Explanipedia

ReFactX: Scalable Reasoning with Reliable Facts via Constrained Generation Open

Riccardo Pozzi, Matteo Palmonari, Andrea Coletta, Luigi Bellomarini, Jens Lehmann , et al. · 2025

Aligning Knowledge Graphs and Language Models for Factual Accuracy Open

Kossi Amouzouvi, Jens Lehmann, Sahar Vahdati · 2025

Large language models like GPT-4, Gemini, and Claude have transformed natural language processing (NLP) tasks such as question answering, dialogue generation, summarization, and so forth; yet their susceptibility to hallucination stands as…

SMART: Relation-Aware Learning of Geometric Representations for Knowledge Graphs Open

Kossi Amouzouvi, Bowen Song, Andrea Coletta, Luigi Bellomarini, Jens Lehmann , et al. · 2025

Knowledge graph representation learning approaches provide a mapping between symbolic knowledge in the form of triples in a knowledge graph (KG) and their feature vectors. Knowledge graph embedding (KGE) models often represent relations in…

IntelliLung: Advancing Safe Mechanical Ventilation using Offline RL with Hybrid Actions and Clinically Aligned Rewards Open

Muhammad Hamza Yousuf, Jason H. Li, Sahar Vahdati, Raphael Theilen, Jakob Wittenstein , et al. · 2025

Invasive mechanical ventilation (MV) is a life-sustaining therapy for critically ill patients in the intensive care unit (ICU). However, optimizing its settings remains a complex and error-prone process due to patient-specific variability.…

SimE: A Knowledge Graph Embedding Model to Encode Self-Similar Structures Through Algebraic and Geometric Transformations Open

Kossi Amouzouvi, Yashrajsinh Chudasama, Disha Purohit, Ariam Rivas, Bowen Song , et al. · 2025

Knowledge Graphs (KGs), with their intricate hierarchies and semantic relationships, present unique challenges for graph representation learning, necessitating tailored approaches to effectively capture and encode their complex structures …

BALI—A Benchmark for Accelerated Language Model Inference Open

Lena Jurkschat, Preetam Gattogi, Sahar Vahdati, Jens Lehmann · 2025

The rise of Large Language Models (LLMs) has revolutionized natural language processing, enabling advancements across diverse applications, including chatbots, live translators, content generation, virtual assistants, and domain-specific a…

Learning Temporal Knowledge Graphs via Time-Sensitive Graph Attention Open

J.Y. Shen, Chengjin Xu, Y. Liu, Xuhui Jiang, J. S. Li , et al. · 2025

Embedding-based graph representation learning methods have shown strong performance on knowledge graphs (KGs), but most are designed for static settings and struggle to model temporal dynamics. To address this gap, we present TimeGate, a n…

Temporal relevance for representing learning over temporal knowledge graphs Open

Bowen Song, Kossi Amouzouvi, Chengjin Xu, Maocai Wang, Jens Lehmann , et al. · 2024

Representation learning for link prediction is one of the leading approaches to deal with incompleteness problem of real world knowledge graphs. Such methods are often called knowledge graph embedding models which represent entities and re…

X-Vent: ICU Ventilation with Explainable Model-Based Reinforcement Learning Open

Farhad Safaei, Miloš Nenadović, Roman Ließner, Raphael Theilen, Jakob Wittenstein , et al. · 2024

This study introduces a Model-Based Deep Reinforcement Learning approach to enhance the effectiveness and transparency of mechanical ventilation treatment in the critical care setting of Intensive Care Units (ICUs). Distinct from conventio…

BanglaQuAD: A Bengali Open-domain Question Answering Dataset Open

Md Rashad Al Hasan Rony, Sudipto Kumar Shaha, Rakib Hasan, Sumon Kanti Dey, Amzad Hossain Rafi , et al. · 2024

Bengali is the seventh most spoken language on earth, yet considered a low-resource language in the field of natural language processing (NLP). Question answering over unstructured text is a challenging NLP task as it requires understandin…

Conversational Question Answering over Knowledge Graphs Open

Endri Kacupaj, Kuldeep Singh, Maria Maleshkova, Jens Lehmann · 2024

Question answering (QA) over knowledge graphs (KGs) is an essential task that maps a user’s utterance to a query over a KG to retrieve the correct answer. Earlier methods in this field relied heavily on predefined templates and rules, whic…

MATTER: Memory-Augmented Transformer Using Heterogeneous Knowledge Sources Open

Dongkyu Lee, Chandana Satya Prakash, Jack FitzGerald, Jens Lehmann · 2024

Leveraging external knowledge is crucial for achieving high performance in knowledge-intensive tasks, such as question answering. The retrieve-and-read approach is widely adopted for integrating external knowledge into a language model. Ho…

Enhancing Contextual Understanding in Large Language Models through Contrastive Decoding Open

Zheng Zhao, Emilio Monti, Jens Lehmann, Haytham Assem · 2024

Large language models (LLMs) tend to inadequately integrate input context during text generation, relying excessively on encoded prior knowledge in model parameters, potentially resulting in generated text with factual inconsistencies or c…

REXEL: An End-to-end Model for Document-Level Relation Extraction and Entity Linking Open

Nacime Bouziani, Shubhi Tyagi, Joseph A. Fisher, Jens Lehmann, Andrea Pierleoni · 2024

Extracting structured information from unstructured text is critical for many downstream NLP applications and is traditionally achieved by closed information extraction (cIE). However, existing approaches for cIE suffer from two limitation…

Investigating Multilingual Instruction-Tuning: Do Polyglot Models Demand for Multilingual Instructions? Open

Alexander Arno Weber, Klaudia Thellmann, Jan Ebert, Nicolas Flores-Herr, Jens Lehmann , et al. · 2024

The adaption of multilingual pre-trained LLMs into eloquent and helpful assistants is essential to facilitate their use across different language regions. In that spirit, we are the first to conduct an extensive study of the performance of…

Large Language Models for Scientific Question Answering: An Extensive Analysis of the SciQA Benchmark Open

Jens Lehmann, Antonello Meloni, Enrico Motta, Francesco Osborne, Diego Reforgiato Recupero , et al. · 2024

Bridging Language Models and Knowledge Graphs with Controlled Natural Languages Open

Dhananjay Bhandiwad, Preetam Gattogi, Ashish Kangen, Marco Basaldella, Sébastien Ferré , et al. · 2024

Beyond Boundaries: A Human-like Approach for Question Answering over Structured and Unstructured Information Sources Open

Jens Lehmann, Dhananjay Bhandiwad, Preetam Gattogi, Sahar Vahdati · 2024

Answering factual questions from heterogenous sources, such as graphs and text, is a key capacity of intelligent systems. Current approaches either (i) perform question answering over text and structured sources as separate pipelines follo…

A Study of LFT Embeddings in the Second Order Clifford Algebra <i>Cl</i> (R²,º) Open

Kossi Amouzouvi, Sahar Vahdati, Bowen Song, Bernard Oduoku Bainson, Nur A Zarin Nishat , et al. · 2024

Knowledge graph embedding models represent entities as vectors in continuous spaces and their relations by geometric transformations, mainly translation, and rotation. However, multi-relational knowledge graphs contain complex sub-graph st…

Language Models as Controlled Natural Language Semantic Parsers for Knowledge Graph Question Answering Open

Jens Lehmann, Preetam Gattogi, Dhananjay Bhandiwad, Sébastien Ferré, Sahar Vahdati · 2023

We propose the use of controlled natural language as a target for knowledge graph question answering (KGQA) semantic parsing via language models as opposed to using formal query languages directly. Controlled natural languages are close to…

Direct Fact Retrieval from Knowledge Graphs without Entity Linking Open

Jinheon Baek, Alham Fikri Aji, Jens Lehmann, Sung Ju Hwang · 2023

There has been a surge of interest in utilizing Knowledge Graphs (KGs) for various natural language processing/understanding tasks. The conventional mechanism to retrieve facts in KGs usually involves three steps: entity span detection, en…

Direct Fact Retrieval from Knowledge Graphs without Entity Linking Open

Jinheon Baek, Alham Fikri Aji, Jens Lehmann, Sung Ju Hwang · 2023

There has been a surge of interest in utilizing Knowledge Graphs (KGs) for various natural language processing/understanding tasks. The conventional mechanism to retrieve facts in KGs usually involves three steps: entity span detection, en…

INVITE: a Testbed of Automatically Generated Invalid Questions to Evaluate Large Language Models for Hallucinations Open

Anil Ramakrishna, Rahul Gupta, Jens Lehmann, Morteza Ziyadi · 2023

Recent advancements in Large language models (LLMs) have enabled them to hold free form conversations over multiple turns, but they exhibit a tendency to make unfounded and incorrect statements, commonly known as hallucinations. In particu…

Toward the Multilingual Semantic Web: Multilingual Ontology Matching and Assessment Open

Shimaa Ibrahim, Said Fathalla, Jens Lehmann, Hajira Jabeen · 2023

The amount of multilingual data on the Web proliferates; therefore, developing ontologies in various natural languages is attracting considerable attention. In order to achieve semantic interoperability for the multilingual Web, cross-ling…

mReFinED: An Efficient End-to-End Multilingual Entity Linking System Open

Peerat Limkonchotiwat, Weiwei Cheng, Christos Christodoulopoulos, Amir Saffari, Jens Lehmann · 2023

End-to-end multilingual entity linking (MEL) is concerned with identifying multilingual entity mentions and their corresponding entity IDs in a knowledge base. Existing works assumed that entity mentions were given and skipped the entity m…

Knowledge Graph Embeddings using Neural Ito Process: From Multiple Walks to Stochastic Trajectories Open

Mojtaba Nayyeri, Bo Xiong, Majid Mohammadi, Mst. Mahfuja Akter, Mirza Mohtashim Alam , et al. · 2023

Knowledge graphs mostly exhibit a mixture of branching relations, e.g., hasFriend, and complex structures, e.g., hierarchy and loop. Most knowledge graph embeddings have problems expressing them, because they model a specific relation r fr…

Predicting Missing Links Using PyKEEN Open

Mehdi Ali, Charles Tapley Hoyt, Daniel Domingo‐Fernándéz, Jens Lehmann · 2022

PyKEEN is a framework, which integrates several approaches to compute knowledge graph embeddings (KGEs). We demonstrate the usage of PyKEEN in an biomedical use case, i.e. we trained and evaluated several KGE models on a biological knowled…

The Tale of Sansa Spark Open

Ivan Ermilov, Jens Lehmann, Gëzim Sejdiu, Lorenz Bühmann, Patrick Westphal , et al. · 2022

We demonstrate the open-source Semantic Analytics Stack (SANSA), which can perform scalable analysis of large-scale knowledge graphs to facilitate applications such as link prediction, knowledge base completion and reasoning. The motivatio…

LEMON: LanguagE MOdel for Negative Sampling of Knowledge Graph Embeddings Open

Md Rashad Al Hasan Rony, Mirza Mohtashim Alam, Semab Ali, Qasid Saleem, Jens Lehmann , et al. · 2022

Knowledge Graph Embedding models have become an important area of machine learning. Those models provide a latent representation of entities and relations of a knowledge graph which can then be used in downstream machine learning tasks suc…

Contrastive Representation Learning for Conversational Question Answering over Knowledge Graphs Open

Endri Kacupaj, Kuldeep Singh, Maria Maleshkova, Jens Lehmann · 2022

This paper addresses the task of conversational question answering (ConvQA) over knowledge graphs (KGs). The majority of existing ConvQA methods rely on full supervision signals with a strict assumption of the availability of gold logical …

Jens Lehmann YOU? Author Swipe