Sören Auer

Hamed Babaei Giglou, Jennifer D'Souza, Sören Auer

We propose the LLMs4OL approach, which utilizes Large Language Models (LLMs) for Ontology Learning (OL). LLMs have shown significant advancements in natural language processing, demonstrating their ability to capture complex language patterns in different knowledge domains. Our LLMs4OL paradigm investigates the following hypothesis: \textit{Can LLMs effectively apply their language pattern capturing capability to OL, which involves automatically extracting and structuring knowledge from natural language text?} To test this hypothesis, we conduct a comprehensive evaluation using the zero-shot prompting method. We evaluate nine different LLM model families for three main OL tasks: term typing, taxonomy discovery, and extraction of non-taxonomic relations. Additionally, the evaluations encompass diverse genres of ontological knowledge, including lexicosemantic knowledge in WordNet, geographical knowledge in GeoNames, and medical knowledge in UMLS.

Jennifer D'Souza, Sören Auer

Domain-specific named entity recognition (NER) on Computer Science (CS) scholarly articles is an information extraction task that is arguably more challenging for the various annotation aims that can beset the task and has been less studied than NER in the general domain. Given that significant progress has been made on NER, we believe that scholarly domain-specific NER will receive increasing attention in the years to come. Currently, progress on CS NER -- the focus of this work -- is hampered in part by its recency and the lack of a standardized annotation aim for scientific entities/terms. This work proposes a standardized task by defining a set of seven contribution-centric scholarly entities for CS NER viz., research problem, solution, resource, language, tool, method, and dataset. Following which, its main contributions are: combines existing CS NER resources that maintain their annotation focus on the set or subset of contribution-centric scholarly entities we consider; further, noting the need for big data to train neural NER models, this work additionally supplies thousands of contribution-centric entity annotations from article titles and abstracts, thus releasing a cumulative large novel resource for CS NER; and, finally, trains a sequence labeling CS NER model inspired after state-of-the-art neural architectures from the general domain NER task. Throughout the work, several practical considerations are made which can be useful to information technology designers of the digital libraries.

Hamed Babaei Giglou, Jennifer D'Souza, Sören Auer

In response to the growing complexity and volume of scientific literature, this paper introduces the LLMs4Synthesis framework, designed to enhance the capabilities of Large Language Models (LLMs) in generating high-quality scientific syntheses. This framework addresses the need for rapid, coherent, and contextually rich integration of scientific insights, leveraging both open-source and proprietary LLMs. It also examines the effectiveness of LLMs in evaluating the integrity and reliability of these syntheses, alleviating inadequacies in current quantitative metrics. Our study contributes to this field by developing a novel methodology for processing scientific papers, defining new synthesis types, and establishing nine detailed quality criteria for evaluating syntheses. The integration of LLMs with reinforcement learning and AI feedback is proposed to optimize synthesis quality, ensuring alignment with established criteria. The LLMs4Synthesis framework and its components are made available, promising to enhance both the generation and evaluation processes in scientific research synthesis.

Salomon Kabongo, Jennifer D'Souza, Sören Auer

We present a large-scale empirical investigation of the zero-shot learning phenomena in a specific recognizing textual entailment (RTE) task category, i.e. the automated mining of leaderboards for Empirical AI Research. The prior reported state-of-the-art models for leaderboards extraction formulated as an RTE task, in a non-zero-shot setting, are promising with above 90% reported performances. However, a central research question remains unexamined: did the models actually learn entailment? Thus, for the experiments in this paper, two prior reported state-of-the-art models are tested out-of-the-box for their ability to generalize or their capacity for entailment, given leaderboard labels that were unseen during training. We hypothesize that if the models learned entailment, their zero-shot performances can be expected to be moderately high as well--perhaps, concretely, better than chance. As a result of this work, a zero-shot labeled dataset is created via distant labeling formulating the leaderboard extraction RTE task.

Fajar J. Ekaputra, Majlinda Llugiqi, Marta Sabou et al.

In line with the general trend in artificial intelligence research to create intelligent systems that combine learning and symbolic components, a new sub-area has emerged that focuses on combining machine learning (ML) components with techniques developed by the Semantic Web (SW) community - Semantic Web Machine Learning (SWeML for short). Due to its rapid growth and impact on several communities in the last two decades, there is a need to better understand the space of these SWeML Systems, their characteristics, and trends. Yet, surveys that adopt principled and unbiased approaches are missing. To fill this gap, we performed a systematic study and analyzed nearly 500 papers published in the last decade in this area, where we focused on evaluating architectural, and application-specific features. Our analysis identified a rapidly growing interest in SWeML Systems, with a high impact on several application domains and tasks. Catalysts for this rapid growth are the increased application of deep learning and knowledge graph technologies. By leveraging the in-depth understanding of this area acquired through this study, a further key contribution of this paper is a classification system for SWeML Systems which we publish as ontology.

Julia Evans, Jennifer D'Souza, Sören Auer

Our study explores how well the state-of-the-art Large Language Models (LLMs), like GPT-4 and Mistral, can assess the quality of scientific summaries or, more fittingly, scientific syntheses, comparing their evaluations to those of human annotators. We used a dataset of 100 research questions and their syntheses made by GPT-4 from abstracts of five related papers, checked against human quality ratings. The study evaluates both the closed-source GPT-4 and the open-source Mistral model's ability to rate these summaries and provide reasons for their judgments. Preliminary results show that LLMs can offer logical explanations that somewhat match the quality ratings, yet a deeper statistical analysis shows a weak correlation between LLM and human ratings, suggesting the potential and current limitations of LLMs in scientific synthesis evaluation.

Mohamad Yaser Jaradeh, Kuldeep Singh, Markus Stocker et al.

Information Extraction (IE) tasks are commonly studied topics in various domains of research. Hence, the community continuously produces multiple techniques, solutions, and tools to perform such tasks. However, running those tools and integrating them within existing infrastructure requires time, expertise, and resources. One pertinent task here is triples extraction and linking, where structured triples are extracted from a text and aligned to an existing Knowledge Graph (KG). In this paper, we present PLUMBER, the first framework that allows users to manually and automatically create suitable IE pipelines from a community-created pool of tools to perform triple extraction and alignment on unstructured text. Our approach provides an interactive medium to alter the pipelines and perform IE tasks. A short video to show the working of the framework for different use-cases is available online under: https://www.youtube.com/watch?v=XC9rJNIUv8g

Mohamad Yaser Jaradeh, Markus Stocker, Sören Auer

Information extraction from scholarly articles is a challenging task due to the sizable document length and implicit information hidden in text, figures, and citations. Scholarly information extraction has various applications in exploration, archival, and curation services for digital libraries and knowledge management systems. We present MORTY, an information extraction technique that creates structured summaries of text from scholarly articles. Our approach condenses the article's full-text to property-value pairs as a segmented text snippet called structured summary. We also present a sizable scholarly dataset combining structured summaries retrieved from a scholarly knowledge graph and corresponding publicly available scientific articles, which we openly publish as a resource for the research community. Our results show that structured summarization is a suitable approach for targeted information extraction that complements other commonly used methods such as question answering and named entity recognition.

Omar Arab Oghli, Jennifer D'Souza, Sören Auer

When semantically describing knowledge graphs (KGs), users have to make a critical choice of a vocabulary (i.e. predicates and resources). The success of KG building is determined by the convergence of shared vocabularies so that meaning can be established. The typical lifecycle for a new KG construction can be defined as follows: nascent phases of graph construction experience terminology divergence, while later phases of graph construction experience terminology convergence and reuse. In this paper, we describe our approach tailoring two AI-based clustering algorithms for recommending predicates (in RDF statements) about resources in the Open Research Knowledge Graph (ORKG) https://orkg.org/. Such a service to recommend existing predicates to semantify new incoming data of scholarly publications is of paramount importance for fostering terminology convergence in the ORKG. Our experiments show very promising results: a high precision with relatively high recall in linear runtime performance. Furthermore, this work offers novel insights into the predicate groups that automatically accrue loosely as generic semantification patterns for semantification of scholarly knowledge spanning 44 research fields.

Nour Ramzy, Soren Auer, Javad Chamanara et al.

Semiconductor supply chains are described by significant demand fluctuation that increases as one moves up the supply chain, the so-called bullwhip effect. To counteract, semiconductor manufacturers aim to optimize capacity utilization, to deliver with shorter lead times and exploit this to generate revenue. Additionally, in a competitive market, firms seek to maintain customer relationships while applying revenue management strategies such as dynamic pricing. Price change potentially generates conflicts with customers. In this paper, we present KnowGraph-PM, a knowledge graph-based dynamic pricing model. The semantic model uses the potential of faster delivery and shorter lead times to define premium prices, thus entail increased profits based on the customer profile. The knowledge graph enables the integration of customer-related information, e.g., customer class and location to customer order data. The pricing algorithm is realized as a SPARQL query that relies on customer profile and order behavior to determine the corresponding price premium. We evaluate the approach by calculating the revenue generated after applying the pricing algorithm. Based on competency questions that translate to SPARQL queries, we validate the created knowledge graph. We demonstrate that semantic data integration enables customer-tailored revenue management.

Jennifer D'Souza, Anita Monteverdi, Muhammad Haris et al.

Background: Recent years are seeing a growing impetus in the semantification of scholarly knowledge at the fine-grained level of scientific entities in knowledge graphs. The Open Research Knowledge Graph (ORKG) https://www.orkg.org/ represents an important step in this direction, with thousands of scholarly contributions as structured, fine-grained, machine-readable data. There is a need, however, to engender change in traditional community practices of recording contributions as unstructured, non-machine-readable text. For this in turn, there is a strong need for AI tools designed for scientists that permit easy and accurate semantification of their scholarly contributions. We present one such tool, ORKG-assays. Implementation: ORKG-assays is a freely available AI micro-service in ORKG written in Python designed to assist scientists obtain semantified bioassays as a set of triples. It uses an AI-based clustering algorithm which on gold-standard evaluations over 900 bioassays with 5,514 unique property-value pairs for 103 predicates shows competitive performance. Results and Discussion: As a result, semantified assay collections can be surveyed on the ORKG platform via tabulation or chart-based visualizations of key property values of the chemicals and compounds offering smart knowledge access to biochemists and pharmaceutical researchers in the advancement of drug development.

Hamed Babaei Giglou, Jennifer D'Souza, Sören Auer

This paper outlines the LLMs4OL 2024, the first edition of the Large Language Models for Ontology Learning Challenge. LLMs4OL is a community development initiative collocated with the 23rd International Semantic Web Conference (ISWC) to explore the potential of Large Language Models (LLMs) in Ontology Learning (OL), a vital process for enhancing the web with structured knowledge to improve interoperability. By leveraging LLMs, the challenge aims to advance understanding and innovation in OL, aligning with the goals of the Semantic Web to create a more intelligent and user-friendly web. In this paper, we give an overview of the 2024 edition of the LLMs4OL challenge and summarize the contributions.

Lena John, Ahmed Malek Ghanmi, Tim Wittenborg et al.

As the volume of scientific literature grows, efficient knowledge organization becomes increasingly challenging. Traditional approaches to structuring scientific content are time-consuming and require significant domain expertise, highlighting the need for tool support. We present ExtracTable, a Human-in-the-Loop (HITL) workflow and framework that assists researchers in transforming unstructured publications into structured representations. The workflow combines large language models (LLMs) with user-defined schemas and is designed for downstream integration into knowledge graphs (KGs). Developed and evaluated in the context of the Open Research Knowledge Graph (ORKG), ExtracTable automates key steps such as document preprocessing and data extraction while ensuring user oversight through validation. In an evaluation with ORKG community participants following the Quality Improvement Paradigm (QIP), ExtracTable demonstrated high usability and practical value. Participants gave it an average System Usability Scale (SUS) score of 84.17 (A+, the highest rating). The time to progress from a research interest to literature-based insights was reduced from between 4 hours and 2 weeks to an average of 24:40 minutes. By streamlining corpus creation and structured data extraction for knowledge graph integration, ExtracTable leverages LLMs and user models to accelerate literature reviews. However, human validation remains essential to ensure quality, and future work will address improving extraction accuracy and entity linking to existing knowledge resources.

Gollam Rabby, Sören Auer, Jennifer D'Souza et al.

The increasing amount of published scholarly articles, exceeding 2.5 million yearly, raises the challenge for researchers in following scientific progress. Integrating the contributions from scholarly articles into a novel type of cognitive knowledge graph (CKG) will be a crucial element for accessing and organizing scholarly knowledge, surpassing the insights provided by titles and abstracts. This research focuses on effectively conveying structured scholarly knowledge by utilizing large language models (LLMs) to categorize scholarly articles and describe their contributions in a structured and comparable manner. While previous studies explored language models within specific research domains, the extensive domain-independent knowledge captured by LLMs offers a substantial opportunity for generating structured contribution descriptions as CKGs. Additionally, LLMs offer customizable pathways through prompt engineering or fine-tuning, thus facilitating to leveraging of smaller LLMs known for their efficiency, cost-effectiveness, and environmental considerations. Our methodology involves harnessing LLM knowledge, and complementing it with domain expert-verified scholarly data sourced from a CKG. This strategic fusion significantly enhances LLM performance, especially in tasks like scholarly article categorization and predicate recommendation. Our method involves fine-tuning LLMs with CKG knowledge and additionally injecting knowledge from a CKG with a novel prompting technique significantly increasing the accuracy of scholarly knowledge extraction. We integrated our approach in the Open Research Knowledge Graph (ORKG), thus enabling precise access to organized scholarly knowledge, crucially benefiting domain-independent scholarly knowledge exchange and dissemination among policymakers, industrial practitioners, and the general public.

Hamed Babaei Giglou, Jennifer D'Souza, Oliver Karras et al.

Ontology Alignment (OA) is fundamental for achieving semantic interoperability across diverse knowledge systems. We present OntoAligner, a comprehensive, modular, and robust Python toolkit for ontology alignment, designed to address current limitations with existing tools faced by practitioners. Existing tools are limited in scalability, modularity, and ease of integration with recent AI advances. OntoAligner provides a flexible architecture integrating existing lightweight OA techniques such as fuzzy matching but goes beyond by supporting contemporary methods with retrieval-augmented generation and large language models for OA. The framework prioritizes extensibility, enabling researchers to integrate custom alignment algorithms and datasets. This paper details the design principles, architecture, and implementation of the OntoAligner, demonstrating its utility through benchmarks on standard OA tasks. Our evaluation highlights OntoAligner's ability to handle large-scale ontologies efficiently with few lines of code while delivering high alignment quality. By making OntoAligner open-source, we aim to provide a resource that fosters innovation and collaboration within the OA community, empowering researchers and practitioners with a toolkit for reproducible OA research and real-world applications.

Sasi Kiran Gaddipati, Farhana Keya, Gollam Rabby et al.

Advances in AI-assisted research have introduced powerful tools for literature retrieval, hypothesis generation, experimentation, and manuscript preparation. However, systems remain fragmented and lack human-centred workflows. To address these gaps, we introduce AIssistant, an agentic, open-source Human-AI collaborative framework designed to simplify the end-to-end creation of scientific workflows. Since our development is still in an early stage, we present here the first experiments with AIssistant for perspective and review research papers in machine learning. Our system integrates modular tools and agents for literature synthesis, section-wise experimentation, citation management, and automatic LaTeX paper text generation, while maintaining human oversight at every stage to ensure accuracy, coherence, and scholarly rigour. We conducted a comprehensive evaluation across three layers: (1) Independent Human Review, following NeurIPS double-blind standards; (2) Automated LLM Review, using GPT-5 as a scalable human review proxy; and (3) Program Chair Oversight, where the chair monitors the entire review process and makes final validation and acceptance decisions. The results demonstrate that AIssistant improves drafting efficiency and thematic consistency. Nonetheless, Human-AI collaboration remains essential for maintaining factual correctness, methodological soundness, and ethical compliance. Despite its effectiveness, we identify key limitations, including hallucinated citations, difficulty adapting to dynamic paper structures, and incomplete integration of multimodal content.

Christoph Schuhmann, Gollam Rabby, Ameya Prabhu et al.

Paywalls, licenses and copyright rules often restrict the broad dissemination and reuse of scientific knowledge. We take the position that it is both legally and technically feasible to extract the scientific knowledge in scholarly texts. Current methods, like text embeddings, fail to reliably preserve factual content, and simple paraphrasing may not be legally sound. We propose a new idea for the community to adopt: convert scholarly documents into knowledge preserving, but style agnostic representations we term Knowledge Units using LLMs. These units use structured data capturing entities, attributes and relationships without stylistic content. We provide evidence that Knowledge Units (1) form a legally defensible framework for sharing knowledge from copyrighted research texts, based on legal analyses of German copyright law and U.S. Fair Use doctrine, and (2) preserve most (~95\%) factual knowledge from original text, measured by MCQ performance on facts from the original copyrighted text across four research domains. Freeing scientific knowledge from copyright promises transformative benefits for scientific research and education by allowing language models to reuse important facts from copyrighted text. To support this, we share open-source tools for converting research documents into Knowledge Units. Overall, our work posits the feasibility of democratizing access to scientific knowledge while respecting copyright.

Diyana Muhammed, Gollam Rabby, Sören Auer

Detecting hallucinations in Large Language Models (LLMs) remains a critical challenge for their reliable deployment in real-world applications. To address this, we introduce SelfCheckAgent, a novel framework integrating three different agents: the Symbolic Agent, the Specialized Detection Agent, and the Contextual Consistency Agent. These agents provide a robust multi-dimensional approach to hallucination detection. Notable results include the Contextual Consistency Agent leveraging Llama 3.1 with Chain-of-Thought (CoT) to achieve outstanding performance on the WikiBio dataset, with NonFactual hallucination detection scoring 93.64%, Factual 70.26%, and Ranking 78.48% respectively. On the AIME dataset, GPT-4o with CoT excels in NonFactual detection with 94.89% but reveals trade-offs in Factual with 30.58% and Ranking with 30.68%, underscoring the complexity of hallucination detection in the complex mathematical domains. The framework also incorporates a triangulation strategy, which increases the strengths of the SelfCheckAgent, yielding significant improvements in real-world hallucination identification. The comparative analysis demonstrates SelfCheckAgent's applicability across diverse domains, positioning it as a crucial advancement for trustworthy LLMs. These findings highlight the potentiality of consistency-driven methodologies in detecting hallucinations in LLMs.

Sameer Sadruddin, Jennifer D'Souza, Eleni Poupaki et al.

Extracting structured information from unstructured text is crucial for modeling real-world processes, but traditional schema mining relies on semi-structured data, limiting scalability. This paper introduces schema-miner, a novel tool that combines large language models with human feedback to automate and refine schema extraction. Through an iterative workflow, it organizes properties from text, incorporates expert input, and integrates domain-specific ontologies for semantic depth. Applied to materials science--specifically atomic layer deposition--schema-miner demonstrates that expert-guided LLMs generate semantically rich schemas suitable for diverse real-world applications.

Christoph Schuhmann, Robert Kaczmarczyk, Gollam Rabby et al.

The advancement of text-to-speech and audio generation models necessitates robust benchmarks for evaluating the emotional understanding capabilities of AI systems. Current speech emotion recognition (SER) datasets often exhibit limitations in emotional granularity, privacy concerns, or reliance on acted portrayals. This paper introduces EmoNet-Voice, a new resource for speech emotion detection, which includes EmoNet-Voice Big, a large-scale pre-training dataset (featuring over 4,500 hours of speech across 11 voices, 40 emotions, and 4 languages), and EmoNet-Voice Bench, a novel benchmark dataset with human expert annotations. EmoNet-Voice is designed to evaluate SER models on a fine-grained spectrum of 40 emotion categories with different levels of intensities. Leveraging state-of-the-art voice generation, we curated synthetic audio snippets simulating actors portraying scenes designed to evoke specific emotions. Crucially, we conducted rigorous validation by psychology experts who assigned perceived intensity labels. This synthetic, privacy-preserving approach allows for the inclusion of sensitive emotional states often absent in existing datasets. Lastly, we introduce Empathic Insight Voice models that set a new standard in speech emotion recognition with high agreement with human experts. Our evaluations across the current model landscape exhibit valuable findings, such as high-arousal emotions like anger being much easier to detect than low-arousal states like concentration.

Parvez Zamil, Gollam Rabby, Md. Sadekur Rahman et al.

The growing volume of biomedical scholarly document abstracts presents an increasing challenge in efficiently retrieving accurate and relevant information. To address this, we introduce a novel approach that integrates an optimized topic modelling framework, OVB-LDA, with the BI-POP CMA-ES optimization technique for enhanced scholarly document abstract categorization. Complementing this, we employ the distilled MiniLM model, fine-tuned on domain-specific data, for high-precision answer extraction. Our approach is evaluated across three configurations: scholarly document abstract retrieval, gold-standard scholarly documents abstract, and gold-standard snippets, consistently outperforming established methods such as RYGH and bio-answer finder. Notably, we demonstrate that extracting answers from scholarly documents abstracts alone can yield high accuracy, underscoring the sufficiency of abstracts for many biomedical queries. Despite its compact size, MiniLM exhibits competitive performance, challenging the prevailing notion that only large, resource-intensive models can handle such complex tasks. Our results, validated across various question types and evaluation batches, highlight the robustness and adaptability of our method in real-world biomedical applications. While our approach shows promise, we identify challenges in handling complex list-type questions and inconsistencies in evaluation metrics. Future work will focus on refining the topic model with more extensive domain-specific datasets, further optimizing MiniLM and utilizing large language models (LLM) to improve both precision and efficiency in biomedical question answering.

Hamed Babaei Giglou, Tilahun Abedissa Taffa, Rana Abdullah et al.

This paper introduces a scholarly Question Answering (QA) system on top of the NFDI4DataScience Gateway, employing a Retrieval Augmented Generation-based (RAG) approach. The NFDI4DS Gateway, as a foundational framework, offers a unified and intuitive interface for querying various scientific databases using federated search. The RAG-based scholarly QA, powered by a Large Language Model (LLM), facilitates dynamic interaction with search results, enhancing filtering capabilities and fostering a conversational engagement with the Gateway search. The effectiveness of both the Gateway and the scholarly QA system is demonstrated through experimental analysis.

Salomon Kabongo, Jennifer D'Souza, Sören Auer

This paper explores the impact of context selection on the efficiency of Large Language Models (LLMs) in generating Artificial Intelligence (AI) research leaderboards, a task defined as the extraction of (Task, Dataset, Metric, Score) quadruples from scholarly articles. By framing this challenge as a text generation objective and employing instruction finetuning with the FLAN-T5 collection, we introduce a novel method that surpasses traditional Natural Language Inference (NLI) approaches in adapting to new developments without a predefined taxonomy. Through experimentation with three distinct context types of varying selectivity and length, our study demonstrates the importance of effective context selection in enhancing LLM accuracy and reducing hallucinations, providing a new pathway for the reliable and efficient generation of AI leaderboards. This contribution not only advances the state of the art in leaderboard generation but also sheds light on strategies to mitigate common challenges in LLM-based information extraction.

Salomon Kabongo, Jennifer D'Souza, Sören Auer

The rapid advancements in Large Language Models (LLMs) have opened new avenues for automating complex tasks in AI research. This paper investigates the efficacy of different LLMs-Mistral 7B, Llama-2, GPT-4-Turbo and GPT-4.o in extracting leaderboard information from empirical AI research articles. We explore three types of contextual inputs to the models: DocTAET (Document Title, Abstract, Experimental Setup, and Tabular Information), DocREC (Results, Experiments, and Conclusions), and DocFULL (entire document). Our comprehensive study evaluates the performance of these models in generating (Task, Dataset, Metric, Score) quadruples from research papers. The findings reveal significant insights into the strengths and limitations of each model and context type, providing valuable guidance for future AI research automation efforts.

Mahsa Shamsabadi, Jennifer D'Souza, Sören Auer

In this paper, we champion the use of structured and semantic content representation of discourse-based scholarly communication, inspired by tools like Wikipedia infoboxes or structured Amazon product descriptions. These representations provide users with a concise overview, aiding scientists in navigating the dense academic landscape. Our novel automated approach leverages the robust text generation capabilities of LLMs to produce structured scholarly contribution summaries, offering both a practical solution and insights into LLMs' emergent abilities. For LLMs, the prime focus is on improving their general intelligence as conversational agents. We argue that these models can also be applied effectively in information extraction (IE), specifically in complex IE tasks within terse domains like Science. This paradigm shift replaces the traditional modular, pipelined machine learning approach with a simpler objective expressed through instructions. Our results show that finetuned FLAN-T5 with 1000x fewer parameters than the state-of-the-art GPT-davinci is competitive for the task.

Jennifer D'Souza, Moussab Hrou, Sören Auer

There have been many recent investigations into prompt-based training of transformer language models for new text genres in low-resource settings. The prompt-based training approach has been found to be effective in generalizing pre-trained or fine-tuned models for transfer to resource-scarce settings. This work, for the first time, reports results on adopting prompt-based training of transformers for \textit{scholarly knowledge graph object prediction}. The work is unique in the following two main aspects. 1) It deviates from the other works proposing entity and relation extraction pipelines for predicting objects of a scholarly knowledge graph. 2) While other works have tested the method on text genera relatively close to the general knowledge domain, we test the method for a significantly different domain, i.e. scholarly knowledge, in turn testing the linguistic, probabilistic, and factual generalizability of these large-scale transformer models. We find that (i) per expectations, transformer models when tested out-of-the-box underperform on a new domain of data, (ii) prompt-based training of the models achieve performance boosts of up to 40\% in a relaxed evaluation setting, and (iii) testing the models on a starkly different domain even with a clever training objective in a low resource setting makes evident the domain knowledge capture gap offering an empirically-verified incentive for investing more attention and resources to the scholarly domain in the context of transformer models.

Salomon Kabongo, Jennifer D'Souza, Sören Auer

The purpose of this work is to describe the Orkg-Leaderboard software designed to extract leaderboards defined as Task-Dataset-Metric tuples automatically from large collections of empirical research papers in Artificial Intelligence (AI). The software can support both the main workflows of scholarly publishing, viz. as LaTeX files or as PDF files. Furthermore, the system is integrated with the Open Research Knowledge Graph (ORKG) platform, which fosters the machine-actionable publishing of scholarly findings. Thus the system output, when integrated within the ORKG's supported Semantic Web infrastructure of representing machine-actionable 'resources' on the Web, enables: 1) broadly, the integration of empirical results of researchers across the world, thus enabling transparency in empirical research with the potential to also being complete contingent on the underlying data source(s) of publications; and 2) specifically, enables researchers to track the progress in AI with an overview of the state-of-the-art (SOTA) across the most common AI tasks and their corresponding datasets via dynamic ORKG frontend views leveraging tables and visualization charts over the machine-actionable data. Our best model achieves performances above 90% F1 on the \textit{leaderboard} extraction task, thus proving Orkg-Leaderboards a practically viable tool for real-world usage. Going forward, in a sense, Orkg-Leaderboards transforms the leaderboard extraction task to an automated digitalization task, which has been, for a long time in the community, a crowdsourced endeavor.

Ming Jiang, Jennifer D'Souza, Sören Auer et al.

The rapid growth of research publications has placed great demands on digital libraries (DL) for advanced information management technologies. To cater to these demands, techniques relying on knowledge-graph structures are being advocated. In such graph-based pipelines, inferring semantic relations between related scientific concepts is a crucial step. Recently, BERT-based pre-trained models have been popularly explored for automatic relation classification. Despite significant progress, most of them were evaluated in different scenarios, which limits their comparability. Furthermore, existing methods are primarily evaluated on clean texts, which ignores the digitization context of early scholarly publications in terms of machine scanning and optical character recognition (OCR). In such cases, the texts may contain OCR noise, in turn creating uncertainty about existing classifiers' performances. To address these limitations, we started by creating OCR-noisy texts based on three clean corpora. Given these parallel corpora, we conducted a thorough empirical evaluation of eight Bert-based classification models by focusing on three factors: (1) Bert variants; (2) classification strategies; and, (3) OCR noise impacts. Experiments on clean data show that the domain-specific pre-trained Bert is the best variant to identify scientific relations. The strategy of predicting a single relation each time outperforms the one simultaneously identifying multiple relations in general. The optimal classifier's performance can decline by around 10% to 20% in F-score on the noisy corpora. Insights discussed in this study can help DL stakeholders select techniques for building optimal knowledge-graph-based systems.

Marco Anteghini, Jennifer D'Souza, Vitor A. P. Martins dos Santos et al.

Biological data and knowledge bases increasingly rely on Semantic Web technologies and the use of knowledge graphs for data integration, retrieval and federated queries. We propose a solution for automatically semantifying biological assays. Our solution contrasts the problem of automated semantification as labeling versus clustering where the two methods are on opposite ends of the method complexity spectrum. Characteristically modeling our problem, we find the clustering solution significantly outperforms a deep neural network state-of-the-art labeling approach. This novel contribution is based on two factors: 1) a learning objective closely modeled after the data outperforms an alternative approach with sophisticated semantic modeling; 2) automatically semantifying biological assays achieves a high performance F1 of nearly 83%, which to our knowledge is the first reported standardized evaluation of the task offering a strong benchmark model.

Mohamad Yaser Jaradeh, Kuldeep Singh, Markus Stocker et al.

Scholarly Knowledge Graphs (KGs) provide a rich source of structured information representing knowledge encoded in scientific publications. With the sheer volume of published scientific literature comprising a plethora of inhomogeneous entities and relations to describe scientific concepts, these KGs are inherently incomplete. We present exBERT, a method for leveraging pre-trained transformer language models to perform scholarly knowledge graph completion. We model triples of a knowledge graph as text and perform triple classification (i.e., belongs to KG or not). The evaluation shows that exBERT outperforms other baselines on three scholarly KG completion datasets in the tasks of triple classification, link prediction, and relation prediction. Furthermore, we present two scholarly datasets as resources for the research community, collected from public KGs and online resources.

Salomon Kabongo, Jennifer D'Souza, Sören Auer

With the rapid growth of research publications, empowering scientists to keep oversight over the scientific progress is of paramount importance. In this regard, the Leaderboards facet of information organization provides an overview on the state-of-the-art by aggregating empirical results from various studies addressing the same research challenge. Crowdsourcing efforts like PapersWithCode among others are devoted to the construction of Leaderboards predominantly for various subdomains in Artificial Intelligence. Leaderboards provide machine-readable scholarly knowledge that has proven to be directly useful for scientists to keep track of research progress. The construction of Leaderboards could be greatly expedited with automated text mining. This study presents a comprehensive approach for generating Leaderboards for knowledge-graph-based scholarly information organization. Specifically, we investigate the problem of automated Leaderboard construction using state-of-the-art transformer models, viz. Bert, SciBert, and XLNet. Our analysis reveals an optimal approach that significantly outperforms existing baselines for the task with evaluation scores above 90% in F1. This, in turn, offers new state-of-the-art results for Leaderboard extraction. As a result, a vast share of empirical AI research can be organized in the next-generation digital libraries as knowledge graphs.

Oliver Karras, Eduard C. Groen, Javed Ali Khan et al.

In recent decades, there has been a major shift towards improved digital access to scholarly works. However, even now that these works are available in digital form, they remain document-based, making it difficult to communicate the knowledge they contain. The next logical step is to extend these works with more flexible, fine-grained, semantic, and context-sensitive representations of scholarly knowledge. The Open Research Knowledge Graph (ORKG) is a platform that structures and interlinks scholarly knowledge, relying on crowdsourced contributions from researchers (as a crowd) to acquire, curate, publish, and process this knowledge. In this experience report, we consider the ORKG in the context of Crowd-based Requirements Engineering (CrowdRE) from two perspectives: (1) As CrowdRE researchers, we investigate how the ORKG practically applies CrowdRE techniques to involve scholars in its development to make it align better with their academic work. We determined that the ORKG readily provides social and financial incentives, feedback elicitation channels, and support for context and usage monitoring, but that there is improvement potential regarding automated user feedback analyses and a holistic CrowdRE approach. (2) As crowd members, we explore how the ORKG can be used to communicate scholarly knowledge about CrowdRE research. For this purpose, we curated qualitative and quantitative scholarly knowledge in the ORKG based on papers contained in two previously published systematic literature reviews (SLRs) on CrowdRE. This knowledge can be explored and compared interactively, and with more data than what the SLRs originally contained. Therefore, the ORKG improves access and communication of the scholarly knowledge about CrowdRE research. For both perspectives, we found the ORKG to be a useful multi-tool for CrowdRE research.

Jennifer D'Souza, Sören Auer, Ted Pedersen

There is currently a gap between the natural language expression of scholarly publications and their structured semantic content modeling to enable intelligent content search. With the volume of research growing exponentially every year, a search feature operating over semantically structured content is compelling. The SemEval-2021 Shared Task NLPContributionGraph (a.k.a. 'the NCG task') tasks participants to develop automated systems that structure contributions from NLP scholarly articles in the English language. Being the first-of-its-kind in the SemEval series, the task released structured data from NLP scholarly articles at three levels of information granularity, i.e. at sentence-level, phrase-level, and phrases organized as triples toward Knowledge Graph (KG) building. The sentence-level annotations comprised the few sentences about the article's contribution. The phrase-level annotations were scientific term and predicate phrases from the contribution sentences. Finally, the triples constituted the research overview KG. For the Shared Task, participating systems were then expected to automatically classify contribution sentences, extract scientific terms and relations from the sentences, and organize them as KG triples. Overall, the task drew a strong participation demographic of seven teams and 27 participants. The best end-to-end task system classified contribution sentences at 57.27% F1, phrases at 46.41% F1, and triples at 22.28% F1. While the absolute performance to generate triples remains low, in the conclusion of this article, the difficulty of producing such data and as a consequence of modeling it is highlighted.

Mohamad Yaser Jaradeh, Kuldeep Singh, Markus Stocker et al.

In the last decade, a large number of Knowledge Graph (KG) information extraction approaches were proposed. Albeit effective, these efforts are disjoint, and their collective strengths and weaknesses in effective KG information extraction (IE) have not been studied in the literature. We propose Plumber, the first framework that brings together the research community's disjoint IE efforts. The Plumber architecture comprises 33 reusable components for various KG information extraction subtasks, such as coreference resolution, entity linking, and relation extraction. Using these components,Plumber dynamically generates suitable information extraction pipelines and offers overall 264 distinct pipelines.We study the optimization problem of choosing suitable pipelines based on input sentences. To do so, we train a transformer-based classification model that extracts contextual embeddings from the input and finds an appropriate pipeline. We study the efficacy of Plumber for extracting the KG triples using standard datasets over two KGs: DBpedia, and Open Research Knowledge Graph (ORKG). Our results demonstrate the effectiveness of Plumber in dynamically generating KG information extraction pipelines,outperforming all baselines agnostics of the underlying KG. Furthermore,we provide an analysis of collective failure cases, study the similarities and synergies among integrated components, and discuss their limitations.

Arthur Brack, Anett Hoppe, Markus Stocker et al.

Current science communication has a number of drawbacks and bottlenecks which have been subject of discussion lately: Among others, the rising number of published articles makes it nearly impossible to get a full overview of the state of the art in a certain field, or reproducibility is hampered by fixed-length, document-based publications which normally cannot cover all details of a research work. Recently, several initiatives have proposed knowledge graphs (KG) for organising scientific information as a solution to many of the current issues. The focus of these proposals is, however, usually restricted to very specific use cases. In this paper, we aim to transcend this limited perspective and present a comprehensive analysis of requirements for an Open Research Knowledge Graph (ORKG) by (a) collecting and reviewing daily core tasks of a scientist, (b) establishing their consequential requirements for a KG-based system, (c) identifying overlaps and specificities, and their coverage in current solutions. As a result, we map necessary and desirable requirements for successful KG-based science communication, derive implications, and outline possible solutions.

Marco Anteghini, Jennifer D'Souza, Vitor A. P. Martins dos Santos et al.

As a novel contribution to the problem of semantifying biological assays, in this paper, we propose a neural-network-based approach to automatically semantify, thereby structure, unstructured bioassay text descriptions. Experimental evaluations, to this end, show promise as the neural-based semantification significantly outperforms a naive frequency-based baseline approach. Specifically, the neural method attains 72% F1 versus 47% F1 from the frequency-based method.

Jennifer D'Souza, Sören Auer

We describe an annotation initiative to capture the scholarly contributions in natural language processing (NLP) articles, particularly, for the articles that discuss machine learning (ML) approaches for various information extraction tasks. We develop the annotation task based on a pilot annotation exercise on 50 NLP-ML scholarly articles presenting contributions to five information extraction tasks 1. machine translation, 2. named entity recognition, 3. question answering, 4. relation classification, and 5. text classification. In this article, we describe the outcomes of this pilot annotation phase. Through the exercise we have obtained an annotation methodology; and found ten core information units that reflect the contribution of the NLP-ML scholarly investigations. The resulting annotation scheme we developed based on these information units is called NLPContributions. The overarching goal of our endeavor is four-fold: 1) to find a systematic set of patterns of subject-predicate-object statements for the semantic structuring of scholarly contributions that are more or less generically applicable for NLP-ML research articles; 2) to apply the discovered patterns in the creation of a larger annotated dataset for training machine readers of research contributions; 3) to ingest the dataset into the Open Research Knowledge Graph (ORKG) infrastructure as a showcase for creating user-friendly state-of-the-art overviews; 4) to integrate the machine readers into the ORKG to assist users in the manual curation of their respective article contributions. We envision that the NLPContributions methodology engenders a wider discussion on the topic toward its further refinement and development. Our pilot annotated dataset of 50 NLP-ML scholarly articles according to the NLPContributions scheme is openly available to the research community at https://doi.org/10.25835/0019761.

Mohamad Yaser Jaradeh, Markus Stocker, Sören Auer

Answering questions on scholarly knowledge comprising text and other artifacts is a vital part of any research life cycle. Querying scholarly knowledge and retrieving suitable answers is currently hardly possible due to the following primary reason: machine inactionable, ambiguous and unstructured content in publications. We present JarvisQA, a BERT based system to answer questions on tabular views of scholarly knowledge graphs. Such tables can be found in a variety of shapes in the scholarly literature (e.g., surveys, comparisons or results). Our system can retrieve direct answers to a variety of different questions asked on tabular data in articles. Furthermore, we present a preliminary dataset of related tables and a corresponding set of natural language questions. This dataset is used as a benchmark for our system and can be reused by others. Additionally, JarvisQA is evaluated on two datasets against other baselines and shows an improvement of two to three folds in performance compared to related methods.

Arthur Brack, Anett Hoppe, Markus Stocker et al.

Current science communication has a number of drawbacks and bottlenecks which have been subject of discussion lately: Among others, the rising number of published articles makes it nearly impossible to get an overview of the state of the art in a certain field, or reproducibility is hampered by fixed-length, document-based publications which normally cannot cover all details of a research work. Recently, several initiatives have proposed knowledge graphs (KGs) for organising scientific information as a solution to many of the current issues. The focus of these proposals is, however, usually restricted to very specific use cases. In this paper, we aim to transcend this limited perspective by presenting a comprehensive analysis of requirements for an Open Research Knowledge Graph (ORKG) by (a) collecting daily core tasks of a scientist, (b) establishing their consequential requirements for a KG-based system, (c) identifying overlaps and specificities, and their coverage in current solutions. As a result, we map necessary and desirable requirements for successful KG-based science communication, derive implications and outline possible solutions.

Ming Jiang, Jennifer D'Souza, Sören Auer et al.

With the rapid growth of research publications, there is a vast amount of scholarly knowledge that needs to be organized in digital libraries. To deal with this challenge, techniques relying on knowledge-graph structures are being advocated. Within such graph-based pipelines, inferring relation types between related scientific concepts is a crucial step. Recently, advanced techniques relying on language models pre-trained on the large corpus have been popularly explored for automatic relation classification. Despite remarkable contributions that have been made, many of these methods were evaluated under different scenarios, which limits their comparability. To this end, we present a thorough empirical evaluation on eight Bert-based classification models by focusing on two key factors: 1) Bert model variants, and 2) classification strategies. Experiments on three corpora show that domain-specific pre-training corpus benefits the Bert-based classification model to identify the type of scientific relations. Although the strategy of predicting a single relation each time achieves a higher classification accuracy than the strategy of identifying multiple relation types simultaneously in general, the latter strategy demonstrates a more consistent performance in the corpus with either a large or small size of annotations. Our study aims to offer recommendations to the stakeholders of digital libraries for selecting the appropriate technique to build knowledge-graph-based systems for enhanced scholarly information organization.

Jennifer D'Souza, Anett Hoppe, Arthur Brack et al.

We introduce the STEM (Science, Technology, Engineering, and Medicine) Dataset for Scientific Entity Extraction, Classification, and Resolution, version 1.0 (STEM-ECR v1.0). The STEM-ECR v1.0 dataset has been developed to provide a benchmark for the evaluation of scientific entity extraction, classification, and resolution tasks in a domain-independent fashion. It comprises abstracts in 10 STEM disciplines that were found to be the most prolific ones on a major publishing platform. We describe the creation of such a multidisciplinary corpus and highlight the obtained findings in terms of the following features: 1) a generic conceptual formalism for scientific entities in a multidisciplinary scientific context; 2) the feasibility of the domain-independent human annotation of scientific entities under such a generic formalism; 3) a performance benchmark obtainable for automatic extraction of multidisciplinary scientific entities using BERT-based neural models; 4) a delineated 3-step entity resolution procedure for human annotation of the scientific entities via encyclopedic entity linking and lexicographic word sense disambiguation; and 5) human evaluations of Babelfy returned encyclopedic links and lexicographic senses for our entities. Our findings cumulatively indicate that human annotation and automatic learning of multidisciplinary scientific concepts as well as their semantic disambiguation in a wide-ranging setting as STEM is reasonable.

Arthur Brack, Jennifer D'Souza, Anett Hoppe et al.

We examine the novel task of domain-independent scientific concept extraction from abstracts of scholarly articles and present two contributions. First, we suggest a set of generic scientific concepts that have been identified in a systematic annotation process. This set of concepts is utilised to annotate a corpus of scientific abstracts from 10 domains of Science, Technology and Medicine at the phrasal level in a joint effort with domain experts. The resulting dataset is used in a set of benchmark experiments to (a) provide baseline performance for this task, (b) examine the transferability of concepts between domains. Second, we present two deep learning systems as baselines. In particular, we propose active learning to deal with different domains in our task. The experimental results show that (1) a substantial agreement is achievable by non-experts after consultation with domain experts, (2) the baseline system achieves a fairly high F1 score, (3) active learning enables us to nearly halve the amount of required training data.

Isaiah Onando Mulang, Kuldeep Singh, Akhilesh Vyas et al.

The collaborative knowledge graphs such as Wikidata excessively rely on the crowd to author the information. Since the crowd is not bound to a standard protocol for assigning entity titles, the knowledge graph is populated by non-standard, noisy, long or even sometimes awkward titles. The issue of long, implicit, and nonstandard entity representations is a challenge in Entity Linking (EL) approaches for gaining high precision and recall. Underlying KG, in general, is the source of target entities for EL approaches, however, it often contains other relevant information, such as aliases of entities (e.g., Obama and Barack Hussein Obama are aliases for the entity Barack Obama). EL models usually ignore such readily available entity attributes. In this paper, we examine the role of knowledge graph context on an attentive neural network approach for entity linking on Wikidata. Our approach contributes by exploiting the sufficient context from a KG as a source of background knowledge, which is then fed into the neural network. This approach demonstrates merit to address challenges associated with entity titles (multi-word, long, implicit, case-sensitive). Our experimental study shows approx 8% improvements over the baseline approach, and significantly outperform an end to end approach for Wikidata entity linking.

Mohamed Nadjib Mami, Damien Graux, Harsh Thakkar et al.

Whereas the availability of data has seen a manyfold increase in past years, its value can be only shown if the data variety is effectively tackled ---one of the prominent Big Data challenges. The lack of data interoperability limits the potential of its collective use for novel applications. Achieving interoperability through the full transformation and integration of diverse data structures remains an ideal that is hard, if not impossible, to achieve. Instead, methods that can simultaneously interpret different types of data available in different data structures and formats have been explored. On the other hand, many query languages have been designed to enable users to interact with the data, from relational, to object-oriented, to hierarchical, to the multitude emerging NoSQL languages. Therefore, the interoperability issue could be solved not by enforcing physical data transformation, but by looking at techniques that are able to query heterogeneous sources using one uniform language. Both industry and research communities have been keen to develop such techniques, which require the translation of a chosen 'universal' query language to the various data model specific query languages that make the underlying data accessible. In this article, we survey more than forty query translation methods and tools for popular query languages, and classify them according to eight criteria. In particular, we study which query language is a most suitable candidate for that 'universal' query language. Further, the results enable us to discover the weakly addressed and unexplored translation paths, to discover gaps and to learn lessons that can benefit future research in the area.

Mohamad Yaser Jaradeh, Allard Oelen, Kheir Eddine Farfar et al.

Despite improved digital access to scholarly knowledge in recent decades, scholarly communication remains exclusively document-based. In this form, scholarly knowledge is hard to process automatically. In this paper, we present the first steps towards a knowledge graph based infrastructure that acquires scholarly knowledge in machine actionable form thus enabling new possibilities for scholarly knowledge curation, publication and processing. The primary contribution is to present, evaluate and discuss multi-modal scholarly knowledge acquisition, combining crowdsourced and automated techniques. We present the results of the first user evaluation of the infrastructure with the participants of a recent international conference. Results suggest that users were intrigued by the novelty of the proposed infrastructure and by the possibilities for innovative scholarly knowledge processing it could enable.

Ashwini Jaya Kumar, Sören Auer, Christoph Schmidt et al.

Applications which use human speech as an input require a speech interface with high recognition accuracy. The words or phrases in the recognised text are annotated with a machine-understandable meaning and linked to knowledge graphs for further processing by the target application. These semantic annotations of recognised words can be represented as a subject-predicate-object triples which collectively form a graph often referred to as a knowledge graph. This type of knowledge representation facilitates to use speech interfaces with any spoken input application, since the information is represented in logical, semantic form, retrieving and storing can be followed using any web standard query languages. In this work, we develop a methodology for linking speech input to knowledge graphs and study the impact of recognition errors in the overall process. We show that for a corpus with lower WER, the annotation and linking of entities to the DBpedia knowledge graph is considerable. DBpedia Spotlight, a tool to interlink text documents with the linked open data is used to link the speech recognition output to the DBpedia knowledge graph. Such a knowledge-based speech recognition interface is useful for applications such as question answering or spoken dialog systems.

Ashwini Jaya Kumar, Camilo Morales, Maria-Esther Vidal et al.

With the evolution of neural network based methods, automatic speech recognition (ASR) field has been advanced to a level where building an application with speech interface is a reality. In spite of these advances, building a real-time speech recogniser faces several problems such as low recognition accuracy, domain constraint, and out-of-vocabulary words. The low recognition accuracy problem is addressed by improving the acoustic model, language model, decoder and by rescoring the N-best list at the output of the decoder. We are considering the N-best list rescoring approach to improve the recognition accuracy. Most of the methods in the literature use the grammatical, lexical, syntactic and semantic connection between the words in a recognised sentence as a feature to rescore. In this paper, we have tried to see the semantic relatedness between the words in a sentence to rescore the N-best list. Semantic relatedness is computed using TransE~\cite{bordes2013translating}, a method for low dimensional embedding of a triple in a knowledge graph. The novelty of the paper is the application of semantic web to automatic speech recognition.

Lavdim Halilaj, Irlán Grangel-González, Gökhan Coskun et al.

Collaborative vocabulary development in the context of data integration is the process of finding consensus between the experts of the different systems and domains. The complexity of this process is increased with the number of involved people, the variety of the systems to be integrated and the dynamics of their domain. In this paper we advocate that the realization of a powerful version control system is the heart of the problem. Driven by this idea and the success of Git in the context of software development, we investigate the applicability of Git for collaborative vocabulary development. Even though vocabulary development and software development have much more similarities than differences there are still important differences. These need to be considered within the development of a successful versioning and collaboration system for vocabulary development. Therefore, this paper starts by presenting the challenges we were faced with during the creation of vocabularies collaboratively and discusses its distinction to software development. Based on these insights we propose Git4Voc which comprises guidelines how Git can be adopted to vocabulary development. Finally, we demonstrate how Git hooks can be implemented to go beyond the plain functionality of Git by realizing vocabulary-specific features like syntactic validation and semantic diffs.

Irlán Grangel-González, Lavdim Halilaj, Gökhan Coskun et al.

In the engineering and manufacturing domain, there is currently an atmosphere of departure to a new era of digitized production. In different regions, initiatives in these directions are known under different names, such as industrie du futur in France, industrial internet in the US or Industrie 4.0 in Germany. While the vision of digitizing production and manufacturing gained much traction lately, it is still relatively unclear how this vision can actually be implemented with concrete standards and technologies. Within the German Industry 4.0 initiative, the concept of an Administrative Shell was devised to respond to these requirements. The Administrative Shell is planned to provide a digital representation of all information being available about and from an object which can be a hardware system or a software platform. In this paper, we present an approach to developing such a digital representation based on semantic knowledge representation formalisms such as RDF, RDF Schema and OWL. We present our concept of a Semantic I4.0 Component which addresses the communication and comprehension challenges in Industry 4.0 scenarios using semantic technologies. Our approach is illustrated with a concrete example showing its benefits in a real-world use case.

Alan Tygel, Sören Auer, Jeremy Debattista et al.

This paper presents an approach for metadata reconciliation, curation and linking for Open Governamental Data Portals (ODPs). ODPs have been lately the standard solution for governments willing to put their public data available for the society. Portal managers use several types of metadata to organize the datasets, one of the most important ones being the tags. However, the tagging process is subject to many problems, such as synonyms, ambiguity or incoherence, among others. As our empiric analysis of ODPs shows, these issues are currently prevalent in most ODPs and effectively hinders the reuse of Open Data. In order to address these problems, we develop and implement an approach for tag reconciliation in Open Data Portals, encompassing local actions related to individual portals, and global actions for adding a semantic metadata layer above individual portals. The local part aims to enhance the quality of tags in a single portal, and the global part is meant to interlink ODPs by establishing relations between tags.