Skip to content
View nfelnlp's full-sized avatar
๐ŸŽฏ
Focusing
๐ŸŽฏ
Focusing

Highlights

  • Pro

Organizations

@DFKI-NLP

Block or report nfelnlp

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this userโ€™s behavior. Learn more about reporting abuse.

Report abuse
nfelnlp/README.md

๐Ÿ‘‹ Hi there

I am a researcher and software engineer at the Speech and Language Technology department of the German Research Center for Artificial Intelligence (DFKI) in Berlin and a PhD candidate in Computer Science advised by Prof. Dr.-Ing. Sebastian Mรถller starting April 2021. Part of the European Language Grid technical team from January 2020 to March 2021.

๐Ÿ”ญ Research

Interpretability and Analysis of NLP Models, especially making exploration of model behavior accessible to more user groups through interactive explanations.

๐Ÿ“ฐ Publications

InterroLang: Exploring NLP Models and Datasets through Dialogue-based Explanations (Feldhus et al., 2023) @ EMNLP 2023 Findings

Thermostat: A Large Collection of NLP Model Explanations and Analysis Tools (Feldhus et al., 2021) @ EMNLP 2021 System Demonstrations

Inseq: An Interpretability Toolkit for Sequence Generation Models (Sarti et al., 2023) @ ACL 2023 System Demonstrations

More of my publications on my homepage and on Google Scholar

๐Ÿ›๏ธ Education

PhD at TU Berlin (2021-2025)
M.Sc. in Cognitive Systems at Uni Potsdam (2016-2020)
B.A. in Computational Linguistics at Uni Heidelberg (2013-2016)

๐Ÿ“Œ Links

๐ŸฆŠ GitLab: @nfel
๐Ÿฆ Twitter: @nfelnlp
๐Ÿ˜ Mastodon (sigmoid.social): @feldhus

Pinned Loading

  1. inseq-team/inseq inseq-team/inseq Public

    Interpretability for sequence generation models ๐Ÿ› ๐Ÿ”

    Python 373 36

  2. DFKI-NLP/InterroLang DFKI-NLP/InterroLang Public

    InterroLang: Exploring NLP Models and Datasets through Dialogue-based Explanations [EMNLP 2023 Findings]

    Python 5 1

  3. DFKI-NLP/SMV DFKI-NLP/SMV Public

    Code and data for the ACL 2023 NLReasoning Workshop paper "Saliency Map Verbalization: Comparing Feature Importance Representations from Model-free and Instruction-based Methods" (Feldhus et al., 2โ€ฆ

    Python 8 1

  4. DFKI-NLP/LLMCheckup DFKI-NLP/LLMCheckup Public

    Code for the NAACL 2024 HCI+NLP Workshop paper "LLMCheckup: Conversational Examination of Large Language Models via Interpretability Tools and Self-explanation" (Wang et al. 2024)

    Python 10 1

  5. DFKI-NLP/emp-exp DFKI-NLP/emp-exp Public

    Jsonnet 7 2

  6. DFKI-NLP/thermostat DFKI-NLP/thermostat Public

    Collection of NLP model explanations and accompanying analysis tools

    Jsonnet 144 8