We’re excited that our colleague Yasir Mahmood is presenting two papers at the AAAI Conference in Singapore!🚀
👉 "Structure-Aware Encodings of Argumentation Properties for Clique-width" by Yasir Mahmood, Markus Hecher, Johanna Groven & Johannes K. Fichte
👉 "Can You Tell the Difference? Contrastive Explanations for ABox Entailments" by Patrick Koopmann, Yasir Mahmood, Axel Ngona & Balram Tiwari
Wishing you a great time and many inspiring exchanges with the AI community!
This week, our colleagues are presenting their latest research @iswc_conf in Nara, Japan!😊 We’re excited to share and discuss our research and to connect with the global Semantic Web community!🤝
Our colleague Moshood Yekini presented the paper "Tree-based OWL Class Expression Learner over Large Knowledge Graphs" by C. Demir, M. Yekini, M. Röder, Y. Mahmood & A. Ngonga at #ECMLPKDD2025 in Porto!🇵🇹 👏
👉Preprint: https://ecmlpkdd-storage.s3.eu-central-1.amazonaws.com/preprints/2025/research/preprint_ecml_pkdd_2025_research_470.pdf
Excited to be part of @IJCAI 2025 in Montréal 🇨🇦! Yasir Mahmood presented "Facets in Argumentation: A Formal Approach to Argument Significance" by Johannes K. Fichte, Nicholas Fröhlich, Markus Hecher, Victor Lagerkvist, Yasir Mahmood, Arne Meier & Jonathan Persson.👏
The preprint is available here 👉 https://ijcai-preprints.s3.us-west-1.amazonaws.com/2025/4105.pdf
🎉 Our group presented 3 papers at the @eswc_conf in Portoroz/Slovenia🇸🇮!
1️⃣ "Robustness Evaluation of Knowledge Graph Embedding Models Under Non-targeted Attacks"
🔗https://link.springer.com/chapter/10.1007/978-3-031-94575-5_15
2️⃣ "Evaluating Approximate Nearest Neighbour Search Systems on Knowledge Graph Embeddings"
🔗 https://link.springer.com/chapter/10.1007/978-3-031-94575-5_4
3️⃣ "ANTS: Abstractive Entity Summarization in Knowledge Graphs"
🔗 https://link.springer.com/chapter/10.1007/978-3-031-94575-5_8
Thanks to the ESWC community and the organising team for a great event!🙌😊
The other DICE contribution at #COLING2025 comes from Nikit, who presented "LOLA - An Open-Source Massively Multilingual Large Language Mode" by Nikit Srivastava, Denis Kuchelev, Tatiana Moteu Ngoli, Kshitij Shetty, Michael Röder, @hamadazahera, Diego Moussallem & Axel Ngonga.🤩 👏
👉 Want to find out more? Find the paper here: https://arxiv.org/abs/2409.11272
This paper presents LOLA, a massively multilingual large language model trained on more than 160 languages using a sparse Mixture-of-Experts Transformer architecture. Our architectural and implementation choices address the challenge of harnessing linguistic diversity while maintaining efficiency and avoiding the common pitfalls of multilinguality. Our analysis of the evaluation results shows competitive performance in natural language generation and understanding tasks. Additionally, we demonstrate how the learned expert-routing mechanism exploits implicit phylogenetic linguistic patterns to potentially alleviate the curse of multilinguality. We provide an in-depth look at the training process, an analysis of the datasets, and a balanced exploration of the model's strengths and limitations. As an open-source model, LOLA promotes reproducibility and serves as a robust foundation for future research. Our findings enable the development of compute-efficient multilingual models with strong, scalable performance across languages.
First conference in 2025!🤩 Many greetings to Daniel, who presented ‘Contextual Augmentation for Entity Linking using Large Language Models’ by Daniel Vollmers, @hamadazahera, Diego Moussallem and Axel Ngonga at #COLING2025 in Abu Dhabi🇦🇪 this week.👏👨💻 #DICEontour
👀 Would you like to find out more about the paper? Take a look here: https://papers.dice-research.org/2025/COLING_EL_Augmentation/public.pdf
DICE