NLP HD logo

Welcome to the Heidelberg Natural Language Processing Group

We aim to make machines understand language

Read more about our research
NLP HD logo

NEWS

news-card-image

Success in the SIGTYP 2024 Shared Task

Frederick Riemenschneider and Kevin Krahn won the constrained subtask of the SIGTYP 2024 shared task.

news-card-image

Letitia Parcalabescu gave a talk at the DKFZ

Letitia Parcalabescu gave an invited talk about her work at heidelberg.ai at the DKFZ.

news-card-image

Our Former ICL Student Laura Zeidler wins the 2023 GSCL Best Thesis Award

Former ICL student Laura Zeidler won the GSCL Best Thesis Award for her BA Thesis: “An Interpreted Dynamic Testsuite for the Evaluation of Semantic Similarity Metrics used in Parsing and Generation”. Congratulations!

news-card-image

New publications are out for ACL 2023, ACL Findings and SemEval 2023

We are happy to announce six new publications, with partners and colleagues, to be presented in Toronto in July.
Congratulations to all authors!

news-card-image

Celebrating the PhD Defense of Juri Opitz

We celebrate the successful PhD defense of Juri Opitz, for his thesis on Metrics of Graph-Based Meaning Representations with Applications from Parsing Evaluation to Explainable NLG Evaluation and Semantic Search. Congratulations!

Nov 23 We welcome Fabian Strobel to our group, as a new PhD student, affiliated with the Heidelberg Academy of Sciences, to work on Transliteration in Ancient Languages. Happy to have you on board, Fabian!
Sep 23 Letitia Parcalabescu will give keynote at LIMO 2023: Linguistic Insights from and for Multimodal Language Processing at KONVENS 2023 in Ingolstadt, about her research on Vision and Language Integration in Multimodal Machine Learning.
Sep 23 We are happy to announce our new publication Argument Quality Prediction for Ranking Documents, by Moritz Plenz, Raphael Buchmüller and Alexander Bondarenko. Accepted at Touché, CLEF 2023.
Sep 23 Frederick Riemenschneider presents his paper Graecia capta ferum victorem cepit. Detecting Latin Allusions to Ancient Greek Literature at ALP 2023, the First Workshop on Ancient Language Processing in Varna, Bulgaria.
Aug 22 ACCEPT organized a Shared Task on Predicting Validity and Novelty of Arguments. Our report will be presented in the ArgMining Workshop 2022.

RESEARCH TEAM

TEAM

Group Leader

Anette Frank

Anette Frank

Prof. Dr.
Chair of Computational Linguistics
Email (click to copy)
Semantic NLP for advanced & situated Natural Language Understanding

Researchers

Xiyan Fu

Xiyan Fu

MSc Computer Science PhD Student Computational Linguistics
Email (click to copy)
Event-based Reasoning
Natural Language Generation
Structured Meaning Representation
Letitia Parcalabescu

Letitia Parcalabescu

MSc Physics PhD Student Computational Linguistics
Email (click to copy)
Multimodal Learning
Vision and Language
Multimodal Understanding
Moritz Plenz

Moritz Plenz

MSc Physics PhD Student Computational Linguistics
Email (click to copy)
Argument Knowledge Graphs
ACCEPT

Frederick Riemenschneider

MA Computational Linguistics BA Classical Philology (Greek)
Email (click to copy)
Low-resource Languages
Multilingual Language Models

Associated Researchers

Phillip Richter-Pechanski

BA Computational Linguistics PhD Student Computational Linguistics
Email (click to copy)
Information Extraction from Medical Texts
Institute for Computational Cardiology

Fabian Strobel

BA Computational Linguistics & Jewish Studies, Heidelberg MSc Digital Humanities, Leipzig PhD Student Computational Linguistics
Email (click to copy)
Transcription and Transliteration
Heidelberg Academy of Sciences

Student Assistants

Janosch Gehring

Student research assistant
in the ACCEPT project
Email (click to copy)
Heidelberg University

“WE AIM
TO MAKE MACHINES
UNDERSTAND LANGUAGE.”

The main purpose of language is to encode and communicate information of all sorts.

Our research focuses on semantics — the study of meaning — and how a machine can assign meaning to utterances: words, sentences and texts, as humans can do. Our work is linguistically informed and applies advanced machine learning techniques.

Understanding of language requires knowledge of language and the world, the ability to perform reasoning, and situational context.
We study how to interface language with knowledge and how to ground language in the visual world. We investigate what can be left implicit in texts, given that language and knowledge interact, allowing humans to read between the lines.

For all this, humans and machines need knowledge:

about language, the world, people, social norms and the visual world.

“How do humans acquire and exchange knowledge?”
  • KNOWLEDGE-BASED LANGUAGE PROCESSING
  • MACHINE READING COMPREHENSION
  • COMMONSENSE INFERENCE IN SOCIAL SITUATIONS
  • COMPUTATIONAL ARGUMENTATION
“And how to express thoughts in language — accurately and naturally?”
  • NATURAL LANGUAGE GENERATION
  • MEANING-BASED NLG EVALUATION METRICS
  • RECONSTRUCTING IMPLICIT KNOWLEDGE IN TEXT
“How to represent the meaning of a discourse?”
  • STRUCTURED MEANING REPRESENTATIONS
  • REPRESENTING EVENTS AND THEIR PARTICIPANTS
  • RESOLVING ANAPHORA
“How do humans communicate in a visual situation?”
  • MULTIMODAL LANGUAGE PROCESSING
  • GROUNDING LANGUAGE IN IMAGES

PUBLICATIONS

PAPER

2024
+ -

ViLMA: A Zero-Shot Benchmark for Linguistic and Temporal Grounding in Video-Language Models

Kesen, I., Pedrotti, A., Dogan, M., Cafagna, M., Acikgoz, E., Parcalabescu, L., Calixto, I., Frank, A., Gatt, A., Erdem, A., Erdem, E. (2024)

arXiv preprint arXiv:2311.07022.

Graph Language Models

Plenz, M., Frank, A. (2024)

arXiv.

Heidelberg-Boston @ SIGTYP 2024 Shared Task: Enhancing Low-Resource Language Analysis With Character-Aware Hierarchical Transformers

Riemenschneider, F., Krahn, K. (2024)

Proceedings of the 6th Workshop on Research in Computational Linguistic Typology and Multilingual NLP, St. Julian's, Malta.
2023
+ -

SETI: Systematicity Evaluation of Textual Inference

Fu, X., Frank, A. (2023)

Findings of the Association for Computational Linguistics: ACL 2023, Toronto, Canada.

SMARAGD: Learning SMatch for Accurate and Rapid Approximate Graph Distance

Opitz, J., Meier, P., Frank, A. (2023)

Proceedings of the 15th International Conference on Computational Semantics (IWCS 2023) , Nancy, France.

AMR4NLI: Interpretable and robust NLI measures from semantic graphs

Opitz, J., Wein, S., Steen, J., Frank, A., Schneider, N. (2023)

Proceedings of the 15th International Conference on Computational Semantics (IWCS 2023), Nancy, France.

MM-SHAP: A Performance-agnostic Metric for Measuring Multimodal Contributions in Vision and Language Models & Tasks

Parcalabescu, L., Frank, A. (2023)

Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL’23), Toronto, Canada.

Similarity-weighted Construction of Contextualized Commonsense Knowledge Graphs for Knowledge-intense Argumentation Tasks

Plenz, M., Opitz, J., Heinisch, P., Cimiano, P., Frank, A. (2023)

Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Toronto, Canada.

Exploring Large Language Models for Classical Philology

Riemenschneider, F., Frank, A. (2023)

Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL’23), Toronto, Canada.

Graecia capta ferum victorem cepit. Detecting Latin Allusions to Ancient Greek Literature

Riemenschneider, F., Frank, A. (2023)

Proceedings of the Ancient Language Processing Workshop, Varna, Bulgaria.

On Measuring Faithfulness of Natural Language Explanations

Parcalabescu, L., Frank, A. (2023)

arXiv preprint arXiv:2311.07466.
2022
+ -

MAGMA – Multimodal Augmentation of Generative Models through Adapter-based Finetuning

Eichenberg, C., Black, S., Weinbach, S., Parcalabescu, L., Frank, A. (2022)

Findings of EMNLP.

Neural Natural Language Generation: A Survey on Multilinguality, Multimodality, Controllability and Learning

Erdem, E., Kuyu, M., Yagcioglu, S., Frank, A., Parcalabescu, L., Plank, B., Babii, A., Turuta, O., Erdem, A., Calixto, I., Lloret, E., Apostol, E., Truica, C., Sandrih, B., Gatt, A., Martincic-Ipsic, S., Berend, G., Korvel, G. (2022)

Journal of Artificial Intelligence Research (JAIR).

Strategies for Framing Argumentative Conclusion Generation

Heinisch, P., Frank, A., Opitz, J., Cimiano, P. (2022)

Proceedings of the 15th International Natural Language Generation Conference.

Data Augmentation for Improving the Prediction of Validity and Novelty of Argumentative Conclusions

Heinisch, P., Plenz, M., Opitz, J., Frank, A., Cimiano, P. (2022)

Proceedings of the 9th Workshop on Argument Mining (ArgMining), Online and in Gyeongju, Republic of Korea.

Overview of the 2022 Validity and Novelty Prediction Shared Task

Heinisch, P., Frank, A., Opitz, J., Plenz, M., Cimiano, P. (2022)

Proceedings of the 9th Workshop on Argument Mining (ArgMining), Online and in Gyeongju, Republic of Korea.

Better Smatch = Better Parser? AMR evaluation is not so simple anymore

Opitz, J., Frank, A. (2022)

Proceedings of the 3rd Workshop on Evaluation & Comparison of NLP Systems (Eval4NLP 2022) ,co-located at AACL 2022.

SBERT studies Meaning Representations: Decomposing Sentence Embeddings into Explainable Semantic Features

Opitz, J., Frank, A. (2022)

Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (AACL-IJCNLP 2022), Online.

VALSE💃: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena

Parcalabescu, L., Cafagna, M., Muradjan, L., Frank, A., Calixto, I., Gatt, A. (2022)

Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics.

A Dynamic, Interpreted CheckList for Meaning-oriented NLG Metric Evaluation – through the Lens of Semantic Similarity Rating

Zeidler, L., Opitz, J., Frank, A. (2022)

Proceedings of the 11th Joint Conference on Lexical and Computational Semantics (*SEM).

PROJECTS

2021
+ -
ACCEPT: Perspectivized Argument Knowledge Graphs for Deliberation Support (2021 – 2024)

ACCEPT: Perspectivized Argument Knowledge Graphs for Deliberation Support (2021 – 2024)

Joint project between Prof. Anette Frank (ICL, Heidelberg University) and Prof. Philipp Cimiano (University of Bielefeld) within the DFG priority program RATIO: Robust Argumentation Machines

2018
+ -
ExpLAIN: Between the Lines – Knowledge-based Analysis of Argumentation in a formal Argumentation
Inference System (2018 – 2021)

ExpLAIN: Between the Lines – Knowledge-based Analysis of Argumentation in a formal Argumentation Inference System (2018 – 2021)

Joint project between Prof. Anette Frank (ICL, Heidelberg University) and Prof. Heiner Stuckenschmidt (University of Mannheim) within the DFG priority program RATIO: Robust Argumentation Machines

The project will uncover missing explanatory links in argumentative texts, fill in automatically acquired knowledge that makes the structure of the argument explicit and establish and verify the knowledge-enhanced argumentation structure with a combination of formal reasoning and machine learning.

Go to project page
2015
+ -
DFG-Graduiertenkolleg AIPHES „Adaptive Informationsaufbereitung aus heterogenen Quellen“ (2015 – 2021)

DFG-Graduiertenkolleg AIPHES „Adaptive Informationsaufbereitung aus heterogenen Quellen“ (2015 – 2021)

The interdisciplinary research training group AIPHES was launched in April 2015. In a three-year program, 11 PhD candidates, as well as postdoctoral researchers and associated researchers will collaborate under the guiding theme of multi-document summarization of heterogeneous resources. Go to project page
Leibniz ScienceCampus "Empirical Linguistics and Computational Language Learning" (2015 – 2020)

Leibniz ScienceCampus "Empirical Linguistics and Computational Language Learning" (2015 – 2020)

The Leibniz ScienceCampus “Empirical Linguistics and Computational Language Modeling” aims to conduct innovative research to support the high-quality automatic annotation of large-scale corpus resources of German language through induction of domain-, genre- and variety-adaptive natural language processing models, to enable advanced empirical research in linguistics as well as innovative applications in the humanities and the social sciences. Go to project page

RELEASES

DATA

CODE

GitHub

Find our latest code on GitHub

You can find our latest code releases on our Heidelberg-NLP Github page!

Over 23 repositories containing code related to our recent publications.

NLP BLOG

View more Blog Posts