Papers by Georg Rehm
ACL 2026 Industry Track: Overview (2026.acl-industry)
Copied to clipboard
| Challenge: | 153 papers were selected for presentation at the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026). |
| Approach: | the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026) organised a dedicated industry track. authors acknowledge the challenges in adapting language technologies for building novel and robust. |
| Outcome: | the industry track attracted 532 papers at the 64th Annual Meeting of the Association for Computational Linguistics . the submissions can be grouped into six different clusters: 1. RAG systems & enterprise knowledge AI; 2. agentic systems and workflows; 3. Language technologies and their applications are an integral and critical part of our daily lives. |
The European Language Technology Landscape in 2020: Language-Centric and Human-Centric AI for Cross-Cultural Communication in Multilingual Europe (2020.lrec-1)
Copied to clipboard
Georg Rehm, Katrin Marheinecke, Stefanie Hegele, Stelios Piperidis, Kalina Bontcheva, Jan Hajič, Khalid Choukri, Andrejs Vasiļjevs, Gerhard Backfried, Christoph Prinz, José Manuel Gómez-Pérez, Luc Meertens, Paul Lukowicz, Josef van Genabith, Andrea Lösch, Philipp Slusallek, Morten Irgens, Patrick Gatellier, Joachim Köhler, Laure Le Bars, Dimitra Anastasiou, Albina Auksoriūtė, Núria Bel, António Branco, Gerhard Budin, Walter Daelemans, Koenraad De Smedt, Radovan Garabík, Maria Gavriilidou, Dagmar Gromann, Svetla Koeva, Simon Krek, Cvetana Krstev, Krister Lindén, Bernardo Magnini, Jan Odijk, Maciej Ogrodniczuk, Eiríkur Rögnvaldsson, Mike Rosner, Bolette Pedersen, Inguna Skadiņa, Marko Tadić, Dan Tufiș, Tamás Váradi, Kadri Vider, Andy Way, François Yvon
| Challenge: | Language Technologies (LTs) are a powerful means to break down language barriers impacting business, cross-lingual and cross-cultural communication in Europe. |
| Approach: | They present an overview of the European LT landscape and the current state of play in industry and the LT market. |
| Outcome: | The present study outlines funding programmes, activities, actions and challenges in the different countries with regard to LT, including the current state of play in industry and the LT market. |
A Dataset of German Legal Documents for Named Entity Recognition (2020.lrec-1)
Copied to clipboard
| Challenge: | a dataset developed for Named Entity Recognition in German federal court decisions is available under a CC-BY 4.0 license. |
| Approach: | They describe a dataset developed for Named Entity Recognition in German federal court decisions. |
| Outcome: | The proposed dataset was developed for training an NER service for German legal documents in the EU project Lynx. |
Common European Language Data Space (2024.lrec-main)
Copied to clipboard
Georg Rehm, Stelios Piperidis, Khalid Choukri, Andrejs Vasiļjevs, Katrin Marheinecke, Victoria Arranz, Aivars Bērziņš, Miltos Deligiannis, Dimitris Galanis, Maria Giagkou, Katerina Gkirtzou, Dimitris Gkoumas, Annika Grützner-Zahn, Athanasia Kolovou, Penny Labropoulou, Andis Lagzdiņš, Elena Leitner, Valérie Mapelli, Hélène Mazo, Simon Ostermann, Stefania Racioppa, Mickaël Rigault, Leon Voukoutis
| Challenge: | the Common European Language Data Space (LDS) is an integral part of the EU data strategy, which aims at developing a single market for data. |
| Approach: | the Common European Language Data Space (LDS) is an integral part of the EU data strategy . its decentralised technical infrastructure and governance scheme are currently being developed by the LDS project . |
| Outcome: | the Common European Language Data Space (LDS) is an integral part of the EU data strategy, which aims at developing a single market for data. |
Automatic and Manual Web Annotations in an Infrastructure to handle Fake News and other Online Media Phenomena (L18-1)
Copied to clipboard
| Challenge: | a growing number of people consume news online, but there are different types of "fake news" many online news outlets use the same journalistic principles that have been in use for newspapers for decades, especially factchecking. |
| Approach: | They propose a metadata scheme to enable users to handle "fake news" they also propose 'filter bubble' effect and abuse language . |
| Outcome: | The proposed metadata scheme enables standardisation of these phenomena in online media. |
Aspect-based Document Similarity for Research Papers (2020.coling-main)
Copied to clipboard
| Challenge: | Traditional document similarity measures do not consider in what aspects two documents are similar. |
| Approach: | They extend document similarity with aspect information by performing a pairwise document classification task. |
| Outcome: | The proposed approach is best performing on 172,073 research paper pairs from the ACL Anthology and CORD-19 corpus. |
European Language Grid: A Joint Platform for the European Language Technology Community (2021.eacl-demos)
Copied to clipboard
Georg Rehm, Stelios Piperidis, Kalina Bontcheva, Jan Hajic, Victoria Arranz, Andrejs Vasiļjevs, Gerhard Backfried, Jose Manuel Gomez-Perez, Ulrich Germann, Rémi Calizzano, Nils Feldhus, Stefanie Hegele, Florian Kintzel, Katrin Marheinecke, Julian Moreno-Schneider, Dimitris Galanis, Penny Labropoulou, Miltos Deligiannis, Katerina Gkirtzou, Athanasia Kolovou, Dimitris Gkoumas, Leon Voukoutis, Ian Roberts, Jana Hamrlova, Dusan Varis, Lukas Kacena, Khalid Choukri, Valérie Mapelli, Mickaël Rigault, Julija Melnika, Miro Janosik, Katja Prinz, Andres Garcia-Silva, Cristian Berrio, Ondrej Klejch, Steve Renals
| Challenge: | Europe is a multilingual society, in which dozens of languages are spoken. |
| Approach: | They describe the European Language Grid, which is targeted to evolve into the primary platform and marketplace for LT in Europe by providing one umbrella platform for the European LT landscape. |
| Outcome: | The European Language Grid (ELG) will provide access to 1300 services for all European languages as well as thousands of data sets. |
Language Technology for Multilingual Europe: An Analysis of a Large-Scale Survey regarding Challenges, Demands, Gaps and Needs (L18-1)
Copied to clipboard
| Challenge: | a survey titled "Language Technology for Multilingual Europe" was conducted between May and June 2017 . 634 participants in 52 countries responded to the survey . |
| Approach: | a large-scale survey was conducted to assess the best multilingual technologies in Europe. a total of 634 participants in 52 countries responded to the survey. |
| Outcome: | The study aims to identify the biggest challenges, obstacles and gaps in European language technology . participants were encouraged to share concrete suggestions and recommendations on how present challenges can be turned into opportunities . |
Symmetric Dot-Product Attention for Efficient Training of BERT Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | Transformer-based models are stretched to enormous sizes, requiring increasingly larger training datasets and unsustainable amount of compute resources. |
| Approach: | They propose an alternative compatibility function for the Transformer-based attention mechanism that exploits an overlap in the learned representation of the traditional scaled dot-product attention mechanism. |
| Outcome: | The proposed model achieves 79.36 on the GLUE benchmark against 78.74 for the traditional implementation and reduces the number of trainable parameters by 6%. |
Generating Extended and Multilingual Summaries with Pre-trained Transformers (2022.lrec-1)
Copied to clipboard
| Challenge: | Almost all summarisation methods focus on a single language and short summaries. |
| Approach: | They propose a dataset for extended summarisation tailored for 11 sentences . they compare three multilingual transformer models on extractive and abstractive summarization tasks . |
| Outcome: | The proposed dataset is tailored for extended summaries of approx. 11 sentences. |
Making Metadata Fit for Next Generation Language Technology Platforms: The Metadata Schema of the European Language Grid (2020.lrec-1)
Copied to clipboard
Penny Labropoulou, Katerina Gkirtzou, Maria Gavriilidou, Miltos Deligiannis, Dimitris Galanis, Stelios Piperidis, Georg Rehm, Maria Berger, Valérie Mapelli, Michael Rigault, Victoria Arranz, Khalid Choukri, Gerhard Backfried, José Manuel Gómez-Pérez, Andres Garcia-Silva
| Challenge: | Metadata are a key factor in the management, sharing and usage of digital assets . the European Language Grid project aims to be the primary hub and marketplace for industry-relevant Language Technology in Europe. |
| Approach: | They propose a rich metadata schema catering for the description of Language Resources and Technologies. |
| Outcome: | The proposed schema powers the European Language Grid platform that aims to be the primary hub and marketplace for industry-relevant Language Technology in Europe. |
HiStruct+: Improving Extractive Text Summarization with Hierarchical Structure Information (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing models that treat texts as linear sequences do not include hierarchical structure information. |
| Approach: | They propose to inject hierarchical structure information into an extractive summarization model by combining hierarchically structured text with a pre-trained Transformer language model. |
| Outcome: | The proposed model outperforms a baseline model on PubMed and arXiv datasets and the hierarchical structure information is not injected. |
Semantic Relations between Text Segments for Semantic Storytelling: Annotation Tool - Dataset - Evaluation (2022.lrec-1)
Copied to clipboard
| Challenge: | Semantic Storytelling is the goal of the future to generate stories based on extracted, processed, classified and annotated information from large content resources. |
| Approach: | They propose to create an automatic classifier for semantic relations between extracted text segments from different news articles. |
| Outcome: | The proposed method has high accuracy scores and is validated by a trained model. |
Neighborhood Contrastive Learning for Scientific Document Representations with Citation Embeddings (2022.emnlp-main)
Copied to clipboard
| Challenge: | Prior work relies on discrete citation relations to generate contrast samples, but discrete ones enforce a hard cut-off to similarity. |
| Approach: | They propose to use nearest neighbor sampling to learn continuous similarity and to sample hard-to-learn negatives and positives by controlling the sampling margin between them. |
| Outcome: | The proposed method outperforms the state-of-the-art on the SciDocs benchmark and can train (or tune) language models sample-efficiently. |
Named Entities in Medical Case Reports: Corpus and Experiments (2020.lrec-1)
Copied to clipboard
| Challenge: | Only very few annotated corpora in the medical domain exist. |
| Approach: | They propose to annotate medical entities in case reports from PubMed Central's open access library. |
| Outcome: | The proposed corpus is the first of its kind to be made available to the scientific community in English. |
Making a Semantic Event-type Ontology Multilingual (2022.lrec-1)
Copied to clipboard
| Challenge: | a new version of SynSemClass is being developed for use in natural language processing . the ontology is a bilingual resource with no links to a valency lexicon . |
| Approach: | They propose to add German entries to the SynSemClass Event-type Ontology . they propose to use the ontology as a human-readable and human-understandable database . |
| Outcome: | The proposed extension of SynSemClass Event-type Ontology is presented in a paper in czech republic . the ontology provides curated data for NLP experiments with cross-lingual synonyms . |
European Language Grid: An Overview (2020.lrec-1)
Copied to clipboard
Georg Rehm, Maria Berger, Ela Elsholz, Stefanie Hegele, Florian Kintzel, Katrin Marheinecke, Stelios Piperidis, Miltos Deligiannis, Dimitris Galanis, Katerina Gkirtzou, Penny Labropoulou, Kalina Bontcheva, David Jones, Ian Roberts, Jan Hajič, Jana Hamrlová, Lukáš Kačena, Khalid Choukri, Victoria Arranz, Andrejs Vasiļjevs, Orians Anvari, Andis Lagzdiņš, Jūlija Meļņika, Gerhard Backfried, Erinç Dikici, Miroslav Janosik, Katja Prinz, Christoph Prinz, Severin Stampler, Dorothea Thomas-Aniola, José Manuel Gómez-Pérez, Andres Garcia Silva, Christian Berrío, Ulrich Germann, Steve Renals, Ondrej Klejch
| Challenge: | European LT business is dominated by hundreds of SMEs and a few large players, with technologies that outperform the global players. |
| Approach: | European Language Grid (ELG) project addresses this by establishing the ELG as the primary platform for LT in Europe. |
| Outcome: | European Language Grid (ELG) will be primary platform for LT in Europe . it will provide access to hundreds of commercial and non-commercial LTs for all European languages, including running tools and services as well as data sets and resources. |
Orchestrating NLP Services for the Legal Domain (2020.lrec-1)
Copied to clipboard
Julian Moreno-Schneider, Georg Rehm, Elena Montiel-Ponsoda, Víctor Rodriguez-Doncel, Artem Revenko, Sotirios Karampatakis, Maria Khvalchik, Christian Sageder, Jorge Gracia, Filippo Maganza
| Challenge: | a legal technology system under development in the EU is based on semantic services and a multilingual legal knowledge Graph. |
| Approach: | They propose a workflow manager that enables flexible orchestration of workflows . they describe different use cases and propose prototypical solutions . |
| Outcome: | The proposed system is based on a set of natural language processing and document curation services and a multilingual legal knowledge graph that contains semantic information and meaningful references to legal documents. |
ACL 2025 Industry Track: Overview (2025.acl-industry)
Copied to clipboard
| Challenge: | 108 papers were selected for presentation at the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025). |
| Approach: | 108 papers were selected for presentation at the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025). |
| Outcome: | The industry track attracted 421 paper submissions at the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025). |
A Dataset of Offensive German Language Tweets Annotated for Speech Acts (2022.lrec-1)
Copied to clipboard
| Challenge: | Using speech act analysis, we analysed 600 offensive and non-offensive tweets in germany . a large body of research exists on the pragmatic characteristics of offensive language . |
| Approach: | They analyze German offensive and non-offensive tweets and use a subset of the 2019 GermEval Shared Task on the Identification of Offensive Language dataset. |
| Outcome: | The proposed dataset includes 600 offensive and non-offensive tweets annotated for speech acts in germany. |
Abstractive Text Summarization based on Language Model Conditioning and Locality Modeling (2020.lrec-1)
Copied to clipboard
Dmitrii Aksenov, Julian Moreno-Schneider, Peter Bourgonje, Robert Schwarzenberg, Leonhard Hennig, Georg Rehm
| Challenge: | Abstractive summarization is an NLP task with many real-world applications. |
| Approach: | They propose to use a pre-trained language model to train a Transformer-based neural model . they propose a new method of BERT-windowing to allow chunk-wise processing of texts longer than the BERT window size . |
| Outcome: | The proposed model outperforms baseline models on CNN/Daily Mail dataset and shows its superiority on German dataset. |
European Language Grid: One Year after (2024.lrec-main)
Copied to clipboard
Georg Rehm, Stelios Piperidis, Dimitris Galanis, Penny Labropoulou, Maria Giagkou, Miltos Deligiannis, Leon Voukoutis, Martin Courtois, Julian Moreno-Schneider, Katrin Marheinecke
| Challenge: | The European Language Grid (ELG) is a cloud platform for the whole European Language Technology community. |
| Approach: | The article provides an overview of the current state of ELG in terms of user adoption and number of language resources and technologies available in early 2024. |
| Outcome: | The European Language Grid (ELG) is a cloud platform for the whole European Language Technology community. |
FoRC4CL: A Fine-grained Field of Research Classification and Annotated Dataset of NLP Articles (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing systems for categorising scientific knowledge are lacking in many digital repositories. |
| Approach: | They propose to classify papers in the ACL Anthology using a hierarchical taxonomy of core CL/NLP topics and sub-topics. |
| Outcome: | The proposed corpus of 1,500 ACL Anthology publications is annotated with their main contributions using a hierarchical taxonomy of core CL/NLP topics and sub-topics. |
A CURATEd CATalog: Rethinking the Extraction of Pretraining Corpora for Mid-Resourced Languages (2024.lrec-main)
Copied to clipboard
Jorge Palomar-Giner, Jose Javier Saiz, Ferran Espuña, Mario Mina, Severino Da Dalt, Joan Llop, Malte Ostendorff, Pedro Ortiz Suarez, Georg Rehm, Aitor Gonzalez-Agirre, Marta Villegas
| Challenge: | CATalog 1.0 is the largest text corpus in Catalan to date . CURATE is a pipeline that can be parallelizable to run in high performance clusters . |
| Approach: | They propose a data pipeline that uses binary filters to filter documents based on text quality . they optimised the pipeline to run in high performance clusters . |
| Outcome: | The proposed pipeline is optimized for high performance cluster environments and runs in high performance. |
Claim Extraction and Law Matching for COVID-19-related Legislation (2022.lrec-1)
Copied to clipboard
| Challenge: | Existing approaches to extract legal claims from news articles and match them with applicable laws are difficult for laypersons to learn since news articles do not refer to underlying laws. |
| Approach: | They propose an automated approach to extract legal claims from news articles and match the claims with applicable laws. |
| Outcome: | The proposed model achieves 46.7 F1 for claim extraction and 91.4 F1 law matching, despite conceptual limitations. |