visualization research. This paper is a critical reflection on the underrepresentation of older adults in visualization research. We discuss why investigating visualization at the intersection of aging matters, why older adults may have been omitted from sample populations in visualization research, how aging may affect visualization use, and how this differs from traditional accessibility research. To encourage further discussion and novel scholarship in this area, we introduce GerontoVis, a term which encapsulates research and practice of data visualization design that primarily focuses on older adults. By introducing this new subfield of visualization research, we hope to shine a spotlight on this growing user population and stimulate innovation toward the development of aging-aware visualization tools. We offer a birds-eye view of the GerontoVis landscape, explore some of its unique challenges, and identify promising areas for future research.
EuroVis 2024 CGF 43-3: Frontmatter
(The Eurographics Association and John Wiley & Sons Ltd., 2024) Aigner, Wolfgang; Archambault, Daniel; Bujack, Roxana; Aigner, Wolfgang; Archambault, Daniel; Bujack, Roxana
Transmittance-based Extinction and Viewpoint Optimization
(The Eurographics Association and John Wiley & Sons Ltd., 2024) Himmler, Paul; Günther, Tobias; Aigner, Wolfgang; Archambault, Daniel; Bujack, Roxana
A long-standing challenge in volume visualization is the effective communication of relevant spatial structures that might be hidden due to occlusions. Given a scalar field that indicates the importance of every point in the domain, previous work synthesized volume visualizations by weighted averaging of samples along view rays or by optimizing a spatially-varying extinction field through an energy minimization. This energy minimization, however, did not directly measure the contribution of an individual sample to the final pixel color. In this paper, we measure the visibility of relevant structures directly by incorporating the transmittance into a non-linear energy minimization. For the first time, we not only perform a transmittance-based extinction optimization, we concurrently optimize the camera position to find ideal viewpoints. We derive the partial derivatives for the gradient-based optimization symbolically, which makes the application of automatic differentiation methods unnecessary. The transmittance-based formulation gives a direct visibility measure that is communicated to the user in order to make aware of potentially overlooked relevant structures. Our approach is compatible with any measure of importance and its versatility is demonstrated in multiple data sets.
psudo: Exploring Multi-Channel Biomedical Image Data with Spatially and Perceptually Optimized Pseudocoloring
(The Eurographics Association and John Wiley & Sons Ltd., 2024) Warchol, Simon; Troidl, Jakob; Muhlich, Jeremy; Krueger, Robert; Hoffer, John; Lin, Tica; Beyer, Johanna; Glassman, Elena; Sorger, Peter; Pfister, Hanspeter; Aigner, Wolfgang; Archambault, Daniel; Bujack, Roxana
Over the past century, multichannel fluorescence imaging has been pivotal in myriad scientific breakthroughs by enabling the spatial visualization of proteins within a biological sample. With the shift to digital methods and visualization software, experts can now flexibly pseudocolor and combine image channels, each corresponding to a different protein, to explore their spatial relationships. We thus propose psudo, an interactive system that allows users to create optimal color palettes for multichannel spatial data. In psudo, a novel optimization method generates palettes that maximize the perceptual differences between channels while mitigating confusing color blending in overlapping channels. We integrate this method into a system that allows users to explore multi-channel image data and compare and evaluate color palettes for their data. An interactive lensing approach provides on-demand feedback on channel overlap and a color confusion metric while giving context to the underlying channel values. Color palettes can be applied globally or, using the lens, to local regions of interest. We evaluate our palette optimization approach using three graphical perception tasks in a crowdsourced user study with 150 participants, showing that users are more accurate at discerning and comparing the underlying data using our approach. Additionally, we showcase psudo in a case study exploring the complex immune responses in cancer tissue data with a biologist.
CAN: Concept-aligned Neurons for Visual Comparison of Neural Networks
(The Eurographics Association and John Wiley & Sons Ltd., 2024) Li, Mingwei; Jeong, Sangwon; Liu, Shusen; Berger, Matthew; Aigner, Wolfgang; Archambault, Daniel; Bujack, Roxana
We present concept-aligned neurons, or CAN, a visualization design for comparing deep neural networks. The goal of CAN is to support users in understanding the similarities and differences between neural networks, with an emphasis on comparing neuron functionality across different models. To make this comparison intuitive, CAN uses concept-based representations of neurons to visually align models in an interpretable manner. A key feature of CAN is the hierarchical organization of concepts, which permits users to relate sets of neurons at different levels of detail. CAN's visualization is designed to help compare the semantic coverage of neurons, as well as assess the distinctiveness, redundancy, and multi-semantic alignment of neurons or groups of neurons, all at different concept granularity. We demonstrate the generality and effectiveness of CAN by comparing models trained on different datasets, neural networks with different architectures, and models trained for different objectives, e.g. adversarial robustness, and robustness to out-of-distribution data.
Deconstructing Human-AI Collaboration: Agency, Interaction, and Adaptation
(The Eurographics Association and John Wiley & Sons Ltd., 2024) Holter, Steffen; El-Assady, Mennatallah; Aigner, Wolfgang; Archambault, Daniel; Bujack, Roxana
As full AI-based automation remains out of reach in most real-world applications, the focus has instead shifted to leveraging the strengths of both human and AI agents, creating effective collaborative systems. The rapid advances in this area have yielded increasingly more complex systems and frameworks, while the nuance of their characterization has gotten more vague. Similarly, the existing conceptual models no longer capture the elaborate processes of these systems nor describe the entire scope of their collaboration paradigms. In this paper, we propose a new unified set of dimensions through which to analyze and describe human- AI systems. Our conceptual model is centered around three high-level aspects - agency, interaction, and adaptation - and is developed through a multi-step process. Firstly, an initial design space is proposed by surveying the literature and consolidating existing definitions and conceptual frameworks. Secondly, this model is iteratively refined and validated by conducting semistructured interviews with nine researchers in this field. Lastly, to illustrate the applicability of our design space, we utilize it to provide a structured description of selected human-AI systems.
Should I make it round? Suitability of circular and linear layouts for comparative tasks with matrix and connective data
(The Eurographics Association and John Wiley & Sons Ltd., 2024) Ståhlbom, Emilia; Molin, Jesper; Ynnerman, Anders; Lundström, Claes; Aigner, Wolfgang; Archambault, Daniel; Bujack, Roxana
Visual representations based on circular shapes are frequently used in visualization applications. One example are circos plots within bioinformatics, which bend graphs into a wheel of information with connective lines running through the center like spokes. The results are aesthetically appealing and impressive visualizations that fit long data sequences into a small quadratic space. However, the authors' experiences are that when asked, a visualization researcher would generally advise against making visualizations with radial layouts. Upon reviewing the literature we found that there is evidence that circular layouts are preferable in some cases, but we found no clear evidence for what layout is preferable for matrices and connective data in particular, which both are common data types in circos plots. In this work, we thus performed a user study to compare circular and linear layouts. The tasks are inspired by genomics data, but our results generalize to many other application areas, involving comparison and connective data. To build the prototype we utilized Gosling, a grammar for visualizing genomics data. We contribute empirical evidence on the suitedness of linear versus circular layouts, adding to the specific and general knowledge concerning perception of circular graphs. In addition, we contribute a case study evaluation of the grammar Gosling as a rapid prototyping language, confirming its utility and providing guidance on suitable areas for future development.
RouteVis: Quantitative Visual Analytics of Various Factors to Understand Route Choice Preferences
(The Eurographics Association and John Wiley & Sons Ltd., 2024) Lv, Cheng; Zhang, Huijie; Lin, Yiming; Dong, Jialu; Tian, Liang; Aigner, Wolfgang; Archambault, Daniel; Bujack, Roxana
Analyzing the preference of route choice not only facilitates the understanding of individuals' decision-making behavior, but also provides valuable information for improving traffic management strategies. As the layout of the road network, the variability of individual preferences and the spatial distribution of origins and destinations all play a role in route choice, it is a great challenge to reveal the interplay of such numerous complex factors. In this paper, we propose RouteVis, an interactive visual analytics system that enables traffic analysts to gain insight into what factors drive individuals to choose a specific route. To uncover the relationship between route choice and influencing factors, we design a quantitative analytical framework that supports analysts in conducting closed-loop analysis of various factors, i.e., data preprocessing, route identification, and the quantification of influence and contribution. Furthermore, given the multidimensional and spatio-temporal characteristics of the analysis results, we customize a set of coordinated views and visual designs to provide an intuitive presentation of the factors affecting people's travels, thus freeing analysts from tedious repetitive tasks and significantly enhancing work efficiency. Two typical usage scenarios and expert feedback on the system's functionality demonstrate that RouteVis can greatly enhance the capabilities of understanding the travel status.
An Experimental Evaluation of Viewpoint-Based 3D Graph Drawing
(The Eurographics Association and John Wiley & Sons Ltd., 2024) Wageningen, Simon van; Mchedlidze, Tamara; Telea, Alexandru; Aigner, Wolfgang; Archambault, Daniel; Bujack, Roxana
Node-link diagrams are a widely used metaphor for creating visualizations of relational data. Most frequently, such techniques address creating 2D graph drawings, which are easy to use on computer screens and in print. In contrast, 3D node-link graph visualizations are far less used, as they have many known limitations and comparatively few well-understood advantages. A key issue here is that such 3D visualizations require users to select suitable viewpoints. We address this limitation by studying the ability of layout techniques to produce high-quality views of 3D graph drawings. For this, we perform a thorough experimental evaluation, comparing 3D graph drawings, rendered from a covering sampling of all viewpoints, with their 2D counterparts across various state-of-the-art node-link drawing algorithms, graph families, and quality metrics. Our results show that, depending on the graph family, 3D node-link diagrams can contain a many viewpoints that yield 2D visualizations that are of higher quality than those created by directly using 2D node-link diagrams. This not only sheds light on the potential of 3D node-link diagrams but also gives a simple approach to produce high-quality 2D node-link diagrams.
HORA 3D: Personalized Flood Risk Visualization as an Interactive Web Service
(The Eurographics Association and John Wiley & Sons Ltd., 2024) Rauer-Zechmeister, Silvana; Cornel, Daniel; Sadransky, Bernhard; Horváth, Zsolt; Konev, Artem; Buttinger-Kreuzhuber, Andreas; Heidrich, Raimund; Blöschl, Günter; Gröller, Eduard; Waser, Jürgen; Aigner, Wolfgang; Archambault, Daniel; Bujack, Roxana
We propose an interactive web-based application to inform the general public about personal flood risks. Flooding is the natural hazard affecting most people worldwide. Protection against flooding is not limited to mitigation measures, but also includes communicating its risks to affected individuals to raise awareness and preparedness for its adverse effects. Until now, this is mostly done with static and indiscriminate 2D maps of the water depth. These flood hazard maps can be difficult to interpret and the user has to derive a personal flood risk based on prior knowledge. In addition to the hazard, the flood risk has to consider the exposure of the own house and premises to high water depths and flow velocities as well as the vulnerability of particular parts. Our application is centered around an interactive personalized visualization to raise awareness of these risk factors for an object of interest. We carefully extract and show only the relevant information from large precomputed flood simulation and geospatial data to keep the visualization simple and comprehensible. To achieve this goal, we extend various existing approaches and combine them with new real-time visualization and interaction techniques in 3D. A new view-dependent focus+context design guides user attention and supports an intuitive interpretation of the visualization to perform predefined exploration tasks. HORA 3D enables users to individually inform themselves about their flood risks. We evaluated the user experience through a broad online survey with 87 participants of different levels of expertise, who rated the helpfulness of the application with 4.7 out of 5 on average.
AutoVizuA11y: A Tool to Automate Screen Reader Accessibility in Charts
(The Eurographics Association and John Wiley & Sons Ltd., 2024) Duarte, Diogo; Costa, Rita; Bizarro, Pedro; Duarte, Carlos; Aigner, Wolfgang; Archambault, Daniel; Bujack, Roxana
Charts remain widely inaccessible on the web for users of assistive technologies like screen readers. This is, in part, due to data visualization experts still lacking the experience, knowledge, and time to consistently implement accessible charts. As a result, screen reader users are prevented from accessing information and are forced to resort to tabular alternatives (if available), limiting the insights that they can gather. We worked with both groups to develop AutoVizuA11y, a tool that automates the addition of accessible features to web-based charts. It generates human-like descriptions of the data using a large language model, calculates statistical insights from the data, and provides keyboard navigation between multiple charts and underlying elements. Fifteen screen reader users interacted with charts made accessible with AutoVizuA11y in a usability test, thirteen of which praised the tool for its intuitive design, short learning curve, and rich information. On average, they took 66 seconds to complete each of the eight analytical tasks presented and achieved a success rate of 89%. Through a SUS questionnaire, the participants gave AutoVizuA11y an ''Excellent'' score-83.5/100 points. We also gathered feedback from two data visualization experts who used the tool. They praised the tool availability, ease of use and functionalities, and provided feedback to add AutoVizuA11y support for other technologies in the future.
InverseVis: Revealing the Hidden with Curved Sphere Tracing
(The Eurographics Association and John Wiley & Sons Ltd., 2024) Lawonn, Kai; Meuschke, Monique; Günther, Tobias; Aigner, Wolfgang; Archambault, Daniel; Bujack, Roxana
Exploratory analysis of scalar fields on surface meshes presents significant challenges in identifying and visualizing important regions, particularly on the surface's backside. Previous visualization methods achieved only a limited visibility of significant features, i.e., regions with high or low scalar values, during interactive exploration. In response to this, we propose a novel technique, InverseVis, which leverages curved sphere tracing and uses the otherwise unused space to enhance visibility. Our approach combines direct and indirect rendering, allowing camera rays to wrap around the surface and reveal information from the backside. To achieve this, we formulate an energy term that guides the image synthesis in previously unused space, highlighting the most important regions of the backside. By quantifying the amount of visible important features, we optimize the camera position to maximize the visibility of the scalar field on both the front and backsides. InverseVis is benchmarked against state-of-the-art methods and a derived technique, showcasing its effectiveness in revealing essential features and outperforming existing approaches.
AVA: Towards Autonomous Visualization Agents through Visual Perception-Driven Decision-Making
(The Eurographics Association and John Wiley & Sons Ltd., 2024) Liu, Shusen; Miao, Haichao; Li, Zhimin; Olson, Matthew; Pascucci, Valerio; Bremer, Peer-Timo; Aigner, Wolfgang; Archambault, Daniel; Bujack, Roxana
With recent advances in multi-modal foundation models, the previously text-only large language models (LLM) have evolved to incorporate visual input, opening up unprecedented opportunities for various applications in visualization. Compared to existing work on LLM-based visualization works that generate and control visualization with textual input and output only, the proposed approach explores the utilization of the visual processing ability of multi-modal LLMs to develop Autonomous Visualization Agents (AVAs) that can evaluate the generated visualization and iterate on the result to accomplish user-defined objectives defined through natural language. We propose the first framework for the design of AVAs and present several usage scenarios intended to demonstrate the general applicability of the proposed paradigm. Our preliminary exploration and proof-of-concept agents suggest that this approach can be widely applicable whenever the choices of appropriate visualization parameters require the interpretation of previous visual output. Our study indicates that AVAs represent a general paradigm for designing intelligent visualization systems that can achieve high-level visualization goals, which pave the way for developing expert-level visualization agents in the future.
Generating Euler Diagrams Through Combinatorial Optimization
(The Eurographics Association and John Wiley & Sons Ltd., 2024) Rottmann, Peter; Rodgers, Peter; Yan, Xinyuan; Archambault, Daniel; Wang, Bei; Haunert, Jan-Henrik; Aigner, Wolfgang; Archambault, Daniel; Bujack, Roxana
Can a given set system be drawn as an Euler diagram? We present the first method that correctly decides this question for arbitrary set systems if the Euler diagram is required to represent each set with a single connected region. If the answer is yes, our method constructs an Euler diagram. If the answer is no, our method yields an Euler diagram for a simplified version of the set system, where a minimum number of set elements have been removed. Further, we integrate known wellformedness criteria for Euler diagrams as additional optimization objectives into our method. Our focus lies on the computation of a planar graph that is embedded in the plane to serve as the dual graph of the Euler diagram. Since even a basic version of this problem is known to be NP-hard, we choose an approach based on integer linear programming (ILP), which allows us to compute optimal solutions with existing mathematical solvers. For this, we draw upon previous research on computing planar supports of hypergraphs and adapt existing ILP building blocks for contiguity-constrained spatial unit allocation and the maximum planar subgraph problem. To generate Euler diagrams for large set systems, for which the proposed simplification through element removal becomes indispensable, we also present an efficient heuristic. We report on experiments with data from MovieDB and Twitter. Over all examples, including 850 non-trivial instances, our exact optimization method failed only for one set system to find a solution without removing a set element. However, with the removal of only a few set elements, the Euler diagrams can be substantially improved with respect to our wellformedness criteria.
Guided By AI: Navigating Trust, Bias, and Data Exploration in AI-Guided Visual Analytics
(The Eurographics Association and John Wiley & Sons Ltd., 2024) Ha, Sunwoo; Monadjemi, Shayan; Ottley, Alvitta; Aigner, Wolfgang; Archambault, Daniel; Bujack, Roxana
The increasing integration of artificial intelligence (AI) in visual analytics (VA) tools raises vital questions about the behavior of users, their trust, and the potential of induced biases when provided with guidance during data exploration. We present an experiment where participants engaged in a visual data exploration task while receiving intelligent suggestions supplemented with four different transparency levels. We also modulated the difficulty of the task (easy or hard) to simulate a more tedious scenario for the analyst. Our results indicate that participants were more inclined to accept suggestions when completing a more difficult task despite the AI's lower suggestion accuracy. Moreover, the levels of transparency tested in this study did not significantly affect suggestion usage or subjective trust ratings of the participants. Additionally, we observed that participants who utilized suggestions throughout the task explored a greater quantity and diversity of data points. We discuss these findings and the implications of this research for improving the design and effectiveness of AI-guided VA tools.
Visual Analytics for Fine-grained Text Classification Models and Datasets
(The Eurographics Association and John Wiley & Sons Ltd., 2024) Battogtokh, Munkhtulga; Xing, Yiwen; Davidescu, Cosmin; Abdul-Rahman, Alfie; Luck, Michael; Borgo, Rita; Aigner, Wolfgang; Archambault, Daniel; Bujack, Roxana
In natural language processing (NLP), text classification tasks are increasingly fine-grained, as datasets are fragmented into a larger number of classes that are more difficult to differentiate from one another. As a consequence, the semantic structures of datasets have become more complex, and model decisions more difficult to explain. Existing tools, suited for coarse-grained classification, falter under these additional challenges. In response to this gap, we worked closely with NLP domain experts in an iterative design-and-evaluation process to characterize and tackle the growing requirements in their workflow of developing fine-grained text classification models. The result of this collaboration is the development of SemLa, a novel Visual Analytics system tailored for 1) dissecting complex semantic structures in a dataset when it is spatialized in model embedding space, and 2) visualizing fine-grained nuances in the meaning of text samples to faithfully explain model reasoning. This paper details the iterative design study and the resulting innovations featured in SemLa. The final design allows contrastive analysis at different levels by unearthing lexical and conceptual patterns including biases and artifacts in data. Expert feedback on our final design and case studies confirm that SemLa is a useful tool for supporting model validation and debugging as well as data annotation.

Browse

Browsing 43-Issue 3 by Issue Date

Results Per Page

Sort Options