CMCedric Möller

Cedric Möller

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Cedric Möller has a total of 13 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Beyond Edge Addition: A Dataset for Information Extraction Incorporating New Instances, Types, and Relations

    by Sven Hertling, Cedric Möller, Nandana Mihindukulasooriya, Ricardo Usbeck

  • Open Access

    Automated Knowledge Graph Construction from Aircraft Maintenance Manuals with Information Extraction and Synthetic Data Augmentation

    by Bhavana Raju, Rohin Kumar Majeti, Cedric Möller, Florian Raddatz

    Aircraft maintenance manuals contain critical technical knowledge distributed across hundreds of pages of unstructured documentation. Locating the right information quickly is a persistent challenge for maintenance engineers because knowledge about components, tools, inspection procedures, defects, and safety requirements is spread across multiple document types. This paper presents an automated pipeline that extracts structured knowledge from aircraft maintenance manuals and organises it into a queryable, ontology-aligned knowledge graph. The pipeline is developed and validated on 27 helicopter main rotor maintenance documents. It combines layout-aware text extraction, named entity recognition across ten entity types, and relation extraction across seven semantic relation types. A synthetic data generation strategy using large language models addresses the scarcity of labelled training data. Augmentation improved named entity recognition strict F1 from 0.68 to 0.77 and relation extraction positive macro F1 from 0.42 to 0.77. The extracted entities and relations populate an ontology-aligned knowledge graph that successfully answered all the domain competency questions, demonstrating that structured maintenance knowledge can be automatically extracted and made queryable through an existing validated ontology to support downstream decision-support and fault-diagnostic applications.

  • Neuro-Symbolic Relation Extraction

    by Xi Yan, Aida Usmanova, Cedric Möller, Patrick Westphal, Ricardo Usbeck

    Neuro-symbolic relation extraction lies at the intersection of neural networks and symbolic reasoning, presenting promising opportunities to enhance the capabilities of natural language processing (NLP) systems. Despite its potential, a comprehensive review of how these systems are developed and applied to the task of relation extraction has been lacking. This chapter addresses this gap by offering an in-depth overview of the current landscape in neuro-symbolic relation extraction, focusing on key methodologies and the datasets utilized in this field. We systematically categorize existing approaches, emphasizing how they integrate neural and symbolic components to tackle various challenges and the types of information they incorporate. Additionally, we review the datasets used to evaluate neuro-symbolic relation extraction systems, detailing their statistics, creation processes, and underlying domains. Furthermore, we discuss future research directions and challenges, such as the analysis of symbolic information and the integration of datasets with existing knowledge graphs. By synthesizing these findings, this chapter aims to provide researchers and practitioners with a clear understanding of the state of neuro-symbolic relation extraction and to inspire further innovations in this rapidly evolving field.

  • Open Access

    Ontology-Guided, Hybrid Prompt Learning for Generalization in Knowledge Graph Question Answering

    by Longquan Jiang, Junbo Huang, Cedric Möller, Ricardo Usbeck

    Most existing Knowledge Graph Question Answering (KGQA) approaches are designed for a specific KG, such as Wikidata, DBpedia or Freebase. Due to the heterogeneity of the underlying graph schema, topology and assertions, most KGQA systems cannot be transferred to unseen Knowledge Graphs (KGs) without resource-intensive training data. We present OntoSCPrompt, a novel Large Language Model (LLM)-based KGQA approach with a two-stage architecture that separates semantic parsing from KG-dependent interactions. OntoSCPrompt first generates a SPARQL query structure (including SPARQL keywords such as SELECT, ASK, WHERE and placeholders for missing tokens) and then fills them with KG-specific information. To enhance the understanding of the underlying KG, we present an ontology-guided, hybrid prompt learning strategy that integrates KG ontology into the learning process of hybrid prompts (e.g., discrete and continuous vectors). We also present several task-specific decoding strategies to ensure the correctness and executability of generated SPARQL queries in both stages. Experimental results demonstrate that OntoSCPrompt performs as well as SOTA approaches without retraining on a number of KGQA datasets such as CWQ, WebQSP and LC-QuAD 1.0 in a resource-efficient manner and can generalize well to unseen domain-specific KGs like DBLP-QuAD and CoyPu KG Code: \href{https://github.com/LongquanJiang/OntoSCPrompt}{https://github.com/LongquanJiang/OntoSCPrompt}

  • Open Access

    Entity Linking with Out-of-Knowledge-Graph Entity Detection and Clustering Using Only Knowledge Graphs

    by Cedric Möller, Ricardo Usbeck

    Entity Linking is crucial for numerous downstream tasks, such as question answering, knowledge graph population, and general knowledge extraction. A frequently overlooked aspect of entity linking is the potential encounter with entities not yet present in a target knowledge graph. Although some recent studies have addressed this issue, they primarily utilize full-text knowledge bases or depend on external information such as crawled webpages. Full-text knowledge bases are not available in all domains and using external information is connected to increased effort. However, these resources are not available in most use cases. In this work, we solely rely on the information within a knowledge graph and assume no external information is accessible. To investigate the challenge of identifying and disambiguating entities absent from the knowledge graph, we introduce a comprehensive silver-standard benchmark dataset that covers texts from 1999 to 2022. Based on our novel dataset, we develop an approach using pre-trained language models and knowledge graph embeddings without the need for a parallel full-text corpus. Moreover, by assessing the influence of knowledge graph embeddings on the given task, we show that implementing a sequential entity linking approach, which considers the whole sentence, can outperform clustering techniques that handle each mention separately in specific instances.


  • Open Access

    Biomedical Entity Linking with Triple-aware Pre-Training

    by Xi Yan, Cedric Möller, Ricardo Usbeck

    Linking biomedical entities is an essential aspect in biomedical natural language processing tasks, such as text mining and question answering. However, a difficulty of linking the biomedical entities using current large language models (LLM) trained on a general corpus is that biomedical entities are scarcely distributed in texts and therefore have been rarely seen during training by the LLM. At the same time, those LLMs are not aware of high level semantic connection between different biomedical entities, which are useful in identifying similar concepts in different textual contexts. To cope with aforementioned problems, some recent works focused on injecting knowledge graph information into LLMs. However, former methods either ignore the relational knowledge of the entities or lead to catastrophic forgetting. Therefore, we propose a novel framework to pre-train the powerful generative LLM by a corpus synthesized from a KG. In the evaluations we are unable to confirm the benefit of including synonym, description or relational information.