Menu
Parisa Safikhani

Parisa Safikhani

Research Area Research Infrastructure and Methods
Researcher
  • +49 511 450670-468
Projects

List of projects

Unfortunately, there is no result available for this search combination
BMBF data portal on education and research/StaGuS - Basic and structural statistical data (2017-2021)
Show 00 more projects
Publications

List of publications

Unfortunately, there is no result available for this search combination

AutoML meets hugging face: Domain-aware pretrained model selection for text classification.

Safikhani, P., & Broneske, D. (2025).
AutoML meets hugging face: Domain-aware pretrained model selection for text classification. In A. Ebrahimi, S. Haider, E. Liu, M. L. Pacheco, & S. Wein (Hrsg.), Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop). Albuquerque, USA: Association for Computational Linguistics.
Abstract

The effectiveness of embedding methods is crucial for optimizing text classification performance in Automated Machine Learning (AutoML). However, selecting the most suitable pre-trained model for a given task remains challenging. This study introduces the Corpus-Driven Domain Mapping (CDDM) pipeline, which utilizes a domain-annotated corpus of pre-fine-tuned models from the Hugging Face Model Hub to improve model selection. Integrating these models into AutoML systems significantly boosts classification performance across multiple datasets compared to baseline methods. Despite some domain recognition inaccuracies, results demonstrate CDDM’s potential to enhance model selection, streamline AutoML workflows, and reduce computational costs.

Framing and BERTology: A data-centric approach to integration of linguistic features into transformer-based pre-trained language models.

Avetisyan, H., Safikhani, P., & Broneske, D. (2024).
Framing and BERTology: A data-centric approach to integration of linguistic features into transformer-based pre-trained language models. In Arai, K. (Hrsg.), Intelligent Systems and Applications (S. 81-90). Cham: Springer. https://doi.org/10.1007/978-3-031-47718-8

Laughing out loud – Exploring AI-generated and human-generated humor.

Safikhani, P., Avetisyan, H., & Broneske, D. (2023).
Laughing out loud – Exploring AI-generated and human-generated humor. Computer Science & Information Technology (CS & IT), 2023, 59-76.

Enhancing AutoNLP with fine-tuned BERT models: An evaluation of text representation methods for AutoPyTorch.

Safikhani, P., & Broneske, D. (2023).
Enhancing AutoNLP with fine-tuned BERT models: An evaluation of text representation methods for AutoPyTorch. In D. C. Wyld & D. Nagamalai (Hrsg.), Computer Science & Information Technology (CS & IT) (S. 23-38). Chennai, Tamil Nadu, India: AIRCC Publishing Corporation.

Automated occupation coding with hierarchical features: A data-centric approach to classification with pre-trained language models.

Safikhani, P., Avetisyan, H., Föste-Eggers, D., & Broneske, D. (2023).
Automated occupation coding with hierarchical features: A data-centric approach to classification with pre-trained language models. Discover Artificial Intelligence 3, 2023(6). https://doi.org/10.1007/s44163-023-00050-y
Show 00 more publications
Presentations

List of presentations & conferences

Unfortunately, there is no result available for this search combination

AutoML meets hugging face: Domain-aware pretrained model selection for text classification.

Safikhani, P. (2025, April/Mai).
AutoML meets hugging face: Domain-aware pretrained model selection for text classification. Poster auf der Konferenz 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies, Albuquerque, USA.
Abstract

The effectiveness of embedding methods is crucial for optimizing text classification performance in Automated Machine Learning (AutoML). However, selecting the most suitable pre-trained model for a given task remains challenging. This study introduces the Corpus-Driven Domain Mapping (CDDM) pipeline, which utilizes a domain-annotated corpus of pre-fine-tuned models from the Hugging Face Model Hub to improve model selection. Integrating these models into AutoML systems significantly boosts classification performance across multiple datasets compared to baseline methods. Despite some domain recognition inaccuracies, results demonstrate CDDM’s potential to enhance model selection, streamline AutoML workflows, and reduce computational costs.

Static and dynamic contextual embedding for AutoML in text classification tasks.

Safikhani, P. (2025, März).
Static and dynamic contextual embedding for AutoML in text classification tasks. Vortrag auf der Konferenz International Conference on Natural Language Processing (ICNLP 2025), Guangzhou, China.

Enhancing AutoML for NLP: Context-aware hyperparameter tuning and text representation using large language models.

Safikhani, P. (2025, Februar).
Enhancing AutoML for NLP: Context-aware hyperparameter tuning and text representation using large language models. Vortrag auf dem Kolloquium Doktorandentag at Otto von Guericke University Magdeburg, Faculty of Computer Science, Magdeburg, Germany.

NLP, LLMs und AutoNLP für die Sozialwissenschaften.

Safikhani, P. (2024, April).
NLP, LLMs und AutoNLP für die Sozialwissenschaften. Poster auf der Tagung DZHW-Forschungstag 2024, Deutsches Zentrum für Hochschul- und Wissenschaftsforschung (DZHW), Hannover.

Laughing out loud – Exploring AI-generated and human-generated humor.

Avetisyan, H., Safikhani, P., & Broneske, D. (2023, Dezember).
Laughing out loud – Exploring AI-generated and human-generated humor. Vortrag auf der Konferenz International Conference on NLP & Artificial Intelligence Techniques (NLAI 2023), Computer Science & Information Technology (CS & IT), Sydney, Australia.

From manual tuning to AutoNLP.

Safikhani, P. (2023, Oktober).
From manual tuning to AutoNLP. Poster auf der Konferenz The Future of Higher Education and Science – A Turn of the Times?, Deutsches Zentrum für Hochschul- und Wissenschaftsforschung (DZHW), Leibniz Forschungszentrum Wissenschaft und Gesellschaft (LCSS), Hannover, Deutschland.

Enhancing AutoNLP with fine-tuned BERT model:​ An evaluation of text representation methods for AutoPyTorch.

Safikhani, P. (2023, September).
Enhancing AutoNLP with fine-tuned BERT model:​ An evaluation of text representation methods for AutoPyTorch. Vortrag auf der Konferenz 4th International Conference on Machine Learning Techniques and NLP (MLNLP 2023), Copenhagen, Denmark.

Framing and BERTology: ​A data-centric approach to integration of linguistic features into transformer-based pre-trained language models​.

Avetisyan, H., Safikhani, P., & Broneske, D. (2023, September).
Framing and BERTology: ​A data-centric approach to integration of linguistic features into transformer-based pre-trained language models​. Vortrag auf der Konferenz Intelligent Systems Conference (IntelliSys 2023), Amsterdam, The Netherlands.

Automatisierte Codierung von Berufsangaben mittels BERT.

Föste-Eggers, D., Avetisyan, H., Safikhani, P., & Broneske, D. (2021, Dezember).
Automatisierte Codierung von Berufsangaben mittels BERT. Vortrag auf der Tagung Methodische Herausforderungen in der empirischen Bildungsforschung, Thementagung der digiGEBF21, DIPF | Leibniz-Institut für Bildungsforschung und Bildungsinformation, Frankfurt am Main.
Show 00 more presentations & conferences

In collaboration with

Hayastan Avetisyan

Hayastan Avetisyan

David Broneske

Dr. David Broneske