In a world where information is exchanged at an increasing pace, knowledge becomes quickly outdated. Formal constructs that capture human knowledge, such as knowledge graphs and ontologies, need to be updated and evaluated to stay relevant and functioning. However, evaluating knowledge models is labour-intensive and prone to errors. This study addresses the challenge of automatically evaluating changes in existing knowledge graphs. We introduce syntactic and semantic metrics tailored for change evaluation. The metrics are implemented and validated through experiments on knowledge graphs across various domains. In these experiments, real-world changes are simulated by removing concepts and introducing faulty ones before measuring the quality with the syntactic and semantic metrics. The hypothesis is that such changes decrease the quality of the knowledge graph: removing concepts influences syntactic qualities such as the structure of the model, while adding faulty concepts affects semantic qualities like model consistency. The validation results support this hypothesis, demonstrating that the introduced metrics effectively reflect the changes made to the graph. Additionally, the experiments show that the size and domain specialisation of a knowledge graph influence how well the metrics detect changes. Overall, this study proposes a novel set of evaluation metrics and provides evidence of their effectiveness for assessing modifications to knowledge graphs across different domains. These metrics can help developers detect errors, highlight unintended side effects, and flag other quality changes that might otherwise go unnoticed.

Type II diabetes is a complex health condition requiring patients to closely and continuously collaborate with healthcare professionals and other caretakers on lifestyle changes. While intelligent products have tremendous potential to support such Diabetes Lifestyle Management (DLM), existing products are typically conceived from a technology-centered perspective that insufficiently acknowledges the degree to which collaboration and inclusion of stakeholders is required. In this article, we argue that the emergent design philosophy of Hybrid Intelligence (HI) forms a suitable alternative lens for research and development. In particular, we (1) highlight a series of pragmatic challenges for effective AI-based DLM support based on results from an expert focus group, and (2) argue for HI’s potential to address these by outlining relevant research trajectories.

Legal texts are often difficult to interpret, and people who interpret them need to make choices about the interpretation. To improve transparency, the interpretation of a legal text can be made explicit by formalising it. However, creating formalised representations of legal texts manually is quite labour-intensive. In this paper, we describe a method to extract structured representations in the Flint language (van Doesburg and van Engers, 2019) from natural language. Automated extraction of knowledge representation not only makes the interpretation and modelling efforts more efficient, it also contributes to reducing inter-coder dependencies. The Flint language offers a formal model that enables the interpretation of legal text by describing the norms in these texts as acts, facts and duties. To extract the components of a Flint representation, we use a rule-based method and a transformer-based method. In the transformer-based method we fine-tune the last layer with annotated legal texts. The results show that the transformed-based method (80% accuracy) outperforms the rule-based method (42% accuracy) on the Dutch Aliens Act. This indicates that the transformer-based method is a promising approach of automatically extracting Flint frames.

Abstract The unification of statistical (data-driven) and symbolic (knowledge-driven) methods is widely recognized as one of the key challenges of modern AI. Recent years have seen a large number of publications on such hybrid neuro-symbolic AI systems. That rapidly growing literature is highly diverse, mostly empirical, and is lacking a unifying view of the large variety of these hybrid systems. In this paper, we analyze a large body of recent literature and we propose a set of modular design patterns for such hybrid, neuro-symbolic systems. We are able to describe the architecture of a very large number of hybrid systems by composing only a small set of elementary patterns as building blocks. The main contributions of this paper are: 1) a taxonomically organised vocabulary to describe both processes and data structures used in hybrid systems; 2) a set of 15+ design patterns for hybrid AI systems organized in a set of elementary patterns and a set of compositional patterns; 3) an application of these design patterns in two realistic use-cases for hybrid AI systems. Our patterns reveal similarities between systems that were not recognized until now. Finally, our design patterns extend and refine Kautz’s earlier attempt at categorizing neuro-symbolic architectures.

Creating ontologies is an expensive task. Our vision is that we can automatically generate ontologies based on a set of relevant documents to create a kick-start in ontology creating sessions. In this paper, we focus on enhancing two often used methods, OpenIE and co-occurrences. We evaluate the methods on two document sets, one about pizza and one about the agriculture domain. The methods are evaluated using two types of F1-score (objective, quantitative) and through a human assessment (subjective, qualitative). The results show that 1) Cooc performs both objectively and subjectively better than OpenIE; 2) the filtering methods based on keywords and on Word2vec perform similarly; 3) the filtering methods both perform better compared to OpenIE and similar to Cooc; 4) Cooc-NVP performs best, especially considering the subjective evaluation. Although, the investigated methods provide a good start for extracting an ontology out of a set of domain documents, various improvements are still possible, especially in the natural language based methods.

General captioning practice involves a single forward prediction, with the aim of predicting the word in the next timestep given the word in the current timestep. In this paper, we present a novel captioning framework, namely Dual Prediction Network (DPN), which is end-to-end trainable and addresses the captioning problem with dual predictions. Specifically, the dual predictions consist of a forward prediction to generate the next word from the current input word, as well as a backward prediction to reconstruct the input word using the predicted word. DPN has two appealing properties: 1) By introducing an extra supervision signal on the prediction, DPN can better capture the interplay between the input and the target; 2) Utilizing the reconstructed input, DPN can make another new prediction. During the test phase, we average both predictions to formulate the final target sentence. Experimental results on the MS COCO dataset demonstrate that, benefiting from the reconstruction step, both generated predictions in DPN outperform the predictions of methods based on the general captioning practice (single forward prediction), and averaging them can bring a further accuracy boost. Overall, DPN achieves competitive results with state-of-the-art approaches, across multiple evaluation metrics.

Big Data Applications (BDAs) are used to support a decision making process, but their developers and users are often unaware of the exact uncertainties that underlie the output of BDAs. In this paper we present a System for Uncertainty Decision Support (SUDS) as a generic plug-in for BDAs that aims to give both developers and users more insight in the location, types and propagation of uncertainties within a BDA. To achieve this, SUDS receives uncertainty information directly from the BDA and provides a separate front-end where the uncertainties can be explored and queried. SUDS combines state of the art methods in knowledge modelling, natural language processing and big data architectures.

In content based video retrieval videos are often indexed with semantic labels ( concepts ) using pre-trained classifiers. These pre-trained classifiers ( concept detectors ), are not perfect, and thus the labels are noisy. Additionally, the amount of pre-trained classifiers is limited. Often automatic methods cannot represent the query adequately in terms of the concepts available. This problem is also apparent in the retrieval of events, such as bike trick or birthday party . Our solution is to obtain user feedback. This user feedback can be provided on two levels: concept level and video level . We introduce the method Adaptive Relevance Feedback ( ARF ) on video level feedback. ARF is based on the classical Rocchio relevance feedback method from Information Retrieval. Furthermore, we explore methods on concept level feedback, such as the re-weighting and Query Point Modification (QPM) methods as well as a method that changes the semantic space the concepts are represented in. Methods on both concept level and video level are evaluated on the international benchmark TRECVID Multimedia Event Detection (MED) and compared to state of the art methods. Results show that relevance feedback on both concept and video level improves performance compared to using no relevance feedback; relevance feedback on video level obtains higher performance compared to relevance feedback on concept level; our proposed ARF method on video level outperforms a state of the art k-NN method, all methods on concept level and even manually selected concepts.

Searching in digital video data for high-level events, such as a parade or a car accident, is challenging when the query is textual and lacks visual example images or videos. Current research in deep neural networks is highly beneficial for the retrieval of high-level events using visual examples, but without examples it is still hard to (1) determine which concepts are useful to pre-train ( Vocabulary challenge ) and (2) which pre-trained concept detectors are relevant for a certain unseen high-level event ( Concept Selection challenge ). In our article, we present our Semantic Event Retrieval System which (1) shows the importance of high-level concepts in a vocabulary for the retrieval of complex and generic high-level events and (2) uses a novel concept selection method ( i-w2v ) based on semantic embeddings. Our experiments on the international TRECVID Multimedia Event Detection benchmark show that a diverse vocabulary including high-level concepts improves performance on the retrieval of high-level events in videos and that our novel method outperforms a knowledge-based concept selection method.

Complex video event detection without visual examples is a very challenging issue in multimedia retrieval. We present a state-of-the-art framework for event search without any need of exemplar videos and textual metadata in search corpus. To perform event search given only query words, the core of our framework is a large, pre-built bank of concept detectors which can understand the content of a video in the perspective of object, scene, action and activity concepts. Leveraging such knowledge can effectively narrow the semantic gap between textual query and the visual content of videos. Besides the large concept bank, this paper focuses on two challenges that largely affect the retrieval performance when the size of the concept bank increases: (1) How to choose the right concepts in the concept bank to accurately represent the query; (2) if noisy concepts are inevitably chosen, how to minimize their influence. We share our novel insights on these particular problems, which paves the way for a practical system that achieves the best performance in NIST TRECVID 2015.

A common approach in content based video information retrieval is to perform automatic shot annotation with semantic labels using pre-trained classifiers. The visual vocabulary of state-of-the-art automatic annotation systems is limited to a few thousand concepts, which creates a semantic gap between the semantic labels and the natural language query. One of the methods to bridge this semantic gap is to expand the original user query using knowledge bases. Both common knowledge bases such as Wikipedia and expert knowledge bases such as a manually created ontology can be used to bridge the semantic gap. Expert knowledge bases have highest performance, but are only available in closed domains. Only in closed domains all necessary information, including structure and disambiguation, can be made available in a knowledge base. Common knowledge bases are often used in open domain, because it covers a lot of general information. In this research, query expansion using common knowledge bases ConceptNet and Wikipedia is compared to an expert description of the topic applied to content-based information retrieval of complex events. We run experiments on the Test Set of TRECVID MED 2014. Results show that 1) Query Expansion can improve performance compared to using no query expansion in the case that the main noun of the query could not be matched to a concept detector; 2) Query expansion using expert knowledge is not necessarily better than query expansion using common knowledge; 3) ConceptNet performs slightly better than Wikipedia; 4) Late fusion can slightly improve performance. To conclude, query expansion has potential in complex event detection.