Logical reasoning is central to human cognition and intelligence. Past research of logical reasoning within AI uses formal language as knowledge representation~(and symbolic reasoners). However, reasoning with formal language has proved challenging~(e.g., brittleness and knowledge-acquisition bottleneck). This paper provides a comprehensive overview on a new paradigm of logical reasoning, which uses natural language as knowledge representation~(and pretrained language models as reasoners), including philosophical definition and categorization of logical reasoning, advantages of the new paradigm, benchmarks and methods, challenges of the new paradigm, desirable tasks & methods in the future, and relation to related NLP fields. This new paradigm is promising since it not only alleviates many challenges of formal representation but also has advantages over end-to-end neural methods.

Structured knowledge bases (KBs) are a foundation of many intelligent applications, yet are notoriously incomplete. Language models (LMs) have recently been proposed for unsupervised knowledge base completion (KBC), yet, despite encouraging initial results, questions regarding their suitability remain open. Existing evaluations often fall short because they only evaluate on popular subjects, or sample already existing facts from KBs. In this work, we introduce a novel, more challenging benchmark dataset, and a methodology tailored for a realistic assessment of the KBC potential of LMs. For automated assessment, we curate a dataset called WD-KNOWN, which provides an unbiased random sample of Wikidata, containing over 3.9 million facts. In a second step, we perform a human evaluation on predictions that are not yet in the KB, as only this provides real insights into the added value over existing KBs. Our key finding is that biases in dataset conception of previous benchmarks lead to a systematic overestimate of LM performance for KBC. However, our results also reveal strong areas of LMs. We could, for example, perform a significant completion of Wikidata on the relations nativeLanguage, by a factor of ~21 (from 260k to 5.8M) at 82% precision, usedLanguage, by a factor of ~2.1 (from 2.1M to 6.6M) at 82% precision, and citizenOf by a factor of ~0.3 (from 4.2M to 5.3M) at 90% precision. Moreover, we find that LMs possess surprisingly strong generalization capabilities: even on relations where most facts were not directly observed in LM training, prediction quality can be high.

Similarities between entities occur frequently in many real-world scenarios. For over a century, researchers in different fields have proposed a range of approaches to measure the similarity between entities. More recently, inspired by "Google Sets", significant academic and commercial efforts have been devoted to expanding a given set of entities with similar ones. As a result, existing approaches nowadays are able to take into account properties shared by entities, hereinafter called nexus of similarity. Accordingly, machines are largely able to deal with both similarity measures and set expansions. To the best of our knowledge, however, there is no way to characterize nexus of similarity between entities, namely identifying such nexus in a formal and comprehensive way so that they are both machine- and human-readable; moreover, there is a lack of consensus on evaluating existing approaches for weakly similar entities. As a first step towards filling these gaps, we aim to complement existing literature by developing a novel logic-based framework to formally and automatically characterize nexus of similarity between tuples of entities within a knowledge base. Furthermore, we analyze computational complexity aspects of this framework.

Deductive domains are typical of many cognitive skills in that no single problem-solving strategy is always optimal for solving all problems. It was shown that students who know how and when to use each strategy (StrTime) outperformed those who know neither and stick to the default strategy (Default). In this work, students were trained on a logic tutor that supports a default forward-chaining and a backward-chaining (BC) strategy, then a probability tutor that only supports BC. We investigated three types of interventions on teaching the Default students how and when to use which strategy on the logic tutor: Example, Nudge and Presented. Meanwhile, StrTime students received no interventions. Overall, our results show that Nudge outperformed their Default peers and caught up with StrTime on both tutors.

Metacognitive skills have been commonly associated with preparation for future learning in deductive domains. Many researchers have regarded strategy- and time-awareness as two metacognitive skills that address how and when to use a problem-solving strategy, respectively. It was shown that students who are both strategy-and time-aware (StrTime) outperformed their nonStrTime peers across deductive domains. In this work, students were trained on a logic tutor that supports a default forward-chaining (FC) and a backward-chaining (BC) strategy. We investigated the impact of mixing BC with FC on teaching strategy- and time-awareness for nonStrTime students. During the logic instruction, the experimental students (Exp) were provided with two BC worked examples and some problems in BC to practice how and when to use BC. Meanwhile, their control (Ctrl) and StrTime peers received no such intervention. Six weeks later, all students went through a probability tutor that only supports BC to evaluate whether the acquired metacognitive skills are transferred from logic. Our results show that on both tutors, Exp outperformed Ctrl and caught up with StrTime.

Despite the great current relevance of Artificial Intelligence, and the extraordinary innovations that this discipline has brought to many fields -among which, without a doubt, medicine is found-, experts in medical applications of Artificial Intelligence are looking for new alternatives to solve problems for which current Artificial Intelligence programs do not provide with optimal solutions. For this, one promising option could be the use of the concepts and ideas of Quantum Mechanics, for the construction of quantum-based Artificial Intelligence systems. From a hybrid classical-quantum perspective, this article deals with the application of quantum computing techniques for the staging of Invasive Ductal Carcinoma of the breast. It includes: (1) a general explanation of a classical, and well-established, approach for medical reasoning, (2) a description of the clinical problem, (3) a conceptual model for staging invasive ductal carcinoma, (4) some basic notions about Quantum Rule-Based Systems, (5) a step-by-step explanation of the proposed approach for quantum staging of the invasive ductal carcinoma, and (6) the results obtained after running the quantum system on a significant number of use cases. A detailed discussion is also provided at the end of this paper.

Knowledge plays a critical role in artificial intelligence. Recently, the extensive success of pre-trained language models (PLMs) has raised significant attention about how knowledge can be acquired, maintained, updated and used by language models. Despite the enormous amount of related studies, there still lacks a unified view of how knowledge circulates within language models throughout the learning, tuning, and application processes, which may prevent us from further understanding the connections between current progress or realizing existing limitations. In this survey, we revisit PLMs as knowledge-based systems by dividing the life circle of knowledge in PLMs into five critical periods, and investigating how knowledge circulates when it is built, maintained and used. To this end, we systematically review existing studies of each period of the knowledge life cycle, summarize the main challenges and current limitations, and discuss future directions.

Every novel technology adds hidden vulnerabilities ready to be exploited by a growing number of cyber-attacks. Automated software testing can be a promising solution to quickly analyze thousands of lines of code by generating and slightly modifying function-specific testing data to encounter a multitude of vulnerabilities and attack vectors. This process draws similarities to the constrained adversarial examples generated by adversarial learning methods, so there could be significant benefits to the integration of these methods in automated testing tools. Therefore, this systematic review is focused on the current state-of-the-art of constrained data generation methods applied for adversarial learning and software testing, aiming to guide researchers and developers to enhance testing tools with adversarial learning methods and improve the resilience and robustness of their digital systems. The found constrained data generation applications for adversarial machine learning were systematized, and the advantages and limitations of approaches specific for software testing were thoroughly analyzed, identifying research gaps and opportunities to improve testing tools with adversarial attack methods.

Acoustic-based fault detection has a high potential to monitor the health condition of mechanical parts. However, the background noise of an industrial environment may negatively influence the performance of fault detection. Limited attention has been paid to improving the robustness of fault detection against industrial environmental noise. Therefore, we present the Lenze production background-noise (LPBN) real-world dataset and an automated and noise-robust auditory inspection (ARAI) system for the end-of-line inspection of geared motors. An acoustic array is used to acquire data from motors with a minor fault, major fault, or which are healthy. A benchmark is provided to compare the psychoacoustic features with different types of envelope features based on expert knowledge of the gearbox. To the best of our knowledge, we are the first to apply time-varying psychoacoustic features for fault detection. We train a state-of-the-art one-class-classifier, on samples from healthy motors and separate the faulty ones for fault detection using a threshold. The best-performing approaches achieve an area under curve of 0.87 (logarithm envelope), 0.86 (time-varying psychoacoustics), and 0.91 (combination of both).

We propose a new framework for combining entity resolution and query answering in knowledge bases (KBs) with tuple-generating dependencies (tgds) and equality-generating dependencies (egds) as rules. We define the semantics of the KB in terms of special instances that involve equivalence classes of entities and sets of values. Intuitively, the former collect all entities denoting the same real-world object, while the latter collect all alternative values for an attribute. This approach allows us to both resolve entities and bypass possible inconsistencies in the data. We then design a chase procedure that is tailored to this new framework and has the feature that it never fails; moreover, when the chase procedure terminates, it produces a universal solution, which in turn can be used to obtain the certain answers to conjunctive queries. We finally discuss challenges arising when the chase does not terminate.