---
_id: '55909'
abstract:
- lang: eng
text: It is generally assumed that language (written and spoken) follows the entropy
rate constancy (ERC) principle, which states that the information density of a
text is constant over time. Recently, this has also been found for nonverbal gestures
used in monologue, but it is still unclear whether the ERC principle also applies
to listeners' nonverbal signals. We focus on listeners' gaze behaviour extracted
from video-recorded conversations and trained a transformer-based neural sequence
model to process the gaze data of the dialogues and compute its information density.
We also compute the information density of the corresponding speech using a pre-trained
language model. Our results show (1) that listeners' gaze behaviour in dialogues
roughly follows the ERC principle, as well as (2) a congruence between information
density of speech and listeners' gaze behaviour.
author:
- first_name: Yu
full_name: Wang, Yu
last_name: Wang
- first_name: Hendrik
full_name: Buschmeier, Hendrik
id: '76456'
last_name: Buschmeier
orcid: 0000-0002-9613-5713
citation:
ama: 'Wang Y, Buschmeier H. Does listener gaze in face-to-face interaction follow
the Entropy Rate Constancy principle: An empirical study. In: Findings of the
Association for Computational Linguistics: EMNLP 2023. ; 2023:15372–15379.'
apa: 'Wang, Y., & Buschmeier, H. (2023). Does listener gaze in face-to-face
interaction follow the Entropy Rate Constancy principle: An empirical study. Findings
of the Association for Computational Linguistics: EMNLP 2023, 15372–15379.'
bibtex: '@inproceedings{Wang_Buschmeier_2023, place={Singapore}, title={Does listener
gaze in face-to-face interaction follow the Entropy Rate Constancy principle:
An empirical study}, booktitle={Findings of the Association for Computational
Linguistics: EMNLP 2023}, author={Wang, Yu and Buschmeier, Hendrik}, year={2023},
pages={15372–15379} }'
chicago: 'Wang, Yu, and Hendrik Buschmeier. “Does Listener Gaze in Face-to-Face
Interaction Follow the Entropy Rate Constancy Principle: An Empirical Study.”
In Findings of the Association for Computational Linguistics: EMNLP 2023,
15372–15379. Singapore, 2023.'
ieee: 'Y. Wang and H. Buschmeier, “Does listener gaze in face-to-face interaction
follow the Entropy Rate Constancy principle: An empirical study,” in Findings
of the Association for Computational Linguistics: EMNLP 2023, Singapore, 2023,
pp. 15372–15379.'
mla: 'Wang, Yu, and Hendrik Buschmeier. “Does Listener Gaze in Face-to-Face Interaction
Follow the Entropy Rate Constancy Principle: An Empirical Study.” Findings
of the Association for Computational Linguistics: EMNLP 2023, 2023, pp. 15372–15379.'
short: 'Y. Wang, H. Buschmeier, in: Findings of the Association for Computational
Linguistics: EMNLP 2023, Singapore, 2023, pp. 15372–15379.'
conference:
location: Singapore
name: The 2023 Conference on Empirical Methods in Natural Language Processing
date_created: 2024-08-30T07:39:24Z
date_updated: 2025-09-11T10:17:51Z
department:
- _id: '660'
extern: '1'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://aclanthology.org/2023.findings-emnlp.1026
oa: '1'
page: 15372–15379
place: Singapore
project:
- _id: '112'
name: 'TRR 318 - A02: TRR 318 - Verstehensprozess einer Erklärung beobachten und
auswerten (Teilprojekt A02)'
publication: 'Findings of the Association for Computational Linguistics: EMNLP 2023'
publication_status: published
quality_controlled: '1'
status: public
title: 'Does listener gaze in face-to-face interaction follow the Entropy Rate Constancy
principle: An empirical study'
type: conference
user_id: '76456'
year: '2023'
...
---
_id: '48778'
author:
- first_name: Maximilian
full_name: Muschalik, Maximilian
last_name: Muschalik
- first_name: Fabian
full_name: Fumagalli, Fabian
id: '93420'
last_name: Fumagalli
- first_name: Rohit
full_name: Jagtani, Rohit
last_name: Jagtani
- first_name: Barbara
full_name: Hammer, Barbara
last_name: Hammer
- first_name: Eyke
full_name: Huellermeier, Eyke
id: '48129'
last_name: Huellermeier
citation:
ama: 'Muschalik M, Fumagalli F, Jagtani R, Hammer B, Huellermeier E. iPDP: On Partial
Dependence Plots in Dynamic Modeling Scenarios. In: Proceedings of the World
Conference on Explainable Artificial Intelligence (XAI). ; 2023. doi:10.1007/978-3-031-44064-9_11'
apa: 'Muschalik, M., Fumagalli, F., Jagtani, R., Hammer, B., & Huellermeier,
E. (2023). iPDP: On Partial Dependence Plots in Dynamic Modeling Scenarios. Proceedings
of the World Conference on Explainable Artificial Intelligence (XAI). https://doi.org/10.1007/978-3-031-44064-9_11'
bibtex: '@inproceedings{Muschalik_Fumagalli_Jagtani_Hammer_Huellermeier_2023, title={iPDP:
On Partial Dependence Plots in Dynamic Modeling Scenarios}, DOI={10.1007/978-3-031-44064-9_11},
booktitle={Proceedings of the World Conference on Explainable Artificial Intelligence
(xAI)}, author={Muschalik, Maximilian and Fumagalli, Fabian and Jagtani, Rohit
and Hammer, Barbara and Huellermeier, Eyke}, year={2023} }'
chicago: 'Muschalik, Maximilian, Fabian Fumagalli, Rohit Jagtani, Barbara Hammer,
and Eyke Huellermeier. “IPDP: On Partial Dependence Plots in Dynamic Modeling
Scenarios.” In Proceedings of the World Conference on Explainable Artificial
Intelligence (XAI), 2023. https://doi.org/10.1007/978-3-031-44064-9_11.'
ieee: 'M. Muschalik, F. Fumagalli, R. Jagtani, B. Hammer, and E. Huellermeier, “iPDP:
On Partial Dependence Plots in Dynamic Modeling Scenarios,” 2023, doi: 10.1007/978-3-031-44064-9_11.'
mla: 'Muschalik, Maximilian, et al. “IPDP: On Partial Dependence Plots in Dynamic
Modeling Scenarios.” Proceedings of the World Conference on Explainable Artificial
Intelligence (XAI), 2023, doi:10.1007/978-3-031-44064-9_11.'
short: 'M. Muschalik, F. Fumagalli, R. Jagtani, B. Hammer, E. Huellermeier, in:
Proceedings of the World Conference on Explainable Artificial Intelligence (XAI),
2023.'
date_created: 2023-11-10T14:17:17Z
date_updated: 2025-09-11T16:14:34Z
department:
- _id: '660'
doi: 10.1007/978-3-031-44064-9_11
language:
- iso: eng
project:
- _id: '126'
name: 'TRR 318 - C3: TRR 318 - Subproject C3'
- _id: '109'
name: 'TRR 318: TRR 318 - Erklärbarkeit konstruieren'
- _id: '117'
name: 'TRR 318 - C: TRR 318 - Project Area C'
publication: Proceedings of the World Conference on Explainable Artificial Intelligence
(xAI)
publication_identifier:
eisbn:
- 1865-0937
eissn:
- '9783031440649'
isbn:
- '9783031440632'
issn:
- 1865-0929
publication_status: published
status: public
title: 'iPDP: On Partial Dependence Plots in Dynamic Modeling Scenarios'
type: conference
user_id: '93420'
year: '2023'
...
---
_id: '48776'
author:
- first_name: Maximilian
full_name: Muschalik, Maximilian
last_name: Muschalik
- first_name: Fabian
full_name: Fumagalli, Fabian
id: '93420'
last_name: Fumagalli
- first_name: Barbara
full_name: Hammer, Barbara
last_name: Hammer
- first_name: Eyke
full_name: Huellermeier, Eyke
id: '48129'
last_name: Huellermeier
citation:
ama: 'Muschalik M, Fumagalli F, Hammer B, Huellermeier E. iSAGE: An Incremental
Version of SAGE for Online Explanation on Data Streams. In: Machine Learning
and Knowledge Discovery in Databases: Research Track - European Conference (ECML
PKDD). Springer Nature Switzerland; 2023. doi:10.1007/978-3-031-43418-1_26'
apa: 'Muschalik, M., Fumagalli, F., Hammer, B., & Huellermeier, E. (2023). iSAGE:
An Incremental Version of SAGE for Online Explanation on Data Streams. In Machine
Learning and Knowledge Discovery in Databases: Research Track - European Conference
(ECML PKDD). Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-43418-1_26'
bibtex: '@inbook{Muschalik_Fumagalli_Hammer_Huellermeier_2023, title={iSAGE: An
Incremental Version of SAGE for Online Explanation on Data Streams}, DOI={10.1007/978-3-031-43418-1_26},
booktitle={Machine Learning and Knowledge Discovery in Databases: Research Track
- European Conference (ECML PKDD)}, publisher={Springer Nature Switzerland}, author={Muschalik,
Maximilian and Fumagalli, Fabian and Hammer, Barbara and Huellermeier, Eyke},
year={2023} }'
chicago: 'Muschalik, Maximilian, Fabian Fumagalli, Barbara Hammer, and Eyke Huellermeier.
“ISAGE: An Incremental Version of SAGE for Online Explanation on Data Streams.”
In Machine Learning and Knowledge Discovery in Databases: Research Track -
European Conference (ECML PKDD). Springer Nature Switzerland, 2023. https://doi.org/10.1007/978-3-031-43418-1_26.'
ieee: 'M. Muschalik, F. Fumagalli, B. Hammer, and E. Huellermeier, “iSAGE: An Incremental
Version of SAGE for Online Explanation on Data Streams,” in Machine Learning
and Knowledge Discovery in Databases: Research Track - European Conference (ECML
PKDD), Springer Nature Switzerland, 2023.'
mla: 'Muschalik, Maximilian, et al. “ISAGE: An Incremental Version of SAGE for Online
Explanation on Data Streams.” Machine Learning and Knowledge Discovery in Databases:
Research Track - European Conference (ECML PKDD), Springer Nature Switzerland,
2023, doi:10.1007/978-3-031-43418-1_26.'
short: 'M. Muschalik, F. Fumagalli, B. Hammer, E. Huellermeier, in: Machine Learning
and Knowledge Discovery in Databases: Research Track - European Conference (ECML
PKDD), Springer Nature Switzerland, 2023.'
date_created: 2023-11-10T14:11:20Z
date_updated: 2025-09-11T16:27:26Z
department:
- _id: '660'
doi: 10.1007/978-3-031-43418-1_26
language:
- iso: eng
project:
- _id: '126'
name: 'TRR 318 - C3: TRR 318 - Subproject C3'
- _id: '117'
name: 'TRR 318 - C: TRR 318 - Project Area C'
- _id: '109'
name: 'TRR 318: TRR 318 - Erklärbarkeit konstruieren'
publication: 'Machine Learning and Knowledge Discovery in Databases: Research Track
- European Conference (ECML PKDD)'
publication_identifier:
eisbn:
- '9783031434181'
eissn:
- 1611-3349
isbn:
- '9783031434174'
issn:
- 0302-9743
publication_status: published
publisher: Springer Nature Switzerland
status: public
title: 'iSAGE: An Incremental Version of SAGE for Online Explanation on Data Streams'
type: book_chapter
user_id: '93420'
year: '2023'
...
---
_id: '48775'
author:
- first_name: Fabian
full_name: Fumagalli, Fabian
id: '93420'
last_name: Fumagalli
- first_name: Maximilian
full_name: Muschalik, Maximilian
last_name: Muschalik
- first_name: Eyke
full_name: Hüllermeier, Eyke
id: '48129'
last_name: Hüllermeier
- first_name: Barbara
full_name: Hammer, Barbara
last_name: Hammer
citation:
ama: 'Fumagalli F, Muschalik M, Hüllermeier E, Hammer B. On Feature Removal for
Explainability in Dynamic Environments. In: Proceedings of the European Symposium
on Artificial Neural Networks (ESANN). ; 2023. doi:10.14428/ESANN/2023.ES2023-148'
apa: Fumagalli, F., Muschalik, M., Hüllermeier, E., & Hammer, B. (2023). On
Feature Removal for Explainability in Dynamic Environments. Proceedings of
the European Symposium on Artificial Neural Networks (ESANN). ESANN 2023 -
European Symposium on Artificial Neural Networks, Computational Intelligence and
Machine Learning, Bruges (Belgium) and online. https://doi.org/10.14428/ESANN/2023.ES2023-148
bibtex: '@inproceedings{Fumagalli_Muschalik_Hüllermeier_Hammer_2023, title={On Feature
Removal for Explainability in Dynamic Environments}, DOI={10.14428/ESANN/2023.ES2023-148},
booktitle={Proceedings of the European Symposium on Artificial Neural Networks
(ESANN)}, author={Fumagalli, Fabian and Muschalik, Maximilian and Hüllermeier,
Eyke and Hammer, Barbara}, year={2023} }'
chicago: Fumagalli, Fabian, Maximilian Muschalik, Eyke Hüllermeier, and Barbara
Hammer. “On Feature Removal for Explainability in Dynamic Environments.” In Proceedings
of the European Symposium on Artificial Neural Networks (ESANN), 2023. https://doi.org/10.14428/ESANN/2023.ES2023-148.
ieee: 'F. Fumagalli, M. Muschalik, E. Hüllermeier, and B. Hammer, “On Feature Removal
for Explainability in Dynamic Environments,” presented at the ESANN 2023 - European
Symposium on Artificial Neural Networks, Computational Intelligence and Machine
Learning, Bruges (Belgium) and online, 2023, doi: 10.14428/ESANN/2023.ES2023-148.'
mla: Fumagalli, Fabian, et al. “On Feature Removal for Explainability in Dynamic
Environments.” Proceedings of the European Symposium on Artificial Neural Networks
(ESANN), 2023, doi:10.14428/ESANN/2023.ES2023-148.
short: 'F. Fumagalli, M. Muschalik, E. Hüllermeier, B. Hammer, in: Proceedings of
the European Symposium on Artificial Neural Networks (ESANN), 2023.'
conference:
location: Bruges (Belgium) and online
name: ESANN 2023 - European Symposium on Artificial Neural Networks, Computational
Intelligence and Machine Learning
date_created: 2023-11-10T14:00:08Z
date_updated: 2025-09-11T16:26:21Z
department:
- _id: '660'
doi: 10.14428/ESANN/2023.ES2023-148
language:
- iso: eng
project:
- _id: '126'
name: 'TRR 318 - C3: TRR 318 - Subproject C3'
- _id: '117'
name: 'TRR 318 - C: TRR 318 - Project Area C'
- _id: '109'
name: 'TRR 318: TRR 318 - Erklärbarkeit konstruieren'
publication: Proceedings of the European Symposium on Artificial Neural Networks (ESANN)
publication_identifier:
unknown:
- ' 978-2-87587-088-9'
publication_status: published
status: public
title: On Feature Removal for Explainability in Dynamic Environments
type: conference
user_id: '93420'
year: '2023'
...
---
_id: '52230'
author:
- first_name: Fabian
full_name: Fumagalli, Fabian
id: '93420'
last_name: Fumagalli
- first_name: Maximilian
full_name: Muschalik, Maximilian
last_name: Muschalik
- first_name: Patrick
full_name: Kolpaczki, Patrick
last_name: Kolpaczki
- first_name: Eyke
full_name: Hüllermeier, Eyke
id: '48129'
last_name: Hüllermeier
- first_name: Barbara
full_name: Hammer, Barbara
last_name: Hammer
citation:
ama: 'Fumagalli F, Muschalik M, Kolpaczki P, Hüllermeier E, Hammer B. SHAP-IQ: Unified
Approximation of any-order Shapley Interactions. In: Advances in Neural Information
Processing Systems (NeurIPS). Vol 36. ; 2023:11515--11551.'
apa: 'Fumagalli, F., Muschalik, M., Kolpaczki, P., Hüllermeier, E., & Hammer,
B. (2023). SHAP-IQ: Unified Approximation of any-order Shapley Interactions. Advances
in Neural Information Processing Systems (NeurIPS), 36, 11515--11551.'
bibtex: '@inproceedings{Fumagalli_Muschalik_Kolpaczki_Hüllermeier_Hammer_2023, title={SHAP-IQ:
Unified Approximation of any-order Shapley Interactions}, volume={36}, booktitle={Advances
in Neural Information Processing Systems (NeurIPS)}, author={Fumagalli, Fabian
and Muschalik, Maximilian and Kolpaczki, Patrick and Hüllermeier, Eyke and Hammer,
Barbara}, year={2023}, pages={11515--11551} }'
chicago: 'Fumagalli, Fabian, Maximilian Muschalik, Patrick Kolpaczki, Eyke Hüllermeier,
and Barbara Hammer. “SHAP-IQ: Unified Approximation of Any-Order Shapley Interactions.”
In Advances in Neural Information Processing Systems (NeurIPS), 36:11515--11551,
2023.'
ieee: 'F. Fumagalli, M. Muschalik, P. Kolpaczki, E. Hüllermeier, and B. Hammer,
“SHAP-IQ: Unified Approximation of any-order Shapley Interactions,” in Advances
in Neural Information Processing Systems (NeurIPS), 2023, vol. 36, pp. 11515--11551.'
mla: 'Fumagalli, Fabian, et al. “SHAP-IQ: Unified Approximation of Any-Order Shapley
Interactions.” Advances in Neural Information Processing Systems (NeurIPS),
vol. 36, 2023, pp. 11515--11551.'
short: 'F. Fumagalli, M. Muschalik, P. Kolpaczki, E. Hüllermeier, B. Hammer, in:
Advances in Neural Information Processing Systems (NeurIPS), 2023, pp. 11515--11551.'
date_created: 2024-03-01T14:15:31Z
date_updated: 2025-09-11T16:18:16Z
department:
- _id: '660'
intvolume: ' 36'
language:
- iso: eng
page: 11515--11551
project:
- _id: '126'
name: 'TRR 318 - C3: TRR 318 - Subproject C3'
- _id: '109'
name: 'TRR 318: TRR 318 - Erklärbarkeit konstruieren'
- _id: '117'
name: 'TRR 318 - C: TRR 318 - Project Area C'
publication: Advances in Neural Information Processing Systems (NeurIPS)
status: public
title: 'SHAP-IQ: Unified Approximation of any-order Shapley Interactions'
type: conference
user_id: '93420'
volume: 36
year: '2023'
...
---
_id: '61301'
article_number: '126722'
author:
- first_name: André
full_name: Artelt, André
last_name: Artelt
- first_name: Roelof
full_name: Visser, Roelof
id: '93919'
last_name: Visser
- first_name: Barbara
full_name: Hammer, Barbara
last_name: Hammer
citation:
ama: Artelt A, Visser R, Hammer B. “I do not know! but why?” — Local model-agnostic
example-based explanations of reject. Neurocomputing. 2023;558. doi:10.1016/j.neucom.2023.126722
apa: Artelt, A., Visser, R., & Hammer, B. (2023). “I do not know! but why?”
— Local model-agnostic example-based explanations of reject. Neurocomputing,
558, Article 126722. https://doi.org/10.1016/j.neucom.2023.126722
bibtex: '@article{Artelt_Visser_Hammer_2023, title={“I do not know! but why?” —
Local model-agnostic example-based explanations of reject}, volume={558}, DOI={10.1016/j.neucom.2023.126722},
number={126722}, journal={Neurocomputing}, publisher={Elsevier BV}, author={Artelt,
André and Visser, Roelof and Hammer, Barbara}, year={2023} }'
chicago: Artelt, André, Roelof Visser, and Barbara Hammer. “‘I Do Not Know! But
Why?’ — Local Model-Agnostic Example-Based Explanations of Reject.” Neurocomputing
558 (2023). https://doi.org/10.1016/j.neucom.2023.126722.
ieee: 'A. Artelt, R. Visser, and B. Hammer, “‘I do not know! but why?’ — Local model-agnostic
example-based explanations of reject,” Neurocomputing, vol. 558, Art. no.
126722, 2023, doi: 10.1016/j.neucom.2023.126722.'
mla: Artelt, André, et al. “‘I Do Not Know! But Why?’ — Local Model-Agnostic Example-Based
Explanations of Reject.” Neurocomputing, vol. 558, 126722, Elsevier BV,
2023, doi:10.1016/j.neucom.2023.126722.
short: A. Artelt, R. Visser, B. Hammer, Neurocomputing 558 (2023).
date_created: 2025-09-16T09:48:54Z
date_updated: 2025-09-17T11:49:31Z
department:
- _id: '660'
doi: 10.1016/j.neucom.2023.126722
intvolume: ' 558'
language:
- iso: eng
project:
- _id: '124'
name: 'TRR 318 ; TP C01: Gesundes Misstrauen in Erklärungen'
publication: Neurocomputing
publication_identifier:
issn:
- 0925-2312
publication_status: published
publisher: Elsevier BV
status: public
title: “I do not know! but why?” — Local model-agnostic example-based explanations
of reject
type: journal_article
user_id: '55908'
volume: 558
year: '2023'
...
---
_id: '33696'
author:
- first_name: Jana
full_name: Wiechmann, Jana
last_name: Wiechmann
- first_name: Thomas
full_name: Glarner, Thomas
last_name: Glarner
- first_name: Frederik
full_name: Rautenberg, Frederik
id: '72602'
last_name: Rautenberg
- first_name: Petra
full_name: Wagner, Petra
last_name: Wagner
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: 'Wiechmann J, Glarner T, Rautenberg F, Wagner P, Haeb-Umbach R. Technically
enabled explaining of voice characteristics. In: 18. Phonetik Und Phonologie
Im Deutschsprachigen Raum (P&P). ; 2022.'
apa: Wiechmann, J., Glarner, T., Rautenberg, F., Wagner, P., & Haeb-Umbach,
R. (2022). Technically enabled explaining of voice characteristics. 18. Phonetik
Und Phonologie Im Deutschsprachigen Raum (P&P).
bibtex: '@inproceedings{Wiechmann_Glarner_Rautenberg_Wagner_Haeb-Umbach_2022, title={Technically
enabled explaining of voice characteristics}, booktitle={18. Phonetik und Phonologie
im deutschsprachigen Raum (P&P)}, author={Wiechmann, Jana and Glarner, Thomas
and Rautenberg, Frederik and Wagner, Petra and Haeb-Umbach, Reinhold}, year={2022}
}'
chicago: Wiechmann, Jana, Thomas Glarner, Frederik Rautenberg, Petra Wagner, and
Reinhold Haeb-Umbach. “Technically Enabled Explaining of Voice Characteristics.”
In 18. Phonetik Und Phonologie Im Deutschsprachigen Raum (P&P), 2022.
ieee: J. Wiechmann, T. Glarner, F. Rautenberg, P. Wagner, and R. Haeb-Umbach, “Technically
enabled explaining of voice characteristics,” Bielefeld, 2022.
mla: Wiechmann, Jana, et al. “Technically Enabled Explaining of Voice Characteristics.”
18. Phonetik Und Phonologie Im Deutschsprachigen Raum (P&P), 2022.
short: 'J. Wiechmann, T. Glarner, F. Rautenberg, P. Wagner, R. Haeb-Umbach, in:
18. Phonetik Und Phonologie Im Deutschsprachigen Raum (P&P), 2022.'
conference:
end_date: 2022-10-07
location: Bielefeld
start_date: 2022-10-06
date_created: 2022-10-12T07:10:03Z
date_updated: 2023-11-22T13:45:30Z
ddc:
- '000'
department:
- _id: '54'
- _id: '660'
file:
- access_level: open_access
content_type: application/pdf
creator: huesera
date_created: 2022-10-12T07:09:26Z
date_updated: 2022-10-12T07:09:26Z
file_id: '33697'
file_name: PP_2022_paper_8911.pdf
file_size: 109294
relation: main_file
file_date_updated: 2022-10-12T07:09:26Z
has_accepted_license: '1'
language:
- iso: eng
oa: '1'
project:
- _id: '129'
grant_number: '438445824'
name: 'TRR 318 - C06: TRR 318 - Technisch unterstütztes Erklären von Stimmcharakteristika
(Teilprojekt C06)'
publication: 18. Phonetik und Phonologie im deutschsprachigen Raum (P&P)
status: public
title: Technically enabled explaining of voice characteristics
type: conference
user_id: '72602'
year: '2022'
...
---
_id: '51348'
abstract:
- lang: eng
text: AbstractWith the perspective on applications
of AI-technology, especially data intensive deep learning approaches, the need
for methods to control and understand such models has been recognized and gave
rise to a new research domain labeled explainable artificial intelligence (XAI).
In this overview paper we give an interim appraisal of what has been achieved
so far and where there are still gaps in the research. We take an interdisciplinary
perspective to identify challenges on XAI research and point to open questions
with respect to the quality of the explanations regarding faithfulness and consistency
of explanations. On the other hand we see a need regarding the interaction between
XAI and user to allow for adaptability to specific information needs and explanatory
dialog for informed decision making as well as the possibility to correct models
and explanations by interaction. This endeavor requires an integrated interdisciplinary
perspective and rigorous approaches to empirical evaluation based on psychological,
linguistic and even sociological theories.
alternative_title:
- An Interdisciplinary Perspective
author:
- first_name: Ute
full_name: Schmid, Ute
last_name: Schmid
- first_name: Britta
full_name: Wrede, Britta
last_name: Wrede
citation:
ama: Schmid U, Wrede B. What is Missing in XAI So Far? KI - Künstliche Intelligenz.
2022;36(3-4):303-315. doi:10.1007/s13218-022-00786-2
apa: Schmid, U., & Wrede, B. (2022). What is Missing in XAI So Far? KI -
Künstliche Intelligenz, 36(3–4), 303–315. https://doi.org/10.1007/s13218-022-00786-2
bibtex: '@article{Schmid_Wrede_2022, title={What is Missing in XAI So Far?}, volume={36},
DOI={10.1007/s13218-022-00786-2},
number={3–4}, journal={KI - Künstliche Intelligenz}, publisher={Springer Science
and Business Media LLC}, author={Schmid, Ute and Wrede, Britta}, year={2022},
pages={303–315} }'
chicago: 'Schmid, Ute, and Britta Wrede. “What Is Missing in XAI So Far?” KI
- Künstliche Intelligenz 36, no. 3–4 (2022): 303–15. https://doi.org/10.1007/s13218-022-00786-2.'
ieee: 'U. Schmid and B. Wrede, “What is Missing in XAI So Far?,” KI - Künstliche
Intelligenz, vol. 36, no. 3–4, pp. 303–315, 2022, doi: 10.1007/s13218-022-00786-2.'
mla: Schmid, Ute, and Britta Wrede. “What Is Missing in XAI So Far?” KI - Künstliche
Intelligenz, vol. 36, no. 3–4, Springer Science and Business Media LLC, 2022,
pp. 303–15, doi:10.1007/s13218-022-00786-2.
short: U. Schmid, B. Wrede, KI - Künstliche Intelligenz 36 (2022) 303–315.
date_created: 2024-02-14T09:41:56Z
date_updated: 2024-02-26T08:48:49Z
department:
- _id: '660'
doi: 10.1007/s13218-022-00786-2
intvolume: ' 36'
issue: 3-4
keyword:
- Artificial Intelligence
language:
- iso: eng
page: 303-315
project:
- _id: '113'
name: 'TRR 318 - A3: TRR 318 - Subproject A3'
- _id: '115'
grant_number: '438445824'
name: 'TRR 318 - A05: TRR 318 - Echtzeitmessung der Aufmerksamkeit im Mensch-Roboter-Erklärdialog
(Teilprojekt A05)'
publication: KI - Künstliche Intelligenz
publication_identifier:
issn:
- 0933-1875
- 1610-1987
publication_status: published
publisher: Springer Science and Business Media LLC
status: public
title: What is Missing in XAI So Far?
type: journal_article
user_id: '54779'
volume: 36
year: '2022'
...
---
_id: '51366'
author:
- first_name: Ute
full_name: Schmid, Ute
last_name: Schmid
- first_name: Britta
full_name: Wrede, Britta
last_name: Wrede
citation:
ama: Schmid U, Wrede B. Explainable AI. KI - Künstliche Intelligenz. 2022;36(3-4):207-210.
doi:10.1007/s13218-022-00788-0
apa: Schmid, U., & Wrede, B. (2022). Explainable AI. KI - Künstliche Intelligenz,
36(3–4), 207–210. https://doi.org/10.1007/s13218-022-00788-0
bibtex: '@article{Schmid_Wrede_2022, title={Explainable AI}, volume={36}, DOI={10.1007/s13218-022-00788-0},
number={3–4}, journal={KI - Künstliche Intelligenz}, publisher={Springer Science
and Business Media LLC}, author={Schmid, Ute and Wrede, Britta}, year={2022},
pages={207–210} }'
chicago: 'Schmid, Ute, and Britta Wrede. “Explainable AI.” KI - Künstliche Intelligenz
36, no. 3–4 (2022): 207–10. https://doi.org/10.1007/s13218-022-00788-0.'
ieee: 'U. Schmid and B. Wrede, “Explainable AI,” KI - Künstliche Intelligenz,
vol. 36, no. 3–4, pp. 207–210, 2022, doi: 10.1007/s13218-022-00788-0.'
mla: Schmid, Ute, and Britta Wrede. “Explainable AI.” KI - Künstliche Intelligenz,
vol. 36, no. 3–4, Springer Science and Business Media LLC, 2022, pp. 207–10, doi:10.1007/s13218-022-00788-0.
short: U. Schmid, B. Wrede, KI - Künstliche Intelligenz 36 (2022) 207–210.
date_created: 2024-02-18T10:03:11Z
date_updated: 2024-02-26T08:48:00Z
department:
- _id: '660'
doi: 10.1007/s13218-022-00788-0
intvolume: ' 36'
issue: 3-4
keyword:
- Artificial Intelligence
language:
- iso: eng
page: 207-210
project:
- _id: '113'
name: 'TRR 318 - A3: TRR 318 - Subproject A3'
- _id: '115'
grant_number: '438445824'
name: 'TRR 318 - A05: TRR 318 - Echtzeitmessung der Aufmerksamkeit im Mensch-Roboter-Erklärdialog
(Teilprojekt A05)'
publication: KI - Künstliche Intelligenz
publication_identifier:
issn:
- 0933-1875
- 1610-1987
publication_status: published
publisher: Springer Science and Business Media LLC
status: public
title: Explainable AI
type: journal_article
user_id: '54779'
volume: 36
year: '2022'
...
---
_id: '51365'
author:
- first_name: Britta
full_name: Wrede, Britta
last_name: Wrede
citation:
ama: 'Wrede B. AI: Back to the Roots? KI - Künstliche Intelligenz. 2022;36(2):117-120.
doi:10.1007/s13218-022-00773-7'
apa: 'Wrede, B. (2022). AI: Back to the Roots? KI - Künstliche Intelligenz,
36(2), 117–120. https://doi.org/10.1007/s13218-022-00773-7'
bibtex: '@article{Wrede_2022, title={AI: Back to the Roots?}, volume={36}, DOI={10.1007/s13218-022-00773-7},
number={2}, journal={KI - Künstliche Intelligenz}, publisher={Springer Science
and Business Media LLC}, author={Wrede, Britta}, year={2022}, pages={117–120}
}'
chicago: 'Wrede, Britta. “AI: Back to the Roots?” KI - Künstliche Intelligenz
36, no. 2 (2022): 117–20. https://doi.org/10.1007/s13218-022-00773-7.'
ieee: 'B. Wrede, “AI: Back to the Roots?,” KI - Künstliche Intelligenz, vol.
36, no. 2, pp. 117–120, 2022, doi: 10.1007/s13218-022-00773-7.'
mla: 'Wrede, Britta. “AI: Back to the Roots?” KI - Künstliche Intelligenz,
vol. 36, no. 2, Springer Science and Business Media LLC, 2022, pp. 117–20, doi:10.1007/s13218-022-00773-7.'
short: B. Wrede, KI - Künstliche Intelligenz 36 (2022) 117–120.
date_created: 2024-02-18T09:55:30Z
date_updated: 2024-02-26T08:50:19Z
department:
- _id: '660'
doi: 10.1007/s13218-022-00773-7
intvolume: ' 36'
issue: '2'
keyword:
- Artificial Intelligence
language:
- iso: eng
page: 117-120
project:
- _id: '113'
name: 'TRR 318 - A3: TRR 318 - Subproject A3'
publication: KI - Künstliche Intelligenz
publication_identifier:
issn:
- 0933-1875
- 1610-1987
publication_status: published
publisher: Springer Science and Business Media LLC
status: public
title: 'AI: Back to the Roots?'
type: journal_article
user_id: '54779'
volume: 36
year: '2022'
...
---
_id: '51344'
abstract:
- lang: eng
text: Modified action demonstration—dubbed motionese—has
been proposed as a way to help children recognize the structure and meaning of
actions. However, until now, it has been investigated only in young infants. This
brief research report presents findings from a cross-sectional study of parental
action demonstrations to three groups of 8–11, 12–23, and 24–30-month-old children
that applied seven motionese parameters; a second study investigated the youngest
group of participants longitudinally to corroborate the cross-sectional results.
Results of both studies suggested that four motionese parameters (Motion Pauses,
Pace, Velocity, Acceleration) seem to structure the action by organizing it in
motion pauses. Whereas these parameters persist over different ages, three other
parameters (Demonstration Length, Roundness, and Range) occur predominantly in
the younger group and seem to serve to organize infants' attention on the basis
of movement. Results are discussed in terms of facilitative vs. pedagogical learning.
author:
- first_name: Katharina
full_name: Rohlfing, Katharina
id: '50352'
last_name: Rohlfing
- first_name: Anna-Lisa
full_name: Vollmer, Anna-Lisa
last_name: Vollmer
- first_name: Jannik
full_name: Fritsch, Jannik
last_name: Fritsch
- first_name: Britta
full_name: Wrede, Britta
last_name: Wrede
citation:
ama: Rohlfing K, Vollmer A-L, Fritsch J, Wrede B. Which “motionese” parameters change
with children’s age? Disentangling attention-getting from action-structuring modifications.
Frontiers in Communication. 2022;7. doi:10.3389/fcomm.2022.922405
apa: Rohlfing, K., Vollmer, A.-L., Fritsch, J., & Wrede, B. (2022). Which “motionese”
parameters change with children’s age? Disentangling attention-getting from action-structuring
modifications. Frontiers in Communication, 7. https://doi.org/10.3389/fcomm.2022.922405
bibtex: '@article{Rohlfing_Vollmer_Fritsch_Wrede_2022, title={Which “motionese”
parameters change with children’s age? Disentangling attention-getting from action-structuring
modifications}, volume={7}, DOI={10.3389/fcomm.2022.922405},
journal={Frontiers in Communication}, publisher={Frontiers Media SA}, author={Rohlfing,
Katharina and Vollmer, Anna-Lisa and Fritsch, Jannik and Wrede, Britta}, year={2022}
}'
chicago: Rohlfing, Katharina, Anna-Lisa Vollmer, Jannik Fritsch, and Britta Wrede.
“Which ‘Motionese’ Parameters Change with Children’s Age? Disentangling Attention-Getting
from Action-Structuring Modifications.” Frontiers in Communication 7 (2022).
https://doi.org/10.3389/fcomm.2022.922405.
ieee: 'K. Rohlfing, A.-L. Vollmer, J. Fritsch, and B. Wrede, “Which ‘motionese’
parameters change with children’s age? Disentangling attention-getting from action-structuring
modifications,” Frontiers in Communication, vol. 7, 2022, doi: 10.3389/fcomm.2022.922405.'
mla: Rohlfing, Katharina, et al. “Which ‘Motionese’ Parameters Change with Children’s
Age? Disentangling Attention-Getting from Action-Structuring Modifications.” Frontiers
in Communication, vol. 7, Frontiers Media SA, 2022, doi:10.3389/fcomm.2022.922405.
short: K. Rohlfing, A.-L. Vollmer, J. Fritsch, B. Wrede, Frontiers in Communication
7 (2022).
date_created: 2024-02-14T09:07:53Z
date_updated: 2024-02-26T08:53:33Z
department:
- _id: '660'
doi: 10.3389/fcomm.2022.922405
intvolume: ' 7'
keyword:
- Social Sciences (miscellaneous)
- Communication
language:
- iso: eng
project:
- _id: '111'
grant_number: '438445824'
name: 'TRR 318 - A01: TRR 318 - Adaptives Erklären (Teilprojekt A01)'
- _id: '113'
name: 'TRR 318 - A3: TRR 318 - Subproject A3'
- _id: '115'
grant_number: '438445824'
name: 'TRR 318 - A05: TRR 318 - Echtzeitmessung der Aufmerksamkeit im Mensch-Roboter-Erklärdialog
(Teilprojekt A05)'
publication: Frontiers in Communication
publication_identifier:
issn:
- 2297-900X
publication_status: published
publisher: Frontiers Media SA
status: public
title: Which “motionese” parameters change with children's age? Disentangling attention-getting
from action-structuring modifications
type: journal_article
user_id: '54779'
volume: 7
year: '2022'
...
---
_id: '51346'
author:
- first_name: André
full_name: Groß, André
id: '93405'
last_name: Groß
orcid: 0000-0002-9593-7220
- first_name: Christian
full_name: Schütze, Christian
last_name: Schütze
- first_name: Britta
full_name: Wrede, Britta
last_name: Wrede
- first_name: Birte
full_name: Richter, Birte
last_name: Richter
citation:
ama: 'Groß A, Schütze C, Wrede B, Richter B. An Architecture Supporting Configurable
Autonomous Multimodal Joint-Attention-Therapy for Various Robotic Systems. In:
INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION. ACM; 2022:154-159.
doi:10.1145/3536220.3558070'
apa: Groß, A., Schütze, C., Wrede, B., & Richter, B. (2022). An Architecture
Supporting Configurable Autonomous Multimodal Joint-Attention-Therapy for Various
Robotic Systems. INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION, 154–159.
https://doi.org/10.1145/3536220.3558070
bibtex: '@inproceedings{Groß_Schütze_Wrede_Richter_2022, title={An Architecture
Supporting Configurable Autonomous Multimodal Joint-Attention-Therapy for Various
Robotic Systems}, DOI={10.1145/3536220.3558070},
booktitle={INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION}, publisher={ACM},
author={Groß, André and Schütze, Christian and Wrede, Britta and Richter, Birte},
year={2022}, pages={154–159} }'
chicago: Groß, André, Christian Schütze, Britta Wrede, and Birte Richter. “An Architecture
Supporting Configurable Autonomous Multimodal Joint-Attention-Therapy for Various
Robotic Systems.” In INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION,
154–59. ACM, 2022. https://doi.org/10.1145/3536220.3558070.
ieee: 'A. Groß, C. Schütze, B. Wrede, and B. Richter, “An Architecture Supporting
Configurable Autonomous Multimodal Joint-Attention-Therapy for Various Robotic
Systems,” in INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION, 2022,
pp. 154–159, doi: 10.1145/3536220.3558070.'
mla: Groß, André, et al. “An Architecture Supporting Configurable Autonomous Multimodal
Joint-Attention-Therapy for Various Robotic Systems.” INTERNATIONAL CONFERENCE
ON MULTIMODAL INTERACTION, ACM, 2022, pp. 154–59, doi:10.1145/3536220.3558070.
short: 'A. Groß, C. Schütze, B. Wrede, B. Richter, in: INTERNATIONAL CONFERENCE
ON MULTIMODAL INTERACTION, ACM, 2022, pp. 154–159.'
date_created: 2024-02-14T09:28:57Z
date_updated: 2024-02-26T08:52:52Z
department:
- _id: '660'
doi: 10.1145/3536220.3558070
language:
- iso: eng
page: 154-159
project:
- _id: '115'
grant_number: '438445824'
name: 'TRR 318 - A05: TRR 318 - Echtzeitmessung der Aufmerksamkeit im Mensch-Roboter-Erklärdialog
(Teilprojekt A05)'
- _id: '113'
name: 'TRR 318 - A3: TRR 318 - Subproject A3'
publication: INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION
publication_status: published
publisher: ACM
status: public
title: An Architecture Supporting Configurable Autonomous Multimodal Joint-Attention-Therapy
for Various Robotic Systems
type: conference
user_id: '54779'
year: '2022'
...
---
_id: '51347'
author:
- first_name: Christian
full_name: Schütze, Christian
last_name: Schütze
- first_name: André
full_name: Groß, André
id: '93405'
last_name: Groß
orcid: 0000-0002-9593-7220
- first_name: Britta
full_name: Wrede, Britta
last_name: Wrede
- first_name: Birte
full_name: Richter, Birte
last_name: Richter
citation:
ama: 'Schütze C, Groß A, Wrede B, Richter B. Enabling Non-Technical Domain Experts
to Create Robot-Assisted Therapeutic Scenarios via Visual Programming. In: INTERNATIONAL
CONFERENCE ON MULTIMODAL INTERACTION. ACM; 2022:166-170. doi:10.1145/3536220.3558072'
apa: Schütze, C., Groß, A., Wrede, B., & Richter, B. (2022). Enabling Non-Technical
Domain Experts to Create Robot-Assisted Therapeutic Scenarios via Visual Programming.
INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION, 166–170. https://doi.org/10.1145/3536220.3558072
bibtex: '@inproceedings{Schütze_Groß_Wrede_Richter_2022, title={Enabling Non-Technical
Domain Experts to Create Robot-Assisted Therapeutic Scenarios via Visual Programming},
DOI={10.1145/3536220.3558072},
booktitle={INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION}, publisher={ACM},
author={Schütze, Christian and Groß, André and Wrede, Britta and Richter, Birte},
year={2022}, pages={166–170} }'
chicago: Schütze, Christian, André Groß, Britta Wrede, and Birte Richter. “Enabling
Non-Technical Domain Experts to Create Robot-Assisted Therapeutic Scenarios via
Visual Programming.” In INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION,
166–70. ACM, 2022. https://doi.org/10.1145/3536220.3558072.
ieee: 'C. Schütze, A. Groß, B. Wrede, and B. Richter, “Enabling Non-Technical Domain
Experts to Create Robot-Assisted Therapeutic Scenarios via Visual Programming,”
in INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION, 2022, pp. 166–170,
doi: 10.1145/3536220.3558072.'
mla: Schütze, Christian, et al. “Enabling Non-Technical Domain Experts to Create
Robot-Assisted Therapeutic Scenarios via Visual Programming.” INTERNATIONAL
CONFERENCE ON MULTIMODAL INTERACTION, ACM, 2022, pp. 166–70, doi:10.1145/3536220.3558072.
short: 'C. Schütze, A. Groß, B. Wrede, B. Richter, in: INTERNATIONAL CONFERENCE
ON MULTIMODAL INTERACTION, ACM, 2022, pp. 166–170.'
date_created: 2024-02-14T09:40:09Z
date_updated: 2024-02-26T08:52:05Z
department:
- _id: '660'
doi: 10.1145/3536220.3558072
language:
- iso: eng
page: 166-170
project:
- _id: '115'
grant_number: '438445824'
name: 'TRR 318 - A05: TRR 318 - Echtzeitmessung der Aufmerksamkeit im Mensch-Roboter-Erklärdialog
(Teilprojekt A05)'
- _id: '113'
name: 'TRR 318 - A3: TRR 318 - Subproject A3'
publication: INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION
publication_status: published
publisher: ACM
status: public
title: Enabling Non-Technical Domain Experts to Create Robot-Assisted Therapeutic
Scenarios via Visual Programming
type: conference
user_id: '54779'
year: '2022'
...
---
_id: '55337'
abstract:
- lang: eng
text: As AI is more and more pervasive in everyday life, humans have an increasing
demand to understand its behavior and decisions. Most research on explainable
AI builds on the premise that there is one ideal explanation to be found. In fact,
however, everyday explanations are co-constructed in a dialogue between the person
explaining (the explainer) and the specific person being explained to (the explainee).
In this paper, we introduce a first corpus of dialogical explanations to enable
NLP research on how humans explain as well as on how AI can learn to imitate this
process. The corpus consists of 65 transcribed English dialogues from the Wired
video series 5 Levels, explaining 13 topics to five explainees of different proficiency.
All 1550 dialogue turns have been manually labeled by five independent professionals
for the topic discussed as well as for the dialogue act and the explanation move
performed. We analyze linguistic patterns of explainers and explainees, and we
explore differences across proficiency levels. BERT-based baseline results indicate
that sequence information helps predicting topics, acts, and moves effectively.
author:
- first_name: Henning
full_name: Wachsmuth, Henning
id: '3900'
last_name: Wachsmuth
- first_name: Milad
full_name: Alshomary, Milad
id: '73059'
last_name: Alshomary
citation:
ama: 'Wachsmuth H, Alshomary M. “Mama Always Had a Way of Explaining Things So I
Could Understand”: A Dialogue Corpus for Learning to Construct Explanations. In:
Calzolari N, Huang C-R, Kim H, et al., eds. Proceedings of the 29th International
Conference on Computational Linguistics. International Committee on Computational
Linguistics; 2022:344–354.'
apa: 'Wachsmuth, H., & Alshomary, M. (2022). “Mama Always Had a Way of Explaining
Things So I Could Understand”: A Dialogue Corpus for Learning to Construct Explanations.
In N. Calzolari, C.-R. Huang, H. Kim, J. Pustejovsky, L. Wanner, K.-S. Choi, P.-M.
Ryu, H.-H. Chen, L. Donatelli, H. Ji, S. Kurohashi, P. Paggio, N. Xue, S. Kim,
Y. Hahm, Z. He, T. K. Lee, E. Santus, F. Bond, & S.-H. Na (Eds.), Proceedings
of the 29th International Conference on Computational Linguistics (pp. 344–354).
International Committee on Computational Linguistics.'
bibtex: '@inproceedings{Wachsmuth_Alshomary_2022, place={Gyeongju, Republic of Korea},
title={“Mama Always Had a Way of Explaining Things So I Could Understand”: A Dialogue
Corpus for Learning to Construct Explanations}, booktitle={Proceedings of the
29th International Conference on Computational Linguistics}, publisher={International
Committee on Computational Linguistics}, author={Wachsmuth, Henning and Alshomary,
Milad}, editor={Calzolari, Nicoletta and Huang, Chu-Ren and Kim, Hansaem and Pustejovsky,
James and Wanner, Leo and Choi, Key-Sun and Ryu, Pum-Mo and Chen, Hsin-Hsi and
Donatelli, Lucia and Ji, Heng and et al.}, year={2022}, pages={344–354} }'
chicago: 'Wachsmuth, Henning, and Milad Alshomary. “‘Mama Always Had a Way of Explaining
Things So I Could Understand’: A Dialogue Corpus for Learning to Construct Explanations.”
In Proceedings of the 29th International Conference on Computational Linguistics,
edited by Nicoletta Calzolari, Chu-Ren Huang, Hansaem Kim, James Pustejovsky,
Leo Wanner, Key-Sun Choi, Pum-Mo Ryu, et al., 344–354. Gyeongju, Republic of Korea:
International Committee on Computational Linguistics, 2022.'
ieee: 'H. Wachsmuth and M. Alshomary, “‘Mama Always Had a Way of Explaining Things
So I Could Understand’: A Dialogue Corpus for Learning to Construct Explanations,”
in Proceedings of the 29th International Conference on Computational Linguistics,
2022, pp. 344–354.'
mla: 'Wachsmuth, Henning, and Milad Alshomary. “‘Mama Always Had a Way of Explaining
Things So I Could Understand’: A Dialogue Corpus for Learning to Construct Explanations.”
Proceedings of the 29th International Conference on Computational Linguistics,
edited by Nicoletta Calzolari et al., International Committee on Computational
Linguistics, 2022, pp. 344–354.'
short: 'H. Wachsmuth, M. Alshomary, in: N. Calzolari, C.-R. Huang, H. Kim, J. Pustejovsky,
L. Wanner, K.-S. Choi, P.-M. Ryu, H.-H. Chen, L. Donatelli, H. Ji, S. Kurohashi,
P. Paggio, N. Xue, S. Kim, Y. Hahm, Z. He, T.K. Lee, E. Santus, F. Bond, S.-H.
Na (Eds.), Proceedings of the 29th International Conference on Computational Linguistics,
International Committee on Computational Linguistics, Gyeongju, Republic of Korea,
2022, pp. 344–354.'
date_created: 2024-07-22T13:05:42Z
date_updated: 2024-07-26T13:05:45Z
department:
- _id: '600'
- _id: '660'
editor:
- first_name: Nicoletta
full_name: Calzolari, Nicoletta
last_name: Calzolari
- first_name: Chu-Ren
full_name: Huang, Chu-Ren
last_name: Huang
- first_name: Hansaem
full_name: Kim, Hansaem
last_name: Kim
- first_name: James
full_name: Pustejovsky, James
last_name: Pustejovsky
- first_name: Leo
full_name: Wanner, Leo
last_name: Wanner
- first_name: Key-Sun
full_name: Choi, Key-Sun
last_name: Choi
- first_name: Pum-Mo
full_name: Ryu, Pum-Mo
last_name: Ryu
- first_name: Hsin-Hsi
full_name: Chen, Hsin-Hsi
last_name: Chen
- first_name: Lucia
full_name: Donatelli, Lucia
last_name: Donatelli
- first_name: Heng
full_name: Ji, Heng
last_name: Ji
- first_name: Sadao
full_name: Kurohashi, Sadao
last_name: Kurohashi
- first_name: Patrizia
full_name: Paggio, Patrizia
last_name: Paggio
- first_name: Nianwen
full_name: Xue, Nianwen
last_name: Xue
- first_name: Seokhwan
full_name: Kim, Seokhwan
last_name: Kim
- first_name: Younggyun
full_name: Hahm, Younggyun
last_name: Hahm
- first_name: Zhong
full_name: He, Zhong
last_name: He
- first_name: Tony Kyungil
full_name: Lee, Tony Kyungil
last_name: Lee
- first_name: Enrico
full_name: Santus, Enrico
last_name: Santus
- first_name: Francis
full_name: Bond, Francis
last_name: Bond
- first_name: Seung-Hoon
full_name: Na, Seung-Hoon
last_name: Na
language:
- iso: eng
page: 344–354
place: Gyeongju, Republic of Korea
project:
- _id: '118'
name: 'TRR 318 - INF: TRR 318 - Project Area INF'
publication: Proceedings of the 29th International Conference on Computational Linguistics
publisher: International Committee on Computational Linguistics
status: public
title: '“Mama Always Had a Way of Explaining Things So I Could Understand”: A Dialogue
Corpus for Learning to Construct Explanations'
type: conference
user_id: '3900'
year: '2022'
...
---
_id: '34067'
author:
- first_name: Meghdut
full_name: Sengupta, Meghdut
id: '99459'
last_name: Sengupta
- first_name: Milad
full_name: Alshomary, Milad
id: '73059'
last_name: Alshomary
- first_name: Henning
full_name: Wachsmuth, Henning
id: '3900'
last_name: Wachsmuth
citation:
ama: 'Sengupta M, Alshomary M, Wachsmuth H. Back to the Roots: Predicting the Source
Domain of Metaphors using Contrastive Learning. In: Proceedings of the 2022
Workshop on Figurative Language Processing. ; 2022.'
apa: 'Sengupta, M., Alshomary, M., & Wachsmuth, H. (2022). Back to the Roots:
Predicting the Source Domain of Metaphors using Contrastive Learning. Proceedings
of the 2022 Workshop on Figurative Language Processing.'
bibtex: '@inproceedings{Sengupta_Alshomary_Wachsmuth_2022, title={Back to the Roots:
Predicting the Source Domain of Metaphors using Contrastive Learning}, booktitle={Proceedings
of the 2022 Workshop on Figurative Language Processing}, author={Sengupta, Meghdut
and Alshomary, Milad and Wachsmuth, Henning}, year={2022} }'
chicago: 'Sengupta, Meghdut, Milad Alshomary, and Henning Wachsmuth. “Back to the
Roots: Predicting the Source Domain of Metaphors Using Contrastive Learning.”
In Proceedings of the 2022 Workshop on Figurative Language Processing,
2022.'
ieee: 'M. Sengupta, M. Alshomary, and H. Wachsmuth, “Back to the Roots: Predicting
the Source Domain of Metaphors using Contrastive Learning,” 2022.'
mla: 'Sengupta, Meghdut, et al. “Back to the Roots: Predicting the Source Domain
of Metaphors Using Contrastive Learning.” Proceedings of the 2022 Workshop
on Figurative Language Processing, 2022.'
short: 'M. Sengupta, M. Alshomary, H. Wachsmuth, in: Proceedings of the 2022 Workshop
on Figurative Language Processing, 2022.'
date_created: 2022-11-14T08:49:07Z
date_updated: 2024-07-26T13:08:46Z
department:
- _id: '600'
- _id: '660'
language:
- iso: eng
project:
- _id: '127'
name: 'TRR 318 - C4: TRR 318 - Subproject C4 - Metaphern als Werkzeug des Erklärens'
publication: Proceedings of the 2022 Workshop on Figurative Language Processing
status: public
title: 'Back to the Roots: Predicting the Source Domain of Metaphors using Contrastive
Learning'
type: conference
user_id: '3900'
year: '2022'
...
---
_id: '46289'
author:
- first_name: Ngoc Chi
full_name: Banh, Ngoc Chi
id: '38219'
last_name: Banh
orcid: 0000-0002-5946-4542
- first_name: Ingrid
full_name: Scharlau, Ingrid
id: '451'
last_name: Scharlau
orcid: 0000-0003-2364-9489
- first_name: Katharina J.
full_name: Rohlfing, Katharina J.
id: '50352'
last_name: Rohlfing
citation:
ama: 'Banh NC, Scharlau I, Rohlfing KJ. Folgen wiederholter Negation auf die Aufmerksamkeit.
In: Bermeitinger C, Greve W, eds. 52. Kongress Der Deutschen Gesellschaft Für
Psychologie. Pabst Science Publishers. ; 2022.'
apa: Banh, N. C., Scharlau, I., & Rohlfing, K. J. (2022). Folgen wiederholter
Negation auf die Aufmerksamkeit. In C. Bermeitinger & W. Greve (Eds.), 52.
Kongress der Deutschen Gesellschaft für Psychologie.
bibtex: '@inproceedings{Banh_Scharlau_Rohlfing_2022, series={Pabst Science Publishers},
title={Folgen wiederholter Negation auf die Aufmerksamkeit}, booktitle={52. Kongress
der Deutschen Gesellschaft für Psychologie}, author={Banh, Ngoc Chi and Scharlau,
Ingrid and Rohlfing, Katharina J.}, editor={Bermeitinger, Christina and Greve,
Werner }, year={2022}, collection={Pabst Science Publishers} }'
chicago: Banh, Ngoc Chi, Ingrid Scharlau, and Katharina J. Rohlfing. “Folgen Wiederholter
Negation Auf Die Aufmerksamkeit.” In 52. Kongress Der Deutschen Gesellschaft
Für Psychologie, edited by Christina Bermeitinger and Werner Greve. Pabst
Science Publishers, 2022.
ieee: N. C. Banh, I. Scharlau, and K. J. Rohlfing, “Folgen wiederholter Negation
auf die Aufmerksamkeit,” in 52. Kongress der Deutschen Gesellschaft für Psychologie,
Hildesheim, Germany, 2022.
mla: Banh, Ngoc Chi, et al. “Folgen Wiederholter Negation Auf Die Aufmerksamkeit.”
52. Kongress Der Deutschen Gesellschaft Für Psychologie, edited by Christina Bermeitinger
and Werner Greve, 2022.
short: 'N.C. Banh, I. Scharlau, K.J. Rohlfing, in: C. Bermeitinger, W. Greve (Eds.),
52. Kongress Der Deutschen Gesellschaft Für Psychologie, 2022.'
conference:
end_date: 2022-10-15
location: Hildesheim, Germany
name: 52nd Congress of the German Psychological Society
start_date: 2022-09-10
date_created: 2023-08-03T14:00:36Z
date_updated: 2023-08-03T14:10:48Z
department:
- _id: '424'
- _id: '660'
editor:
- first_name: 'Christina '
full_name: 'Bermeitinger, Christina '
last_name: Bermeitinger
- first_name: 'Werner '
full_name: 'Greve, Werner '
last_name: Greve
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://www.uni-hildesheim.de/dgps2022/wp-content/uploads/2022/09/DGPsKongress2022_Abstractband_20220926.pdf
oa: '1'
project:
- _id: '115'
grant_number: '438445824'
name: 'TRR 318 - A05: TRR 318 - Echtzeitmessung der Aufmerksamkeit im Mensch-Roboter-Erklärdialog
(Teilprojekt A05)'
publication: 52. Kongress der Deutschen Gesellschaft für Psychologie
quality_controlled: '1'
series_title: Pabst Science Publishers
status: public
title: Folgen wiederholter Negation auf die Aufmerksamkeit
type: conference_abstract
user_id: '38219'
year: '2022'
...
---
_id: '51343'
abstract:
- lang: eng
text: This paper presents preliminary work on the formalization of three prominent
cognitive biases in the diagnostic reasoning process over epileptic seizures,
psychogenic seizures and syncopes. Diagnostic reasoning is understood as iterative
exploration of medical evidence. This exploration is represented as a partially
observable Markov decision process where the state (i.e., the correct diagnosis)
is uncertain. Observation likelihoods and belief updates are computed using a
Bayesian network which defines the interrelation between medical risk factors,
diagnoses and potential findings. The decision problem is solved via partially
observable upper confidence bounds for trees in Monte-Carlo planning. We compute
a biased diagnostic exploration policy by altering the generated state transition,
observation and reward during look ahead simulations. The resulting diagnostic
policies reproduce reasoning errors which have only been described informally
in the medical literature. We plan to use this formal representation in the future
to inversely detect and classify biased reasoning in actual diagnostic trajectories
obtained from physicians.
author:
- first_name: Dominik
full_name: Battefeld, Dominik
id: '91864'
last_name: Battefeld
orcid: 0000-0002-5480-0594
- first_name: Stefan
full_name: Kopp, Stefan
last_name: Kopp
citation:
ama: 'Battefeld D, Kopp S. Formalizing cognitive biases in medical diagnostic reasoning.
In: Proceedings of the 8th Workshop on Formal and Cognitive Reasoning.
; 2022.'
apa: Battefeld, D., & Kopp, S. (2022). Formalizing cognitive biases in medical
diagnostic reasoning. Proceedings of the 8th Workshop on Formal and Cognitive
Reasoning. 8th Workshop on Formal and Cognitive Reasoning (FCR), Trier.
bibtex: '@inproceedings{Battefeld_Kopp_2022, title={Formalizing cognitive biases
in medical diagnostic reasoning}, booktitle={Proceedings of the 8th Workshop on
Formal and Cognitive Reasoning}, author={Battefeld, Dominik and Kopp, Stefan},
year={2022} }'
chicago: Battefeld, Dominik, and Stefan Kopp. “Formalizing Cognitive Biases in Medical
Diagnostic Reasoning.” In Proceedings of the 8th Workshop on Formal and Cognitive
Reasoning, 2022.
ieee: D. Battefeld and S. Kopp, “Formalizing cognitive biases in medical diagnostic
reasoning,” presented at the 8th Workshop on Formal and Cognitive Reasoning (FCR),
Trier, 2022.
mla: Battefeld, Dominik, and Stefan Kopp. “Formalizing Cognitive Biases in Medical
Diagnostic Reasoning.” Proceedings of the 8th Workshop on Formal and Cognitive
Reasoning, 2022.
short: 'D. Battefeld, S. Kopp, in: Proceedings of the 8th Workshop on Formal and
Cognitive Reasoning, 2022.'
conference:
end_date: 2022-09-23
location: Trier
name: 8th Workshop on Formal and Cognitive Reasoning (FCR)
start_date: '2022-09-19 '
date_created: 2024-02-14T09:06:04Z
date_updated: 2024-10-31T10:00:01Z
ddc:
- '000'
department:
- _id: '660'
file:
- access_level: closed
content_type: application/pdf
creator: doba2
date_created: 2024-10-31T09:59:46Z
date_updated: 2024-10-31T09:59:46Z
file_id: '56846'
file_name: paper8.pdf
file_size: 261528
relation: main_file
success: 1
file_date_updated: 2024-10-31T09:59:46Z
has_accepted_license: '1'
keyword:
- Diagnostic reasoning
- Cognitive bias
- Cognitive model
- POMDP
- Bayesian network
- Epilepsy
- CDSS
language:
- iso: eng
project:
- _id: '128'
name: 'TRR 318 - C5: TRR 318 - Subproject C5'
publication: Proceedings of the 8th Workshop on Formal and Cognitive Reasoning
quality_controlled: '1'
status: public
title: Formalizing cognitive biases in medical diagnostic reasoning
type: conference
user_id: '91864'
year: '2022'
...
---
_id: '48780'
abstract:
- lang: eng
text: Explainable Artificial Intelligence (XAI) has mainly focused on static learning
tasks so far. In this paper, we consider XAI in the context of online learning
in dynamic environments, such as learning from real-time data streams, where models
are learned incrementally and continuously adapted over the course of time. More
specifically, we motivate the problem of explaining model change, i.e. explaining
the difference between models before and after adaptation, instead of the models
themselves. In this regard, we provide the first efficient model-agnostic approach
to dynamically detecting, quantifying, and explaining significant model changes.
Our approach is based on an adaptation of the well-known Permutation Feature Importance
(PFI) measure. It includes two hyperparameters that control the sensitivity and
directly influence explanation frequency, so that a human user can adjust the
method to individual requirements and application needs. We assess and validate
our method’s efficacy on illustrative synthetic data streams with three popular
model classes.
author:
- first_name: Maximilian
full_name: Muschalik, Maximilian
last_name: Muschalik
- first_name: Fabian
full_name: Fumagalli, Fabian
id: '93420'
last_name: Fumagalli
- first_name: Barbara
full_name: Hammer, Barbara
last_name: Hammer
- first_name: Eyke
full_name: Huellermeier, Eyke
id: '48129'
last_name: Huellermeier
citation:
ama: Muschalik M, Fumagalli F, Hammer B, Huellermeier E. Agnostic Explanation of
Model Change based on Feature Importance. KI - Künstliche Intelligenz.
2022;36(3-4):211-224. doi:10.1007/s13218-022-00766-6
apa: Muschalik, M., Fumagalli, F., Hammer, B., & Huellermeier, E. (2022). Agnostic
Explanation of Model Change based on Feature Importance. KI - Künstliche Intelligenz,
36(3–4), 211–224. https://doi.org/10.1007/s13218-022-00766-6
bibtex: '@article{Muschalik_Fumagalli_Hammer_Huellermeier_2022, title={Agnostic
Explanation of Model Change based on Feature Importance}, volume={36}, DOI={10.1007/s13218-022-00766-6},
number={3–4}, journal={KI - Künstliche Intelligenz}, publisher={Springer Science
and Business Media LLC}, author={Muschalik, Maximilian and Fumagalli, Fabian and
Hammer, Barbara and Huellermeier, Eyke}, year={2022}, pages={211–224} }'
chicago: 'Muschalik, Maximilian, Fabian Fumagalli, Barbara Hammer, and Eyke Huellermeier.
“Agnostic Explanation of Model Change Based on Feature Importance.” KI - Künstliche
Intelligenz 36, no. 3–4 (2022): 211–24. https://doi.org/10.1007/s13218-022-00766-6.'
ieee: 'M. Muschalik, F. Fumagalli, B. Hammer, and E. Huellermeier, “Agnostic Explanation
of Model Change based on Feature Importance,” KI - Künstliche Intelligenz,
vol. 36, no. 3–4, pp. 211–224, 2022, doi: 10.1007/s13218-022-00766-6.'
mla: Muschalik, Maximilian, et al. “Agnostic Explanation of Model Change Based on
Feature Importance.” KI - Künstliche Intelligenz, vol. 36, no. 3–4, Springer
Science and Business Media LLC, 2022, pp. 211–24, doi:10.1007/s13218-022-00766-6.
short: M. Muschalik, F. Fumagalli, B. Hammer, E. Huellermeier, KI - Künstliche Intelligenz
36 (2022) 211–224.
date_created: 2023-11-10T14:21:06Z
date_updated: 2025-01-16T16:19:35Z
department:
- _id: '660'
doi: 10.1007/s13218-022-00766-6
intvolume: ' 36'
issue: 3-4
keyword:
- Artificial Intelligence
language:
- iso: eng
page: 211-224
project:
- _id: '126'
name: 'TRR 318 - C3: TRR 318 - Subproject C3'
- _id: '117'
name: 'TRR 318 - C: TRR 318 - Project Area C'
- _id: '109'
grant_number: '438445824'
name: 'TRR 318: TRR 318 - Erklärbarkeit konstruieren'
publication: KI - Künstliche Intelligenz
publication_identifier:
issn:
- 0933-1875
- 1610-1987
publication_status: published
publisher: Springer Science and Business Media LLC
status: public
title: Agnostic Explanation of Model Change based on Feature Importance
type: journal_article
user_id: '93420'
volume: 36
year: '2022'
...
---
_id: '32247'
author:
- first_name: Milad
full_name: Alshomary, Milad
id: '73059'
last_name: Alshomary
- first_name: Jonas
full_name: Rieskamp, Jonas
id: '77643'
last_name: Rieskamp
- first_name: Henning
full_name: Wachsmuth, Henning
id: '3900'
last_name: Wachsmuth
citation:
ama: 'Alshomary M, Rieskamp J, Wachsmuth H. Generating Contrastive Snippets for
Argument Search. In: Proceedings of the 9th International Conference on Computational
Models of Argument. ; 2022:21-31. doi:http://dx.doi.org/10.3233/FAIA220138'
apa: Alshomary, M., Rieskamp, J., & Wachsmuth, H. (2022). Generating Contrastive
Snippets for Argument Search. Proceedings of the 9th International Conference
on Computational Models of Argument, 21–31. http://dx.doi.org/10.3233/FAIA220138
bibtex: '@inproceedings{Alshomary_Rieskamp_Wachsmuth_2022, title={Generating Contrastive
Snippets for Argument Search}, DOI={http://dx.doi.org/10.3233/FAIA220138},
booktitle={Proceedings of the 9th International Conference on Computational Models
of Argument}, author={Alshomary, Milad and Rieskamp, Jonas and Wachsmuth, Henning},
year={2022}, pages={21–31} }'
chicago: Alshomary, Milad, Jonas Rieskamp, and Henning Wachsmuth. “Generating Contrastive
Snippets for Argument Search.” In Proceedings of the 9th International Conference
on Computational Models of Argument, 21–31, 2022. http://dx.doi.org/10.3233/FAIA220138.
ieee: 'M. Alshomary, J. Rieskamp, and H. Wachsmuth, “Generating Contrastive Snippets
for Argument Search,” in Proceedings of the 9th International Conference on
Computational Models of Argument, 2022, pp. 21–31, doi: http://dx.doi.org/10.3233/FAIA220138.'
mla: Alshomary, Milad, et al. “Generating Contrastive Snippets for Argument Search.”
Proceedings of the 9th International Conference on Computational Models of
Argument, 2022, pp. 21–31, doi:http://dx.doi.org/10.3233/FAIA220138.
short: 'M. Alshomary, J. Rieskamp, H. Wachsmuth, in: Proceedings of the 9th International
Conference on Computational Models of Argument, 2022, pp. 21–31.'
date_created: 2022-06-28T09:03:30Z
date_updated: 2025-02-20T08:22:16Z
department:
- _id: '600'
- _id: '660'
doi: http://dx.doi.org/10.3233/FAIA220138
language:
- iso: eng
page: 21 - 31
project:
- _id: '118'
name: 'TRR 318 - INF: TRR 318 - Project Area INF'
publication: Proceedings of the 9th International Conference on Computational Models
of Argument
status: public
title: Generating Contrastive Snippets for Argument Search
type: conference
user_id: '3900'
year: '2022'
...
---
_id: '30840'
author:
- first_name: Milad
full_name: Alshomary, Milad
id: '73059'
last_name: Alshomary
- first_name: Roxanne
full_name: El Baff, Roxanne
last_name: El Baff
- first_name: Timon
full_name: Gurcke, Timon
id: '52174'
last_name: Gurcke
- first_name: Henning
full_name: Wachsmuth, Henning
id: '3900'
last_name: Wachsmuth
citation:
ama: 'Alshomary M, El Baff R, Gurcke T, Wachsmuth H. The Moral Debater: A Study
on the Computational Generation of Morally Framed Arguments. In: Proceedings
of the 60th Annual Meeting of the Association for Computational Linguistics.
; 2022:8782-8797.'
apa: 'Alshomary, M., El Baff, R., Gurcke, T., & Wachsmuth, H. (2022). The Moral
Debater: A Study on the Computational Generation of Morally Framed Arguments.
Proceedings of the 60th Annual Meeting of the Association for Computational
Linguistics, 8782–8797.'
bibtex: '@inproceedings{Alshomary_El Baff_Gurcke_Wachsmuth_2022, title={The Moral
Debater: A Study on the Computational Generation of Morally Framed Arguments},
booktitle={Proceedings of the 60th Annual Meeting of the Association for Computational
Linguistics}, author={Alshomary, Milad and El Baff, Roxanne and Gurcke, Timon
and Wachsmuth, Henning}, year={2022}, pages={8782–8797} }'
chicago: 'Alshomary, Milad, Roxanne El Baff, Timon Gurcke, and Henning Wachsmuth.
“The Moral Debater: A Study on the Computational Generation of Morally Framed
Arguments.” In Proceedings of the 60th Annual Meeting of the Association for
Computational Linguistics, 8782–97, 2022.'
ieee: 'M. Alshomary, R. El Baff, T. Gurcke, and H. Wachsmuth, “The Moral Debater:
A Study on the Computational Generation of Morally Framed Arguments,” in Proceedings
of the 60th Annual Meeting of the Association for Computational Linguistics,
2022, pp. 8782–8797.'
mla: 'Alshomary, Milad, et al. “The Moral Debater: A Study on the Computational
Generation of Morally Framed Arguments.” Proceedings of the 60th Annual Meeting
of the Association for Computational Linguistics, 2022, pp. 8782–97.'
short: 'M. Alshomary, R. El Baff, T. Gurcke, H. Wachsmuth, in: Proceedings of the
60th Annual Meeting of the Association for Computational Linguistics, 2022, pp.
8782–8797.'
date_created: 2022-04-06T14:05:45Z
date_updated: 2025-02-20T08:22:46Z
department:
- _id: '600'
- _id: '660'
language:
- iso: eng
page: 8782 - 8797
project:
- _id: '118'
name: 'TRR 318 - INF: TRR 318 - Project Area INF'
publication: Proceedings of the 60th Annual Meeting of the Association for Computational
Linguistics
status: public
title: 'The Moral Debater: A Study on the Computational Generation of Morally Framed
Arguments'
type: conference
user_id: '3900'
year: '2022'
...