Position within the page tree

Tanja Munz-Körner

Dipl.-Inf., M. Sc.

Doctoral Researcher
Institute for Visualisation and Interactive Systems (VIS)
Weiskopf Group

Contact

+49 711 685 88632
Email

Universitätsstraße 38
70569 Stuttgart
Deutschland
Room: 1.369

Publications

Publications:

2022
1. Munz, Tanja ; Väth, Dirk ; Kuznecov, Paul ; Vu, Ngoc Thang ; Weiskopf, Daniel: Visualization-based improvement of neural machine translation. In: Computers & Graphics, Computers & Graphics. Bd. 103 (2022), S. 45–60
  - BibTeX
  - Link
  BibTeX
  @article{munz2022nmtvis, abstract = {We introduce a novel visual-interactive approach for analyzing, understanding, and correcting neural machine translation. Our system supports users in automatically translating documents using neural machine translation and identifying and correcting possible erroneous translations. User corrections can then be used to fine-tune the neural machine translation model and automatically improve the whole document. While translation results of neural machine translation can be impressive, there are still many challenges such as over- and under-translation, domain-specific terminology, and handling long sentences, making it necessary for users to verify translation results. Our system aims at supporting users in this task. Our visual analytics approach combines several visualization techniques in an interactive system. A parallel coordinates plot with multiple metrics related to translation quality can be used to find, filter, and select translations that might contain errors. An interactive beam search visualization and graph- or matrix-based visualizations for attention weights can be used for post-editing and understanding machine-generated translations. The machine translation model is updated from user corrections to improve the translation quality of the whole document. We designed our approach for an LSTM-based translation model and extended it to also include the Transformer architecture. We show for representative examples possible mistranslations and how to use our system to deal with them. A user study revealed that many participants favor such a system over manual text-based translation, especially for translating large documents. Furthermore, we performed quantitative computer-based experiments that show that our system can be used to improve translation quality and reduce post-editing efforts for domain-specific documents.}, author = {Munz, Tanja and Väth, Dirk and Kuznecov, Paul and Vu, Ngoc Thang and Weiskopf, Daniel}, doi = {https://doi.org/10.1016/j.cag.2021.12.003}, issn = {0097-8493}, journal = {Computers & Graphics}, pages = {45-60}, title = {Visualization-based improvement of neural machine translation}, url = {https://www.sciencedirect.com/science/article/pii/S0097849321002594}, volume = 103, year = 2022 }
  Link
  https://www.sciencedirect.com/science/article/pii/S0097849321002594
2021
1. Garcia, Rafael ; Munz, Tanja ; Weiskopf, Daniel: Visual analytics tool for the interpretation of hidden states in recurrent neural networks. In: Visual Computing for Industry, Biomedicine, and Art, Visual Computing for Industry, Biomedicine, and Art. Bd. 4 (2021), Nr. 24
  - BibTeX
  - Link
  BibTeX
  @article{vciba2021hiddenStates, abstract = {In this paper, we introduce a visual analytics approach aimed at helping machine learning experts analyze the hidden states of layers in recurrent neural networks. Our technique allows the user to interactively inspect how hidden states store and process information throughout the feeding of an input sequence into the network. The technique can help answer questions, such as which parts of the input data have a higher impact on the prediction and how the model correlates each hidden state configuration with a certain output. Our visual analytics approach comprises several components: First, our input visualization shows the input sequence and how it relates to the output (using color coding). In addition, hidden states are visualized through a nonlinear projection into a 2-D visualization space using t-distributed stochastic neighbor embedding to understand the shape of the space of the hidden states. Trajectories are also employed to show the details of the evolution of the hidden state configurations. Finally, a time-multi-class heatmap matrix visualizes the evolution of the expected predictions for multi-class classifiers, and a histogram indicates the distances between the hidden states within the original space. The different visualizations are shown simultaneously in multiple views and support brushing-and-linking to facilitate the analysis of the classifications and debugging for misclassified input sequences. To demonstrate the capability of our approach, we discuss two typical use cases for long short-term memory models applied to two widely used natural language processing datasets.}, author = {Garcia, Rafael and Munz, Tanja and Weiskopf, Daniel}, doi = {10.1186/s42492-021-00090-0}, issn = {25244442}, journal = {Visual Computing for Industry, Biomedicine, and Art}, number = 24, refid = {Garcia2021}, title = {Visual analytics tool for the interpretation of hidden states in recurrent neural networks}, url = {https://doi.org/10.1186/s42492-021-00090-0}, volume = 4, year = 2021 }
  Link
  https://doi.org/10.1186/s42492-021-00090-0
2. Munz, Tanja ; Väth, Dirk ; Kuznecov, Paul ; Vu, Thang ; Weiskopf, Daniel: Visual-Interactive Neural Machine Translation. In: Graphics Interface 2021, Graphics Interface 2021, 2021
  - BibTeX
  - Link
  BibTeX
  @inproceedings{gi2021nmtvis, author = {Munz, Tanja and Väth, Dirk and Kuznecov, Paul and Vu, Thang and Weiskopf, Daniel}, booktitle = {Graphics Interface 2021}, title = {Visual-Interactive Neural Machine Translation}, url = {https://openreview.net/forum?id=DQHaCvN9xd}, year = 2021 }
  Link
  https://openreview.net/forum?id=DQHaCvN9xd
2020
1. Munz, Tanja ; Schaefer, Noel ; Blascheck, Tanja ; Kurzhals, Kuno ; Zhang, Eugene ; Weiskopf, Daniel: Demo of a Visual Gaze Analysis System for Virtual Board Games. In: ACM Symposium on Eye Tracking Research and Applications, ACM Symposium on Eye Tracking Research and Applications. Stuttgart, Germany : Association for Computing Machinery, 2020
  - BibTeX
  BibTeX
  @inproceedings{10.1145/3379157.3391985, articleno = {2}, author = {Munz, Tanja and Schaefer, Noel and Blascheck, Tanja and Kurzhals, Kuno and Zhang, Eugene and Weiskopf, Daniel}, booktitle = {ACM Symposium on Eye Tracking Research and Applications}, doi = {10.1145/3379157.3391985}, location = {Stuttgart, Germany}, numpages = {3}, publisher = {Association for Computing Machinery}, series = {ETRA ’20 Adjunct}, title = {Demo of a Visual Gaze Analysis System for Virtual Board Games}, year = 2020 }
2. Heyen, Frank ; Munz, Tanja ; Neumann, Michael ; Ortega, Daniel ; Vu, Ngoc Thang ; Weiskopf, Daniel ; Sedlmair, Michael: ClaVis: An Interactive Visual Comparison System for Classifiers. In: Proceedings of the International Conference on Advanced Visual Interfaces (AVI), Proceedings of the International Conference on Advanced Visual Interfaces (AVI) : ACM, 2020 — ISBN 9781450375351, S. 9:1-9:9
  - BibTeX
  - Link
  BibTeX
  @inproceedings{10.1145/3399715.3399814, abstract = {We propose ClaVis, a visual analytics system for comparative analysis of classification models. ClaVis allows users to visually compare the performance and behavior of tens to hundreds of classifiers trained with different hyperparameter configurations. Our approach is plugin-based and classifier-agnostic and allows users to add their own datasets and classifier implementations. It provides multiple visualizations, including a multivariate ranking, a similarity map, a scatterplot that reveals correlations between parameters and scores, and a training history chart. We demonstrate the effectivity of our approach in multiple case studies for training classification models in the domain of natural language processing.}, author = {Heyen, Frank and Munz, Tanja and Neumann, Michael and Ortega, Daniel and Vu, Ngoc Thang and Weiskopf, Daniel and Sedlmair, Michael}, booktitle = {Proceedings of the International Conference on Advanced Visual Interfaces (AVI)}, doi = {10.1145/3399715.3399814}, isbn = {9781450375351}, pages = {9:1-9:9}, publisher = {ACM}, series = {AVI '20}, title = {ClaVis: An Interactive Visual Comparison System for Classifiers}, url = {https://doi.org/10.1145/3399715.3399814}, year = 2020 }
  Link
  https://doi.org/10.1145/3399715.3399814
3. Munz, Tanja ; Schäfer, Noel ; Blascheck, Tanja ; Kurzhals, Kuno ; Zhang, Eugene ; Weiskopf, Daniel: Comparative Visual Gaze Analysis for Virtual Board Games. In: The 13th International Symposium on Visual Information Communication and Interaction (VINCI 2020), The 13th International Symposium on Visual Information Communication and Interaction (VINCI 2020). (2020)
  - BibTeX
  BibTeX
  @article{vinci2020boardGames, author = {Munz, Tanja and Schäfer, Noel and Blascheck, Tanja and Kurzhals, Kuno and Zhang, Eugene and Weiskopf, Daniel}, doi = {10.1145/3430036.3430038}, journal = {The 13th International Symposium on Visual Information Communication and Interaction (VINCI 2020)}, title = {Comparative Visual Gaze Analysis for Virtual Board Games}, year = 2020 }
2019
1. Munz, Tanja ; Chuang, Lewis L. ; Pannasch, Sebastian ; Weiskopf, Daniel: VisME: Visual microsaccades explorer. In: Journal of Eye Movement Research, Journal of Eye Movement Research. Bd. 12 (2019), Nr. 6
  - BibTeX
  - Link
  BibTeX
  @article{munz2019visme, abstractnote = {<p>This work presents a visual analytics approach to explore microsaccade distributions in high-frequency eye tracking data. Research studies often apply filter algorithms and parameter values for microsaccade detection. Even when the same algorithms are employed, different parameter values might be adopted across different studies. In this paper, we present a visual analytics system (VisME) to promote reproducibility in the data analysis of microsaccades. It allows users to interactively vary the parametric values for microsaccade filters and evaluate the resulting influence on microsaccade behavior across individuals and on a group level. In particular, we exploit brushing-and-linking techniques that allow the microsaccadic properties of space, time, and movement direction to be extracted, visualized, and compared across multiple views. We demonstrate in a case study the use of our visual analytics system on data sets collected from natural scene viewing and show in a qualitative usability study the usefulness of this approach for eye tracking researchers. We believe that interactive tools such as VisME will promote greater transparency in eye movement research by providing researchers with the ability to easily understand complex eye tracking data sets; such tools can also serve as teaching systems. VisME is provided as open source software.</p&gt;}, author = {Munz, Tanja and Chuang, Lewis L. and Pannasch, Sebastian and Weiskopf, Daniel}, doi = {10.16910/jemr.12.6.5}, journal = {Journal of Eye Movement Research}, month = {12}, number = 6, title = {VisME: Visual microsaccades explorer}, url = {https://bop.unibe.ch/JEMR/article/view/JEMR.12.6.5}, volume = 12, year = 2019 }
  Link
  https://bop.unibe.ch/JEMR/article/view/JEMR.12.6.5
2. Munz, Tanja ; Burch, Michael ; van Benthem, Toon ; Poels, Yoeri ; Beck, Fabian ; Weiskopf, Daniel: Overlap-Free Drawing of Generalized Pythagoras Trees for Hierarchy Visualization. In: 2019 IEEE Visualization Conference (VIS), 2019 IEEE Visualization Conference (VIS), 2019, S. 251–255
  - BibTeX
  - Link
  BibTeX
  @inproceedings{8933606, abstract = {Generalized Pythagoras trees were developed for visualizing hierarchical data, producing organic, fractal-like representations. However, the drawback of the original layout algorithm is visual overlap of tree branches. To avoid such overlap, we introduce an adapted drawing algorithm using ellipses instead of circles to recursively place tree nodes representing the subhierarchies. Our technique is demonstrated by resolving overlap in diverse real-world and generated datasets, while comparing the results to the original approach.}, author = {Munz, Tanja and Burch, Michael and van Benthem, Toon and Poels, Yoeri and Beck, Fabian and Weiskopf, Daniel}, booktitle = {2019 IEEE Visualization Conference (VIS)}, doi = {10.1109/VISUAL.2019.8933606}, month = {10}, pages = {251-255}, title = {Overlap-Free Drawing of Generalized Pythagoras Trees for Hierarchy Visualization}, url = {https://ieeexplore.ieee.org/document/8933606/}, year = 2019 }
  Link
  https://ieeexplore.ieee.org/document/8933606/
2016
1. Beck, Fabian ; Burch, Michael ; Munz, Tanja ; Di Silvestro, Lorenzo ; Weiskopf, Daniel: Generalized Pythagoras Trees: A Fractal Approach to Hierarchy Visualization. In: Computer Vision, Imaging and Computer Graphics - Theory and Applications, VISIGRAPP 2014, Revised Selected Papers, Computer Vision, Imaging and Computer Graphics - Theory and Applications, VISIGRAPP 2014, Revised Selected Papers : Springer, 2016
  - BibTeX
  - Link
  BibTeX
  @inbook{6180bb801e1640dcb16ab4128586a17e, author = {Beck, Fabian and Burch, Michael and Munz, Tanja and Di Silvestro, Lorenzo and Weiskopf, Daniel}, booktitle = {Computer Vision, Imaging and Computer Graphics - Theory and Applications, VISIGRAPP 2014, Revised Selected Papers}, publisher = {Springer}, title = {Generalized Pythagoras Trees: A Fractal Approach to Hierarchy Visualization}, url = {http://dx.doi.org/10.1007/978-3-319-25117-2_8}, year = 2016 }
  Link
  http://dx.doi.org/10.1007/978-3-319-25117-2_8
2015
1. Burch, Michael ; Munz, Tanja ; Weiskopf, Daniel: Edge-stacked Timelines for Visualizing Dynamic Weighted Digraphs. In: Braz, J. ; Kerren, A. ; Linsen, L. (Hrsg.) ; Braz, J. ; Kerren, A. ; Linsen, L. (Hrsg.): Proceedings of the 6th International Conference on Information Visualization Theory and Applications (IVAPP), Proceedings of the 6th International Conference on Information Visualization Theory and Applications (IVAPP) : SciTePress, 2015 — ISBN 978-989-758-088-8, S. 93–100
  - BibTeX
  BibTeX
  @inproceedings{burch2015edgestacked, address = {Setúbal}, author = {Burch, Michael and Munz, Tanja and Weiskopf, Daniel}, booktitle = {Proceedings of the 6th International Conference on Information Visualization Theory and Applications (IVAPP)}, doi = {10.5220/0005259200930100}, editor = {Braz, José and Kerren, Andreas and Linsen, Lars}, eventdate = {2015-03-11/2015-03-14}, eventtitle = {6th International Conference on Information Visualization Theory and Applications (IVAPP)}, isbn = {978-989-758-088-8}, pages = {93-100}, publisher = {SciTePress}, title = {Edge-stacked Timelines for Visualizing Dynamic Weighted Digraphs}, venue = {Berlin, Germany}, year = 2015 }
2. Burch, Michael ; Munz, Tanja ; Beck, Fabian ; Weiskopf, Daniel: Visualizing Work Processes in Software Engineering with Developer Rivers. In: Proceedings of the 3rd IEEE Working Conference on Software Visualization (VISSOFT ’15), Proceedings of the 3rd IEEE Working Conference on Software Visualization (VISSOFT ’15) : IEEE, 2015
  - BibTeX
  - Link
  BibTeX
  @inproceedings{30fa1ac3c0414a2991f88cd0f62e2e84, author = {Burch, Michael and Munz, Tanja and Beck, Fabian and Weiskopf, Daniel}, booktitle = { Proceedings of the 3rd IEEE Working Conference on Software Visualization (VISSOFT '15)}, publisher = {IEEE}, title = {Visualizing Work Processes in Software Engineering with Developer Rivers}, url = {http://dx.doi.org/10.1109/VISSOFT.2015.7332421}, year = 2015 }
  Link
  http://dx.doi.org/10.1109/VISSOFT.2015.7332421
2014
1. Beck, Fabian ; Burch, Michael ; Munz, Tanja ; Di Silvestro, Lorenzo ; Weiskopf, Daniel: Generalized Pythagoras Trees for Visualizing Hierarchies. In: IVAPP ’14: Proceedings of the 5th International Conference on Information Visualization Theory and Application, IVAPP ’14: Proceedings of the 5th International Conference on Information Visualization Theory and Application : SCITEPRESS, 2014
  - BibTeX
  - Link
  BibTeX
  @inproceedings{74cc02804b2c4998b156bbb96bff68fa, author = {Beck, Fabian and Burch, Michael and Munz, Tanja and Di Silvestro, Lorenzo and Weiskopf, Daniel}, booktitle = {IVAPP '14: Proceedings of the 5th International Conference on Information Visualization Theory and Application}, publisher = {SCITEPRESS}, title = {Generalized Pythagoras Trees for Visualizing Hierarchies}, url = {http://dx.doi.org/10.5220/0004654500170028}, year = 2014 }
  Link
  http://dx.doi.org/10.5220/0004654500170028

Tanja Munz-Körner

Contact

Publications

2022

BibTeX

Link

2021

BibTeX

Link

BibTeX

Link

2020

BibTeX

BibTeX

Link

BibTeX

2019

BibTeX

Link

BibTeX

Link

2016

BibTeX

Link

2015

BibTeX

BibTeX

Link

2014

BibTeX

Link

Audience

Formalities

Services

Organization

Tanja Munz-Körner

Contact

Publications

2022

BibTeX

Link

2021

BibTeX

Link

BibTeX

Link

2020

BibTeX

BibTeX

Link

BibTeX

2019

BibTeX

Link

BibTeX

Link

2016

BibTeX

Link

2015

BibTeX

BibTeX

Link

2014

BibTeX

Link

Here you can reach us

Audience

Formalities

Services

Organization