Invasive mechanical ventilation (MV) is a life-sustaining therapy commonly used in the intensive care unit (ICU) for patients with severe and acute conditions. These patients frequently rely on MV for breathing. Given the high risk of death in such cases, optimal MV settings can reduce mortality, minimize ventilator-induced lung injury, shorten ICU stays, and ease the strain on healthcare resources. However, optimizing MV settings remains a complex and error-prone process due to patient-specific variability. While Offline Reinforcement Learning (RL) shows promise for optimizing MV settings, current methods struggle with the hybrid (continuous and discrete) nature of MV settings. Discretizing continuous settings leads to exponential growth in the action space, which limits the number of optimizable settings. Converting the predictions back to continuous can cause a distribution shift, compromising safety and performance. To address this challenge, in the IntelliLung project, we are developing an AI-based approach where we constrain the action space and employ factored action critics. This approach allows us to scale to six optimizable settings compared to 2-3 in previous studies. We adapt SOTA offline RL algorithms to operate directly on hybrid action spaces, avoiding the pitfalls of discretization. We also introduce a clinically grounded reward function based on ventilator-free days and physiological targets. Using multi-objective optimization for reward selection, we show that this leads to a more equitable consideration of all clinically relevant objectives. Notably, we develop a system in close collaboration with healthcare professionals that is aligned with real-world clinical objectives and designed with future deployment in mind.

Machine-translated benchmarks are widely used to assess the multilingual capabilities of large language models (LLMs), yet translation errors in these benchmarks remain underexplored, raising concerns about the reliability and comparability of multilingual evaluation.We address two practical gaps: (i) how well automatic MQM-style error spans from LLM judges and a span-aware QE baseline (xCOMET-XXL) match expert human span annotations on benchmark translations, and (ii) how strongly translation errors (as opposed to source-side issues in the English original) explain accuracy drops on translated benchmarks.We find that span agreement is non-trivial on naturally occurring benchmark translations, and that target-side translation errors are consistently associated with measurable, percentagepoint drops in translated accuracy even after controlling for English correctness and sourceside anomalies.

Knowledge Graph Question Answering (KGQA) has advanced through structured query generation, yet most efforts target RDF/SPARQL, leaving Cypher and property graphs underexplored, despite increasing demand for unified KGQA in industry settings. We propose UniQGen, a novel constraint-based framework that employs LLM agents to dynamically extract and refine representative graph query clauses into executable, intent-aligned graph queries across query languages. The foundation of our method is a variant of Chase & Backchase, a family of algorithms for query optimization and reformulation. We extend Chase & Backchase with a dynamic reasoning process over query constraints that also interact with LLMs for query quality estimation. With a Cypher-supported Freebase graph deployed on Amazon Neptune, we extensively evaluate our approach on popular KGQA benchmarks (GraphQ, GrailQA, and WebQSP). We demonstrate that UniQGen outperforms state-of-the-art graph query generation techniques in both accuracy and efficiency, with F1 gains of 31.6% on GraphQ and 4.9% on GrailQA. Unlike prior methods, our framework does not require fine-tuning for schema matching, making it more extensible to schema-less graphs and semantics in query workloads, and is more suitable for enterprise-grade KGQA. We release Cypher outputs and a Neptune-ready Freebase snapshot to support reproducible, cross-language KGQA research.

International audience

Knowledge graph embedding (KGE) models provide a low-dimensional representation of knowledge graphs in continuous vector spaces. This representation learning enables different downstream AI tasks such as link prediction for graph completion. However, most embedding models are only designed considering the algebra and geometry of the entity embedding space, the algebra of the relation embedding space, and the interaction between relation and entity embeddings. Neglecting the geometry of relation embedding limits the optimization of entity and relation distribution leading to suboptimal performance of knowledge graph completion. To address this issue, we propose a new perspective in the design of KGEs by looking into the geometry of relation embedding space. The proposed method and its variants are developed on top of an existing framework, RotatE, from which we leverage the geometry of the relation embeddings by mutating the unit circle to an ellipse, and further generalize it with the concept of a butterfly curve, consecutively. Besides the theoretical abilities of the model in preserving topological and relational patterns, the experiments on the WN18RR, FB15K-237 and YouTube benchmarks showed that this new family of KGEs can challenge or outperform state-of-the-art models.

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 conventional model-free methods, our approach benefits from the model-based algorithms’ capability to learn and interrogate dynamics models, enabling better generalization through synthetic data generation and a deeper understanding of the system dynamics. Coupled with Explainable AI (XAI) techniques, we focus on uncovering the underlying mechanisms of patient-ventilator interactions as learned by the AI. Our findings show a significant improvement in treatment efficacy, measured by Fitted Q Evaluation (FQE) metrics, achieved without the need for auxiliary rewards. This advancement not only highlights the potential of model-based reinforcement learning in healthcare but also emphasizes the importance of transparent AI design in healthcare applications.

Alexander Arno Weber, Klaudia Thellmann, Jan Ebert, Nicolas Flores-Herr, Jens Lehmann, Michael Fromm, Mehdi Ali. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.

Zheng Zhao, Emilio Monti, Jens Lehmann, Haytham Assem. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.

Abstract 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 followed by a merge step or (ii) provide an early integration, giving up the strengths of particular information sources. To solve this problem, we present “HumanIQ”, a method that teaches language models to dynamically combine retrieved information by imitating how humans use retrieval tools. Our approach couples a generic method for gathering human demonstrations of tool use with adaptive few-shot learning for tool augmented models. We show that HumanIQ confers significant benefits, including i) reducing the error rate of our strongest baseline (GPT-4) by over 50% across 3 benchmarks, (ii) improving human preference over responses from vanilla GPT-4 (45.3% wins, 46.7% ties, 8.0% loss), and (iii) outperforming numerous task-specific baselines.

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, entity disambiguation, and relation classification.However, this approach requires additional labels for training each of the three subcomponents in addition to pairs of input texts and facts, and also may accumulate errors propagated from failures in previous steps.To tackle these limitations, we propose a simple knowledge retrieval framework, which directly retrieves facts from the KGs given the input text based on their representational similarities, which we refer to as Direct Fact Retrieval (Di-FaR).Specifically, we first embed all facts in KGs onto a dense embedding space by using a language model trained by only pairs of input texts and facts, and then provide the nearest facts in response to the input text.Since the fact, consisting of only two entities and one relation, has little context to encode, we propose to further refine ranks of top-k retrieved facts with a reranker that contextualizes the input text and the fact jointly.We validate our Di-FaR framework on multiple fact retrieval tasks, showing that it significantly outperforms relevant baselines that use the three-step approach.

Skilled employees are the most important pillars of an organization. Despite this, most organizations face high attrition and turnover rates. While several machine learning models have been developed to analyze attrition and its causal factors, the interpretations of those models remain opaque. In this paper, we propose the HR-DSS approach, which stands for Human Resource (HR) Decision Support System, and uses explainable AI for employee attrition problems. The system is designed to assist HR departments in interpreting the predictions provided by machine learning models. In our experiments, we employ eight machine learning models to provide predictions. We further process the results achieved by the best-performing model by the SHAP explainability process and use the SHAP values to generate natural language explanations which can be valuable for HR. Furthermore, using "What-if-analysis", we aim to observe plausible causes for attrition of an individual employee. The results show that by adjusting the specific dominant features of each individual, employee attrition can turn into employee retention through informative business decisions.

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 (human) natural languages, but can be unambiguously translated into a formal language such as SPARQL. Our research hypothesis is that the pre-training of large language models (LLMs) on vast amounts of textual data leads to the ability to parse into controlled natural language for KGQA with limited training data requirements. We devise an LLM-specific approach for semantic parsing to study this hypothesis. To conduct our study, we created a dataset that allows the comparison of one formal and two different controlled natural languages. Our analysis shows that training data requirements are indeed substantially reduced when using controlled natural languages, which is relevant since collecting and maintaining high-quality KGQA semantic parsing training data is very expensive and time-consuming.

Knowledge graph embedding models have gained significant attention in AI research. The aim of knowledge graph embedding is to embed the graphs into a vector space in which the structure of the graph is preserved. Recent works have shown that the inclusion of background knowledge, such as logical rules, can improve the performance of embeddings in downstream machine learning tasks. However, so far, most existing models do not allow the inclusion of rules. We address the challenge of including rules and present a new neural based embedding model (LogicENN). We prove that LogicENN can learn every ground truth of encoded rules in a knowledge graph. To the best of our knowledge, this has not been proved so far for the neural based family of embedding models. Moreover, we derive formulae for the inclusion of various rules, including (anti-)symmetric, inverse, irreflexive and transitive, implication, composition, equivalence and negation. Our formulation allows to avoid grounding for implication and equivalence relations. Our experiments show that LogicENN outperforms the existing models in link prediction.

Recent years, Knowledge Graph Embeddings (KGEs) have shown promising performance on link prediction tasks by mapping the entities and relations from a Knowledge Graph (KG) into a geometric space and thus have gained increasing attentions. In addition, many recent Knowledge Graphs involve evolving data, e.g., the fact (Obama, PresidentOf, USA) is valid only from 2009 to 2017. This introduces important challenges for knowledge representation learning since such temporal KGs change over time. In this work, we strive to move beyond the complex or hypercomplex space for KGE and propose a novel geometric algebra based embedding approach, GeomE, which uses multivector representations and the geometric product to model entities and relations. GeomE subsumes several state-of-the-art KGE models and is able to model diverse relations patterns. On top of this, we extend GeomE to TGeomE for temporal KGE, which performs 4th-order tensor factorization of a temporal KG and devises a new linear temporal regularization for time representation learning. Moreover, we study the effect of time granularity on the performance of TGeomE models. Experimental results show that our proposed models achieve the state-of-the-art performances on link prediction over four commonly-used static KG datasets and four well-established temporal KG datasets across various metrics.

5645

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 forms of queries to extract answers from the KG. However, creating such a gold logical form is not viable for each potential question in a real-world scenario. Hence, in the case of missing gold logical forms, the existing information retrieval-based approaches use weak supervision via heuristics or reinforcement learning, formulating ConvQA as a KG path ranking problem. Despite missing gold logical forms, an abundance of conversational contexts, such as entire dialog history with fluent responses and domain information, can be incorporated to effectively reach the correct KG path. This work proposes a contrastive representation learning-based approach to rank KG paths effectively. Our approach solves two key challenges. Firstly, it allows weak supervision-based learning that omits the necessity of gold annotations. Second, it incorporates the conversational context (entire dialog history and domain information) to jointly learn its homogeneous representation with KG paths to improve contrastive representations for effective path ranking. We evaluate our approach on standard datasets for ConvQA, on which it significantly outperforms existing baselines on all domains and overall. Specifically, in some cases, the Mean Reciprocal Rank (MRR) and [email protected] ranking metrics improve by absolute 10 and 18 points, respectively, compared to the state-of-the-art performance.

For many years, link prediction on knowledge. graphs has been a purely transductive task, not allowing for reasoning on unseen entities. Recently, increasing efforts are put into exploring semi- and fully inductive scenarios, enabling inference over unseen and emerging entities. Still, all these approaches only consider triple-based KGs, whereas their richer counterparts, hyper-relational KGs (e.g., Wikidata), have not yet been properly studied. In this work, we classify different inductive settings and study the benefits of employing hyper-relational KGs on a wide range of semi- and fully inductive link prediction tasks powered by recent advancements in graph neural networks. Our experiments on a novel set of benchmarks show that qualifiers over typed edges can lead to performance improvements of 6% of absolute gains (for the Hits@10 metric) compared to triple-only baselines. Our code is available at https://github.com/mali-git/hyper_relational_ilp.

Climate change has a severe impact on the overall ecosystem of the whole world, including humankind. This demo paper presents Climate Bot - a machine reading comprehension system for question answering over documents about climate change. The proposed Climate Bot provides an interface for users to ask questions in natural language and get answers from reliable data sources. The purpose of the climate bot is to spread awareness about climate change and help individuals and communities to learn about the impact and challenges of climate change. Additionally, we open-sourced an annotated climate change dataset CCMRC to promote further research on the topic. This paper describes the dataset collection, annotation, system design, and evaluation.

Knowledge graph (KG) alignment is to match entities in different KGs, which is important to knowledge fusion and integration. Temporal KGs (TKGs) extend traditional Knowledge Graphs (KGs) by associating static triples with specific timestamps (e.g., temporal scopes or time points). Moreover, open-world KGs (OKGs) are dynamic with new emerging entities and timestamps. While entity alignment (EA) between KGs has drawn increasing attention from the research community, EA between TKGs and OKGs still remains unexplored. In this work, we propose a novel Temporal Relational Entity Alignment method (TREA) which is able to learn alignment-oriented TKG embeddings and represent new emerging entities. We first map entities, relations and timestamps into an embedding space, and the initial feature of each entity is represented by fusing the embeddings of its connected relations and timestamps as well as its neighboring entities. A graph neural network (GNN) is employed to capture intra-graph information and a temporal relational attention mechanism is utilized to integrate relation and time features of links between nodes. Finally, a margin-based full multi-class log-loss is used for efficient training and a sequential time regularizer is used to model unobserved timestamps. We use three well-established TKG datasets, as references for evaluating temporal and non-temporal EA methods. Experimental results show that our method outperforms the state-of-the-art EA methods.

The heterogeneity in recently published knowledge graph embedding models' implementations, training, and evaluation has made fair and thorough comparisons difficult. To assess the reproducibility of previously published results, we re-implemented and evaluated 21 models in the PyKEEN software package. In this paper, we outline which results could be reproduced with their reported hyper-parameters, which could only be reproduced with alternate hyper-parameters, and which could not be reproduced at all, as well as provide insight as to why this might be the case. We then performed a large-scale benchmarking on four datasets with several thousands of experiments and 24,804 GPU hours of computation time. We present insights gained as to best practices, best configurations for each model, and where improvements could be made over previously published best configurations. Our results highlight that the combination of model architecture, training approach, loss function, and the explicit modeling of inverse relations is crucial for a model's performance and is not only determined by its architecture. We provide evidence that several architectures can obtain results competitive to the state of the art when configured carefully. We have made all code, experimental configurations, results, and analyses available at https://github.com/pykeen/pykeen and https://github.com/pykeen/benchmarking.

9064

Fabian Galetzka, Jewgeni Rose, David Schlangen, Jens Lehmann. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

This paper presents DistRDF2ML, the generic, scalable, and distributed framework for creating in-memory data preprocessing pipelines for Spark-based machine learning on RDF knowledge graphs. This framework introduces software modules that transform large-scale RDF data into ML-ready fixed-length numeric feature vectors. The developed modules are optimized to the multi-modal nature of knowledge graphs. DistRDF2ML provides aligned software design and usage principles as common data science stacks that offer an easy-to-use package for creating machine learning pipelines. The modules used in the pipeline, the hyper-parameters and the results are exported as a semantic structure that can be used to enrich the original knowledge graph. The semantic representation of metadata and machine learning results offers the advantage of increasing the machine learning pipelines' reusability, explainability, and reproducibility. The entire framework of DistRDF2ML is open source, integrated into the holistic SANSA stack, documented in scala-docs, and covered by unit tests. DistRDF2ML demonstrates its scalable design across different processing power configurations and (hyper-)parameter setups within various experiments. The framework brings the three worlds of knowledge graph engineers, distributed computation developers, and data scientists closer together and offers all of them the creation of explainable ML pipelines using a few lines of code.

Endri Kacupaj, Joan Plepi, Kuldeep Singh, Harsh Thakkar, Jens Lehmann, Maria Maleshkova. Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume. 2021.

Manoj Prabhakar Kannan Ravi, Kuldeep Singh, Isaiah Onando Mulang’, Saeedeh Shekarpour, Johannes Hoffart, Jens Lehmann. Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume. 2021.

Knowledge Graph Embeddings (KGEs) have shown promising performance on link prediction tasks by mapping the entities and relations from a knowledge graph into a geometric space.The capability of KGEs in preserving graph characteristics including structural aspects and semantics, highly depends on the design of their score function, as well as the inherited abilities from the underlying geometry.Many KGEs use the Euclidean geometry which renders them incapable of preserving complex structures and consequently causes wrong inferences by the models.To address this problem, we propose a neuro differential KGE that embeds nodes of a KG on the trajectories of Ordinary Differential Equations (ODEs).To this end, we represent each relation (edge) in a KG as a vector field on several manifolds.We specifically parameterize ODEs by a neural network to represent complex manifolds and complex vector fields on the manifolds.Therefore, the underlying embedding space is capable to assume the shape of various geometric forms to encode heterogeneous subgraphs.Experiments on synthetic and benchmark datasets using state-of-the-art KGE models justify the ODE trajectories as a means to enable structure preservation and consequently avoiding wrong inferences.

The automatic evaluation of open-domain dialogues remains a largely unsolved challenge.Thus, despite the abundance of work done in the field, human judges have to evaluate dialogues' quality.As a consequence, performing such evaluations at scale is usually expensive.This work investigates using a deep-learning model trained on the General Language Understanding Evaluation (GLUE) benchmark to serve as a quality indication of open-domain dialogues.The aim is to use the various GLUE tasks as different perspectives on judging the quality of conversation, thus reducing the need for additional training data or responses that serve as quality references.Due to this nature, the method can infer various quality metrics and derive a component-based overall score.We achieve statistically significant correlation coefficients of up to 0.7.

Entity alignment aims to identify equivalent entity pairs between different knowledge graphs (KGs).Recently, the availability of temporal KGs (TKGs) that contain time information created the need for reasoning over time in such TKGs.Existing embeddingbased entity alignment approaches disregard time information that commonly exists in many large-scale KGs, leaving much room for improvement.In this paper, we focus on the task of aligning entity pairs between TKGs and propose a novel Time-aware Entity Alignment approach based on Graph Neural Networks (TEA-GNN).We embed entities, relations and timestamps of different KGs into a vector space and use GNNs to learn entity representations.To incorporate both relation and time information into the GNN structure of our model, we use a time-aware attention mechanism which assigns different weights to different nodes with orthogonal transformation matrices computed from embeddings of the relevant relations and timestamps in a neighborhood.Experimental results on multiple real-world TKG datasets show that our method significantly outperforms the state-ofthe-art methods due to the inclusion of time information.

51

Knowledge graphs (KGs) represent world facts in a structured form. Although knowledge graphs are quantitatively huge and consist of millions of triples, the coverage is still only a small fraction of world's knowledge. Among the top approaches of recent years, link prediction using knowledge graph embedding (KGE) models has gained significant attention for knowledge graph completion. Various embedding models have been proposed so far, among which, some recent KGE models obtain state-of-the-art performance on link prediction tasks by using embeddings with a high dimension (e.g. 1000) which accelerate the costs of training and evaluation considering the large scale of KGs. In this paper, we propose a simple but effective performance boosting strategy for KGE models by using multiple low dimensions in different repetition rounds of the same model. For example, instead of training a model one time with a large embedding size of 1200, we repeat the training of the model 6 times in parallel with an embedding size of 200 and then combine the 6 separate models for testing while the overall numbers of adjustable parameters are same (6*200=1200) and the total memory footprint remains the same. We show that our approach enables different models to better cope with their expressiveness issues on modeling various graph patterns such as symmetric, 1-n, n-1 and n-n. In order to justify our findings, we conduct experiments on various KGE models. Experimental results on standard benchmark datasets, namely FB15K, FB15K-237 and WN18RR, show that multiple low-dimensional models of the same kind outperform the corresponding single high-dimensional models on link prediction in a certain range and have advantages in training efficiency by using parallel training while the overall numbers of adjustable parameters are same.

Chengjin Xu, Yung-Yu Chen, Mojtaba Nayyeri, Jens Lehmann. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2021.

In the context of social media, geolocation inference on news or events has become a very important task. In this paper, we present the GeoWINE (Geolocation-based Wiki-Image-News-Event retrieval) demonstrator, an effective modular system for multimodal retrieval which expects only a single image as input. The GeoWINE system consists of five modules in order to retrieve related information from various sources. The first module is a state-of-the-art model for geolocation estimation of images. The second module performs a geospatial-based query for entity retrieval using the Wikidata knowledge graph. The third module exploits four different image embedding representations, which are used to retrieve most similar entities compared to the input image. The last two modules perform news and event retrieval from EventRegistry and the Open Event Knowledge Graph (OEKG). GeoWINE provides an intuitive interface for end-users and is insightful for experts for reconfiguration to individual setups. The GeoWINE achieves promising results in entity label prediction for images on Google Landmarks dataset. The demonstrator is publicly available at http://cleopatra.ijs.si/geowine/.

SUMMARY: As machine learning and artificial intelligence increasingly attain a larger number of applications in the biomedical domain, at their core, their utility depends on the data used to train them. Due to the complexity and high dimensionality of biomedical data, there is a need for approaches that combine prior knowledge around known biological interactions with patient data. Here, we present CLinical Embedding of Patients (CLEP), a novel approach that generates new patient representations by leveraging both prior knowledge and patient-level data. First, given a patient-level dataset and a knowledge graph containing relations across features that can be mapped to the dataset, CLEP incorporates patients into the knowledge graph as new nodes connected to their most characteristic features. Next, CLEP employs knowledge graph embedding models to generate new patient representations that can ultimately be used for a variety of downstream tasks, ranging from clustering to classification. We demonstrate how using new patient representations generated by CLEP significantly improves performance in classifying between patients and healthy controls for a variety of machine learning models, as compared to the use of the original transcriptomics data. Furthermore, we also show how incorporating patients into a knowledge graph can foster the interpretation and identification of biological features characteristic of a specific disease or patient subgroup. Finally, we released CLEP as an open source Python package together with examples and documentation. AVAILABILITY AND IMPLEMENTATION: CLEP is available to the bioinformatics community as an open source Python package at https://github.com/hybrid-kg/clep under the Apache 2.0 License. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Recently, knowledge graph embeddings (KGEs) have received significant attention, and several software libraries have been developed for training and evaluation. While each of them addresses specific needs, we report on a community effort to a re-design and re-implementation of PyKEEN, one of the early KGE libraries. PyKEEN 1.0 enables users to compose knowledge graph embedding models based on a wide range of interaction models, training approaches, loss functions, and permits the explicit modeling of inverse relations. It allows users to measure each component's influence individually on the model's performance. Besides, an automatic memory optimization has been realized in order to optimally exploit the provided hardware. Through the integration of Optuna, extensive hyper-parameter optimization (HPO) functionalities are provided.

Cooking is an endeavour unique to humans. It is mainly considered an art requiring culinary intuition acquired through practice. The preparation of food is a complex and subjective process that makes it challenging to determine underlying rules for automation. In this paper, we present AutoChef, the first open-source autonomous recipe generator. AutoChef extracts the data from existing recipes using natural language processing, learns the combination of ingredients, preparation actions and cooking instructions, and autonomously generates the recipes. Furthermore, AutoChef uses Genetic Programming to represent and evolve the recipes. The fitness of recipes is designed to evaluate the combination of ingredients, actions and cooking-processes learned from the existing recipe data. Finally, the resulting recipes are translated back into text format and evaluated by human experts.

In this paper, we introduce the MLM (Multiple Languages and Modalities) dataset - a new resource to train and evaluate multitask systems on samples in multiple modalities and three languages. The generation process and inclusion of semantic data provide a resource that further tests the ability for multitask systems to learn relationships between entities. The dataset is designed for researchers and developers who build applications that perform multiple tasks on data encountered on the web and in digital archives. A second version of MLM provides a geo-representative subset of the data with weighted samples for countries of the European Union. We demonstrate the value of the resource in developing novel applications in the digital humanities with a motivating use case and specify a benchmark set of tasks to retrieve modalities and locate entities in the dataset. Evaluation of baseline multitask and single task systems on the full and geo-representative versions of MLM demonstrate the challenges of generalising on diverse data. In addition to the digital humanities, we expect the resource to contribute to research in multimodal representation learning, location estimation, and scene understanding.

Pretrained Transformer models have emerged as state-of-the-art approaches that learn contextual information from the text to improve the performance of several NLP tasks. These models, albeit powerful, still require specialized knowledge in specific scenarios. In this paper, we argue that context derived from a knowledge graph (in our case: Wikidata) provides enough signals to inform pretrained transformer models and improve their performance for named entity disambiguation (NED) on Wikidata KG. We further hypothesize that our proposed KG context can be standardized for Wikipedia, and we evaluate the impact of KG context on the state of the art NED model for the Wikipedia knowledge base. Our empirical results validate that the proposed KG context can be generalized (for Wikipedia), and providing KG context in transformer architectures considerably outperforms the existing baselines, including the vanilla transformer models.

Computer-based systems for communication with humans are a cornerstone of AI research since the 1950s.So far, the most effective way to assess the quality of the dialogues produced by these systems is to use resource-intensive manual labor instead of automated means.In this work, we investigate whether language models (LM) based on transformer neural networks can indicate the quality of a conversation.In a general sense, language models are methods that learn to predict one or more words based on an already given context.Due to their unsupervised nature, they are candidates for efficient, automatic indication of dialogue quality.We demonstrate that human evaluators have a positive correlation between the output of the language models and scores.We also provide some insights into their behavior and inner-working in a conversational context.

In the last few years, there has been a surge of interest in learning representations of entities and relations in knowledge graph (KG).However, the recent availability of temporal knowledge graphs (TKGs) that contain time information for each fact created the need for reasoning over time in such TKGs.In this regard, we present a new approach of TKG embedding, TeRo, which defines the temporal evolution of entity embedding as a rotation from the initial time to the current time in the complex vector space.Specially, for facts involving time intervals, each relation is represented as a pair of dual complex embeddings to handle the beginning and the end of the relation, respectively.We show our proposed model overcomes the limitations of the existing KG embedding models and TKG embedding models and has the ability of learning and inferring various relation patterns over time.Experimental results on four different TKGs show that TeRo significantly outperforms existing state-of-the-art models for link prediction.In addition, we analyze the effect of time granularity on link prediction over TKGs, which as far as we know has not been investigated in previous literature.

Knowledge graph (KG) embedding aims at embedding entities and relations in a KG into a low dimensional latent representation space.Existing KG embedding approaches model entities and relations in a KG by utilizing real-valued , complex-valued, or hypercomplex-valued (Quaternion or Octonion) representations, all of which are subsumed into a geometric algebra.In this work, we introduce a novel geometric algebra-based KG embedding framework, GeomE, which utilizes multivector representations and the geometric product to model entities and relations.Our framework subsumes several state-of-the-art KG embedding approaches and is advantageous with its ability of modeling various key relation patterns, including (anti-)symmetry, inversion and composition, rich expressiveness with higher degree of freedom as well as good generalization capacity.Experimental results on multiple benchmark knowledge graphs show that the proposed approach outperforms existing state-of-the-art models for link prediction.

Over the past decade, knowledge graphs became popular for capturing structured domain knowledge. Relational learning models enable the prediction of missing links inside knowledge graphs. More specifically, latent distance approaches model the relationships among entities via a distance between latent representations. Translating embedding models (e.g., TransE) are among the most popular latent distance approaches which use one distance function to learn multiple relation patterns. However, they are mostly inefficient in capturing symmetric relations since the representation vector norm for all the symmetric relations becomes equal to zero. They also lose information when learning relations with reflexive patterns since they become symmetric and transitive. We propose the Multiple Distance Embedding model (MDE) that addresses these limitations and a framework to collaboratively combine variant latent distance-based terms. Our solution is based on two principles: 1) we use a limit-based loss instead of a margin ranking loss and, 2) by learning independent embedding vectors for each of the terms we can collectively train and predict using contradicting distance terms. We further demonstrate that MDE allows modeling relations with (anti)symmetry, inversion, and composition patterns. We propose MDE as a neural network model that allows us to map non-linear relations between the embedding vectors and the expected output of the score function. Our empirical results show that MDE performs competitively to state-of-the-art embedding models on several benchmark datasets.

The emergence of structured databases for Question Answering (QA) systems has led to developing methods, in which the problem of learning the correct answer efficiently is based on a linking task between the constituents of the question and the corresponding entries in the database. As a result, parsing the questions in order to determine their main elements, which are required for answer retrieval, becomes crucial. However, most datasets for QA systems lack gold annotations for parsing, i.e., labels are only available in the form of (question, formal-query, answer). In this paper, we propose a distantly supervised learning framework based on reinforcement learning to learn the mentions of entities and relations in questions. We leverage the provided formal queries to characterize delayed rewards for optimizing a policy gradient objective for the parsing model. An empirical evaluation of our approach shows a significant improvement in the performance of entity and relation linking compared to the state of the art. We also demonstrate that a more accurate parsing component enhances the overall performance of QA systems.

Hyper-relational knowledge graphs (KGs) (e.g., Wikidata) enable associating additional key-value pairs along with the main triple to disambiguate, or restrict the validity of a fact.In this work, we propose a message passing based graph encoder -STARE capable of modeling such hyper-relational KGs.Unlike existing approaches, STARE can encode an arbitrary number of additional information (qualifiers) along with the main triple while keeping the semantic roles of qualifiers and triples intact.We also demonstrate that existing benchmarks for evaluating link prediction (LP) performance on hyper-relational KGs suffer from fundamental flaws and thus develop a new Wikidata-based dataset -WD50K.Our experiments demonstrate that STARE based LP model outperforms existing approaches across multiple benchmarks.We also confirm that leveraging qualifiers is vital for link prediction with gains up to 25 MRR points compared to triple-based representations.

Question Answering (QA) systems over Knowledge Graphs (KGs) aim to provide a concise answer to a given natural language question. Despite the significant evolution of QA methods over the past years, there are still some core lines of work, which are lagging behind. This is especially true for methods and datasets that support the verbalization of answers in natural language. Specifically, to the best of our knowledge, none of the existing Question Answering datasets provide any verbalization data for the question-query pairs. Hence, we aim to fill this gap by providing the first QA dataset VQuAnDa that includes the verbalization of each answer. We base VQuAnDa on a commonly used large-scale QA dataset – LC-QuAD, in order to support compatibility and continuity of previous work. We complement the dataset with baseline scores for measuring future training and evaluation work, by using a set of standard sequence to sequence models and sharing the results of the experiments. This resource empowers researchers to train and evaluate a variety of models to generate answer verbalizations.

227

Improvements in web technologies and artificial intelligence enable novel, more data-driven research practices for scientists. However, scientific knowledge generated from data-intensive research practices is disseminated with unstructured formats, thus hindering the scholarly communication in various respects. The traditional document-based representation of scholarly information hampers the reusability of research contributions. To address this concern, we developed the Physics Ontology (PhySci) to represent physics-related scholarly data in a machine-interpretable format. PhySci facilitates knowledge exploration, comparison, and organization of such data by representing it as knowledge graphs. It establishes a unique conceptualization to increase the visibility and accessibility to the digital content of physics publications. We present the iterative design principles by outlining a methodology for its development and applying three different evaluation approaches: data-driven and criteria-based evaluation, as well as ontology testing.

Embedding models based on translation and rotation have gained significant attention in link prediction tasks for knowledge graphs. Most of the earlier works have modified the score function of Knowledge Graph Embedding models in order to improve the performance of link prediction tasks. However, as proven theoretically and experimentally, the performance of such Embedding models strongly depends on the loss function. One of the prominent approaches in defining loss functions is to set a margin between positive and negative samples during the learning process. This task is particularly important because it directly affects the learning and ranking of triples and ultimately defines the final output. Approaches for setting a margin have the following challenges: a) the length of the margin has to be fixed manually, b) without a fixed point for center of the margin, the scores of positive triples are not necessarily enforced to be sufficiently small to fulfill the translation/rotation from head to tail by using the relation vector. In this paper, we propose a family of loss functions dubbed SlidE±to address the aforementioned challenges. The formulation of the proposed loss functions enables an automated technique to adjust the length of the margin adaptive to a defined center. In our experiments on a set of standard benchmark datasets including Freebase and WordNet, the effectiveness of our approach is confirmed for training Knowledge Graph Embedding models, specifically TransE and RotatE as a case study, on link prediction tasks.

Dialogue systems for interaction with humans have been enjoying increased popularity in the research and industry fields. To this day, the best way to estimate their success is through means of human evaluation and not automated approaches, despite the abundance of work done in the field. In this paper, we investigate the effectiveness of perceiving dialogue evaluation as an anomaly detection task. The paper looks into four dialogue modeling approaches and how their objective functions correlate with human annotation scores. A high-level perspective exhibits negative results. However, a more in-depth look shows some potential for using anomaly detection for evaluating dialogues.

Attention-based encoder-decoder neural network models have recently shown promising results in goal-oriented dialogue systems. However, these models struggle to reason over and incorporate state-full knowledge while preserving their end-to-end text generation functionality. Since such models can greatly benefit from user intent and knowledge graph integration, in this paper we propose an RNN-based end-to-end encoder-decoder architecture which is trained with joint embeddings of the knowledge graph and the corpus as input. The model provides an additional integration of user intent along with text generation, trained with multi-task learning paradigm along with an additional regularization technique to penalize generating the wrong entity as output. The model further incorporates a Knowledge Graph entity lookup during inference to guarantee the generated output is state-full based on the local knowledge graph provided. We finally evaluated the model using the BLEU score, empirical evaluation depicts that our proposed architecture can aid in the betterment of task-oriented dialogue system’s performance.

Increasing data volumes have extensively increased application possibilities. However, accessing this data in an ad hoc manner remains an unsolved problem due to the diversity of data management approaches, formats and storage frameworks, resulting in the need to effectively access and process distributed heterogeneous data at scale. For years, Semantic Web techniques have addressed data integration challenges with practical knowledge representation models and ontology-based mappings. Leveraging these techniques, we provide a solution enabling uniform access to large, heterogeneous data sources, without enforcing centralization; thus realizing the vision of a Semantic Data Lake. In this paper, we define the core concepts underlying this vision and the architectural requirements that systems implementing it need to fulfill. Squerall, an example of such a system, is an extensible framework built on top of state-of-the-art Big Data technologies. We focus on Squerall's distributed query execution techniques and strategies, empirically evaluating its performance throughout its various sub-phases.

SUMMARY: Knowledge graph embeddings (KGEs) have received significant attention in other domains due to their ability to predict links and create dense representations for graphs' nodes and edges. However, the software ecosystem for their application to bioinformatics remains limited and inaccessible for users without expertise in programing and machine learning. Therefore, we developed BioKEEN (Biological KnowlEdge EmbeddiNgs) and PyKEEN (Python KnowlEdge EmbeddiNgs) to facilitate their easy use through an interactive command line interface. Finally, we present a case study in which we used a novel biological pathway mapping resource to predict links that represent pathway crosstalks and hierarchies. AVAILABILITY AND IMPLEMENTATION: BioKEEN and PyKEEN are open source Python packages publicly available under the MIT License at https://github.com/SmartDataAnalytics/BioKEEN and https://github.com/SmartDataAnalytics/PyKEEN. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Noise is often present in real datasets used for training Machine Learning classifiers. Their disruptive effects in the learning process may include: increasing the complexity of the induced models, a higher processing time and a reduced predictive power in the classification of new examples. Therefore, treating noisy data in a preprocessing step is crucial for improving data quality and to reduce their harmful effects in the learning process. There are various filters using different concepts for identifying noisy examples in a dataset. Their ability in noise preprocessing is usually assessed in the identification of artificial noise injected into one or more datasets. This is performed to overcome the limitation that only a domain expert can guarantee whether a real example is indeed noisy. The most frequently used label noise injection method is the noise at random method, in which a percentage of the training examples have their labels randomly exchanged. This is carried out regardless of the characteristics and example space positions of the selected examples. This paper proposes two novel methods to inject label noise in classification datasets. These methods, based on complexity measures, can produce more challenging and realistic noisy datasets by the disturbance of the labels of critical examples situated close to the decision borders and can improve the noise filtering evaluation. An extensive experimental evaluation of different noise filters is performed using public datasets with imputed label noise and the influence of the noise injection methods are compared in both data preprocessing and classification steps.

Building systems that can communicate with humans is a core problem in Artificial Intelligence.This work proposes a novel neural network architecture for response selection in an end-to-end multi-turn conversational dialogue setting.The architecture applies context level attention and incorporates additional external knowledge provided by descriptions of domain-specific words.It uses a bi-directional Gated Recurrent Unit (GRU) for encoding context and responses and learns to attend over the context words given the latent response representation and vice versa.In addition, it incorporates external domain specific information using another GRU for encoding the domain keyword descriptions.This allows better representation of domain-specific keywords in responses and hence improves the overall performance.Experimental results show that our model outperforms all other state-of-the-art methods for response selection in multi-turn conversations.

In this work, we outline an approach for question answering over regulatory documents. In contrast to traditional means to access information in the domain, the proposed system attempts to deliver an accurate and precise answer to user queries. This is accomplished by a two-step approach which first selects relevant paragraphs given a question; and then compares the selected paragraph with user query to predict a span in the paragraph as the answer. We employ neural network based solutions for each step, and compare them with existing, and alternate baselines. We perform our evaluations with a gold-standard benchmark comprising over 600 questions on the MaRisk regulatory document. In our experiments, we observe that our proposed system outperforms other baselines.

Modern question answering (QA) systems need to flexibly integrate a number of components specialised to fulfil specific tasks in a QA pipeline. Key QA tasks include Named Entity Recognition and Disambiguation, Relation Extraction, and Query Building. Since a number of different software components exist that implement different strategies for each of these tasks, it is a major challenge to select and combine the most suitable components into a QA system, given the characteristics of a question. We study this optimisation problem and train classifiers, which take features of a question as input and have the goal of optimising the selection of QA components based on those features. We then devise a greedy algorithm to identify the pipelines that include the suitable components and can effectively answer the given question. We implement this model within Frankenstein, a QA framework able to select QA components and compose QA pipelines. We evaluate the effectiveness of the pipelines generated by Frankenstein using the QALD and LC-QuAD benchmarks. These results not only suggest that Frankenstein precisely solves the QA optimisation problem but also enables the automatic composition of optimised QA pipelines, which outperform the static Baseline QA pipeline. Thanks to this flexible and fully automated pipeline generation process, new QA components can be easily included in Frankenstein, thus improving the performance of the generated pipelines.

Exploration and analysis of large amounts of machine generated data requires innovative approaches. We propose a combination of Semantic Web and Machine Learning to facilitate the analysis. First, data is collected and converted to RDF according to a schema in the Web Ontology Language OWL. Several components can continue working with the data, to interlink, label, augment, or classify. The size of the data poses new challenges to existing solutions, which we solve in this contribution by transitioning from in-memory to database.

Document similarity is the problem of estimating the degree to which a given pair of documents has similar semantic content. An accurate document similarity measure can improve several enterprise relevant tasks such as document clustering, text mining, and question-answering. In this paper, we show that a document's thematic flow, which is often disregarded by bag-of-word techniques, is pivotal in estimating their similarity. To this end, we propose a novel semantic document similarity framework, called SimDoc. We model documents as topic-sequences, where topics represent latent generative clusters of related words. Then, we use a sequence alignment algorithm to estimate their semantic similarity. We further conceptualize a novel mechanism to compute topic-topic similarity to fine tune our system. In our experiments, we show that SimDoc outperforms many contemporary bag-of-words techniques in accurately computing document similarity, and on practical applications such as document clustering.

Query containment is a fundamental problem in data management with its main application being in global query optimization. A number of SPARQL query containment solvers for SPARQL have been recently developed. To the best of our knowledge, the Query Containment Benchmark (QC-Bench) is the only benchmark for evaluating these containment solvers. However, this benchmark contains a fixed number of synthetic queries, which were handcrafted by its creators. We propose SQCFramework, a SPARQL query containment benchmark generation framework which is able to generate customized SPARQL containment benchmarks from real SPARQL query logs. The framework is flexible enough to generate benchmarks of varying sizes and according to the user-defined criteria on the most important SPARQL features to be considered for query containment benchmarking. This is achieved using different clustering algorithms. We compare state-of-the-art SPARQL query containment solvers by using different query containment benchmarks generated from DBpedia and Semantic Web Dog Food query logs. In addition, we analyze the quality of the different benchmarks generated by SQCFramework.

Being able to access knowledge bases in an intuitive way has been an active area of research over the past years. In particular, several question answering (QA) approaches which allow to query RDF datasets in natural language have been developed as they allow end users to access knowledge without needing to learn the schema of a knowledge base and learn a formal query language. To foster this research area, several training datasets have been created, e.g. in the QALD (Question Answering over Linked Data) initiative. However, existing datasets are insufficient in terms of size, variety or complexity to apply and evaluate a range of machine learning based QA approaches for learning complex SPARQL queries. With the provision of the Large-Scale Complex Question Answering Dataset (LC-QuAD), we close this gap by providing a dataset with 5000 questions and their corresponding SPARQL queries over the DBpedia dataset. In this article, we describe the dataset creation process and how we ensure a high variety of questions, which should enable to assess the robustness and accuracy of the next generation of QA systems for knowledge graphs. These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

A choice of the best computational solution for a particular task is increasingly reliant on experimentation. Even though experiments are often described through text, tables, and figures, their descriptions are often incomplete or confusing. Thus, researchers often have to perform lengthy web searches for reproducing and understanding the results. In order to minimize this gap, vocabularies and ontologies have been proposed for representing data mining and machine learning (ML) experiments. However, we still lack proper tools to export properly these metadata. To this end, we present an open-source library dubbed LOG4MEX which aims at supporting the scientific community to fulfill this gap.

Question Answering (QA) systems over Knowledge Graphs (KG) automatically answer natural language questions using facts contained in a knowledge graph. Simple questions, which can be answered by the extraction of a single fact, constitute a large part of questions asked on the web but still pose challenges to QA systems, especially when asked against a large knowledge resource. Existing QA systems usually rely on various components each specialised in solving different sub-tasks of the problem (such as segmentation, entity recognition, disambiguation, and relation classification etc.). In this work, we follow a quite different approach: We train a neural network for answering simple questions in an end-to-end manner, leaving all decisions to the model. It learns to rank subject-predicate pairs to enable the retrieval of relevant facts given a question. The network contains a nested word/character-level question encoder which allows to handle out-of-vocabulary and rare word problems while still being able to exploit word-level semantics. Our approach achieves results competitive with state-of-the-art end-to-end approaches that rely on an attention mechanism.

We show how to convert OWL Class Expressions to SPARQL queries where the instances of that concept are with a specific ABox equal to the SPARQL query result. Furthermore, we implement and integrate our converter into the CELOE algorithm (Class Expression Learning for Ontology Engineering), where it replaces the position of a traditional OWL reasoner. This will foster the application of structured machine learning to the Semantic Web, since most data is readily available in triple stores. We provide experimental evidence for the usefulness of the bridge. In particular, we show that we can improve the run time of machine learning approaches by several orders of magnitude.

The Wikimedia Commons is an online repository of over twenty-five million freely usable audio, video and still image files, including scanned books, historically significant photographs, animal recordings, illustrative figures and maps. Being volunteer-contributed, these media files have different amounts of descriptive metadata with varying degrees of accuracy. The DBpedia Information Extraction Framework is capable of parsing unstructured text into semi-structured data from Wikipedia and transforming it into RDF for general use, but so far it has only been used to extract encyclopedia-like content. In this paper, we describe the creation of the DBpedia Commons ( DBc ) dataset, which was achieved by an extension of the Extraction Framework to support knowledge extraction from Wikimedia Commons as a media repository. To our knowledge, this is the first complete RDFization of the Wikimedia Commons and the largest media metadata RDF database in the LOD cloud.

Knowledge representation models based on Fuzzy Description Logics (DLs) can provide a foundation for reasoning in intelligent learning environments. While basic DLs are suitable for expressing crisp concepts and binary relationships, Fuzzy DLs are capable of processing degrees of truth/completeness about vague or imprecise information. This paper tackles the issue of representing fuzzy classes using OWL2 in a dataset describing Performance Assessment Results of Students (PARS).

Linked Open Data (LOD) comprises an unprecedented volume of structured data on the Web. However, these datasets are of varying quality ranging from extensively curated datasets to crowdsourced or extracted data of often relatively low quality. We present a methodology for test-driven quality assessment of Linked Data, which is inspired by test-driven software development. We argue that vocabularies, ontologies and knowledge bases should be accompanied by a number of test cases, which help to ensure a basic level of quality. We present a methodology for assessing the quality of linked data resources, based on a formalization of bad smells and data quality problems. Our formalization employs SPARQL query templates, which are instantiated into concrete quality test case queries. Based on an extensive survey, we compile a comprehensive library of data quality test case patterns. We perform automatic test case instantiation based on schema constraints or semi-automatically enriched schemata and allow the user to generate specific test case instantiations that are applicable to a schema or dataset. We provide an extensive evaluation of five LOD datasets, manual test case instantiation for five schemas and automatic test case instantiations for all available schemata registered with Linked Open Vocabularies (LOV). One of the main advantages of our approach is that domain specific semantics can be encoded in the data quality test cases, thus being able to discover data quality problems beyond conventional quality heuristics.

Over the past years, Semantic Web and Linked Data technologies have reached the backend of a considerable number of applications. Consequently, large amounts of RDF data are constantly being made available across the planet. While experts can easily gather information from this wealth of data by using the W3C standard query language SPARQL, most lay users lack the expertise necessary to proficiently interact with these applications. Consequently, non-expert users usually have to rely on forms, query builders, question answering or keyword search tools to access RDF data. However, these tools have so far been unable to explicate the queries they generate to lay users, making it difficult for these users to i) assess the correctness of the query generated out of their input, and ii) to adapt their queries or iii) to choose in an informed manner between possible interpretations of their input. This paper addresses this drawback by presenting SPARQL2NL, a generic approach that allows verbalizing SPARQL queries, i.e., converting them into natural language. Our framework can be integrated into applications where lay users are required to understand SPARQL or to generate SPARQL queries in a direct (forms, query builders) or an indirect (keyword search, question answering) manner. We evaluate our approach on the DBpedia question set provided by QALD-2 within a survey setting with both SPARQL experts and lay users. The results of the 115 filled surveys show that SPARQL2NL can generate complete and easily understandable natural language descriptions. In addition, our results suggest that even SPARQL experts can process the natural language representation of SPARQL queries computed by our approach more efficiently than the corresponding SPARQL queries. Moreover, non-experts are enabled to reliably understand the content of SPARQL queries.

A central component in many applications is the underlying data management layer. In Data-Web applications, the central component of this layer is the triple store. It is thus evident that finding the most adequate store for the application to develop is of crucial importance for individual projects as well as for data integration on the Data Web in general. In this paper, we propose a generic benchmark creation procedure for SPARQL, which we apply to the DBpedia knowledge base. In contrast to previous approaches, our benchmark is based on queries that were actually issued by humans and applications against existing RDF data not resembling a relational schema. In addition, our approach does not only take the query string but also the features of the queries into consideration during the benchmark generation process. Our generic procedure for benchmark creation is based on query-log mining, SPARQL feature analysis and clustering. After presenting the method underlying our benchmark generation algorithm, we use the generated benchmark to compare the popular triple store implementations Virtuoso, Sesame, Jena-TDB, and BigOWLIM.

As an increasing amount of RDF data is published as Linked Data, intuitive ways of accessing this data become more and more important. Question answering approaches have been proposed as a good compromise between intuitiveness and expressivity. Most question answering systems translate questions into triples which are matched against the RDF data to retrieve an answer, typically relying on some similarity metric. However, in many cases, triples do not represent a faithful representation of the semantic structure of the natural language question, with the result that more expressive queries can not be answered. To circumvent this problem, we present a novel approach that relies on a parse of the question to produce a SPARQL template that directly mirrors the internal structure of the question. This template is then instantiated using statistical entity identification and predicate detection. We show that this approach is competitive and discuss cases of questions that can be answered with our approach but not with competing approaches.

Ontologies based on Description Logics (DLs) have proved to be useful in formally sharing knowledge across applications. Recently, several tools have extended ontologies with fuzzy logic capabilities in order to apply ontology-based reasoning to vague and imprecise domains. This paper first analyses the state of the art in tools for fuzzy ontologies management and then describes how some of the most significant ones have been integrated in order to extend an ontology-based Inductive Logic Programming (ILP) system with fuzzy logic capabilities. A fuzzy version of a well-known ILP test case has been developed in order to validate the approach. This research represents a first step towards fuzzy inductive reasoning for OWL ontologies.

It is widely accepted that there is a large disparity between the availability of treatment options and the prevalence of diseases all over the world, thus placing individuals in danger. This disparity is partially caused by the restricted access to information that would allow health care and research policy makers to formulate more appropriate measures to mitigate it. Specifically, this shortage of information is caused by the difficulty in reliably obtaining and integrating data regarding the disease burden and the respective research investments. In response to these challenges, the Linked Data paradigm provides a simple mechanism for publishing and interlinking structured information on the Web. In conjunction with the ever increasing data on diseases and health care research available as Linked Data, an opportunity is created to reduce this information gap that would allow for better policy in response to these disparities. In this paper, we present the ReDD-Observatory, an approach for evaluating the Research-Disease Disparity based on the interlinking and integrating of various biomedical data sources. Specifically, we devise a method for representing statistical information as Linked Data and adopt interlinking algorithms for integrating relevant datasets (mainly GHO, Linked CT and PubMed). The assessment of the disparity is then performed with a number of parametrized SPARQL queries on the integrated data substrate. As a consequence, we are for the first time able to provide reliable indicators for the extent of the research-disease disparity in a semi-automated fashion, thus enabling health care professionals and policy makers to make more informed decisions.

In this paper we present Triplify - a simplistic but effective approach to publish Linked Data from relational databases. Triplify is based on mapping HTTP-URI requests onto relational database queries. Triplify transforms the resulting relations into RDF statements and publishes the data on the Web in various RDF serializations, in particular as Linked Data. The rationale for developing Triplify is that the largest part of information on the Web is already stored in structured form, often as data contained in relational databases, but usually published by Web applications only as HTML mixing structure, layout and content. In order to reveal the pure structured information behind the current Web, we have implemented Triplify as a light-weight software component, which can be easily integrated into and deployed by the numerous, widely installed Web applications. Our approach includes a method for publishing update logs to enable incremental crawling of linked data sources. Triplify is complemented by a library of configurations for common relational schemata and a REST-enabled data source registry. Triplify configurations containing mappings are provided for many popular Web applications, including osCommerce, WordPress, Drupal, Gallery, and phpBB. We will show that despite its light-weight architecture Triplify is usable to publish very large datasets, such as 160GB of geo data from the OpenStreetMap project.

The vision of the Semantic Web is to make use of semantic representations on the largest possible scale - the Web. Large knowledge bases such as DBpedia, OpenCyc, GovTrack, and others are emerging and are freely available as Linked Data and SPARQL endpoints. Exploring and analysing such knowledge bases is a significant hurdle for Semantic Web research and practice. As one possible direction for tackling this problem, the authors present an approach for obtaining complex class descriptions from objects in knowledge bases by using Machine Learning techniques. They describe in detail how we leverage existing techniques to achieve scalability on large knowledge bases available as SPARQL endpoints or Linked Data. Their algorithms are made available in the open source DL-Learner project and we present several real-life scenarios in which they can be used by Semantic Web applications.