FIZ-Karlsruhe – Leibniz-Institute for Information Infrastructure, Eggenstein-Leopoldshafen, Germany and Karlsruhe Institute of Technology, Karlsruhe, Germany
Auto-generated profile, based on publicly available information
Genet Asefa Gesese
FIZ-Karlsruhe – Leibniz-Institute for Information Infrastructure, Eggenstein-Leopoldshafen, Germany and Karlsruhe Institute of Technology, Karlsruhe, Germany
Scholarly data is growing continuously containing information about the articles from a plethora of venues including conferences, journals, etc. Many initiatives have been taken to make scholarly data available in the form of Knowledge Graphs (KGs). These efforts to standardize these data and make them accessible have also led to many challenges such as exploration of scholarly articles, ambiguous authors, etc. This study more specifically targets the problem of Author Name Disambiguation (AND) on Scholarly KGs and presents a novel framework, Literally Author Name Disambiguation (LAND), which utilizes Knowledge Graph Embeddings (KGEs) using multimodal literal information generated from these KGs. This framework is based on three components: (1) multimodal KGEs, (2) a blocking procedure, and finally, (3) hierarchical Agglomerative Clustering. Extensive experiments have been conducted on two newly created KGs: (i) KG containing information from Scientometrics Journal from 1978 onwards (OC-782K), and (ii) a KG extracted from a well-known benchmark for AND provided by AMiner (AMiner-534K). The results show that our proposed architecture outperforms our baselines of 8–14% in terms of F1 score and shows competitive performances on a challenging benchmark such as AMiner. The code and the datasets are publicly available through Github (https://github.com/sntcristian/and-kge) and Zenodo (https://doi.org/10.5281/zenodo.6309855) respectively.
Due to the open world assumption, Knowledge Graphs (KGs) are never complete. In order to address this issue, various Link Prediction (LP) methods are proposed so far. Some of these methods are inductive LP models which are capable of learning representations for entities not seen during training. However, to the best of our knowledge, none of the existing inductive LP models focus on learning representations for unseen relations. In this work, a novel Relation Aware Inductive Link preDiction (RAILD) is proposed for KG completion which learns representations for both unseen entities and unseen relations. In addition to leveraging textual literals associated with both entities and relations by employing language models, RAILD also introduces a novel graph-based approach to generate features for relations. Experiments are conducted with different existing and newly created challenging benchmark datasets and the results indicate that RAILD leads to performance improvement over the state-of-the-art models. Moreover, since there are no existing inductive LP models which learn representations for unseen relations, we have created our own baselines and the results obtained with RAILD also outperform these baselines.
Existing scholarly information extraction (SIE) datasets focus on scientific papers and overlook implementation-level details in code repositories. README files describe datasets, source code, and other implementation-level artifacts, however, their free-form Markdown offers little semantic structure, making automatic information extraction difficult. To address this gap, NERdME is introduced: 200 manually annotated README files with over νm10000 labeled spans and 10 entity types. Baseline results using large language models and fine-tuned transformers show clear differences between paper-level and implementation-level entities, indicating the value of extending SIE benchmarks with entity types available in README files. A downstream entity-linking experiment was conducted to demonstrate that entities derived from READMEs can support artifact discovery and metadata integration.
Knowledge Graphs (KGs) are composed of structured information about a particular domain in the form of entities and relations. In addition to the structured information KGs help in facilitating interconnectivity and interoperability between different resources represented in the Linked Data Cloud. KGs have been used in a variety of applications such as entity linking, question answering, recommender systems, etc. However, KG applications suffer from high computational and storage costs. Hence, there arises the necessity for a representation able to map the high dimensional KGs into low dimensional spaces, i.e., embedding space, preserving structural as well as relational information. This paper conducts a survey of KG embedding models which not only consider the structured information contained in the form of entities and relations in a KG but also the unstructured information represented as literals such as text, numerical values, images, etc. Along with a theoretical analysis and comparison of the methods proposed so far for generating KG embeddings with literals, an empirical evaluation of the different methods under identical settings has been performed for the general task of link prediction.
Document image classification (DIC) for historical archival documents remains challenging due to heterogeneous layouts, degraded documents, and class imbalance. Existing benchmarks mainly target contemporary documents and typically assume access to large amounts of annotated training data, which is often unrealistic in archival settings where labeled data is limited. In this work, BZK-LE is introduced as a dataset for evaluating existing DIC models under zero-shot and few-shot settings. It consists of 9,144 index cards and their corresponding layout class labels, from the Bundeszentralkartei (BZK), documenting post-war compensation proceedings related to Nazi persecution. The dataset comprises 22 distinct pre-printed layout types and preserves the natural class imbalance. The images exhibit typical archival artifacts such as handwritten and typewritten text, annotations, stamps, and spatial misalignment. Baseline results using state-of-the-art layout-aware DIC models are reported on both versions. The datasets are available under https://zenodo.org/records/18790631.
As research in Artificial Intelligence and Data Science continues to grow in volume and complexity, it becomes increasingly difficult to ensure transparency, reproducibility, and discoverability. To address these challenges, as research artifacts should be understandable and usable by machines, the NFDI4DataScience consortium is developing and providing Research Knowledge Graphs (RKGs). Building upon earlier works, this paper presents recent progress in creating semantically rich RKGs using standardized ontologies, shared vocabularies, and automated Information Extraction techniques. Key achievements include the development of the NFDI4DS ontology, metadata standards, tools, and services designed to support the FAIR principles, as well as community-led projects and various implementations of RKGs. Together, these efforts aim to capture and connect the complex relationships between datasets, models, software, and scientific publications.