Large-scale knowledge graphs (KGs) provide structured representations of human knowledge. However, as it is impossible to contain all knowledge, KGs are usually incomplete. Reasoning based on existing facts paves a way to discover missing facts. In this paper, we study the problem of learning logic rules for reasoning on knowledge graphs for completing missing factual triplets. Learning logic rules equips a model with strong interpretability as well as the ability to generalize to similar tasks. We propose a model called MPLR that improves the existing models to fully use training data and multi-target scenarios are considered. In addition, considering the deficiency in evaluating the performance of models and the quality of mined rules, we further propose two novel indicators to help with the problem. Experimental results empirically demonstrate that our MPLR model outperforms state-of-the-art methods on five benchmark datasets. The results also prove the effectiveness of the indicators.

Natural Language Interfaces to Databases (NLIDBs), where users pose queries in Natural Language (NL), are crucial for enabling non-experts to gain insights from data. Developing such interfaces, by contrast, is dependent on experts who often code heuristics for mapping NL to SQL. Alternatively, NLIDBs based on machine learning models rely on supervised examples of NL to SQL mappings (NL-SQL pairs) used as training data. Such examples are again procured using experts, which typically involves more than a one-off interaction. Namely, each data domain in which the NLIDB is deployed may have different characteristics and therefore require either dedicated heuristics or domain-specific training examples. To this end, we propose an alternative approach for training machine learning-based NLIDBs, using weak supervision. We use the recently proposed question decomposition representation called QDMR, an intermediate between NL and formal query languages. Recent work has shown that non-experts are generally successful in translating NL to QDMR. We consequently use NL-QDMR pairs, along with the question answers, as supervision for automatically synthesizing SQL queries. The NL questions and synthesized SQL are then used to train NL-to-SQL models, which we test on five benchmark datasets. Extensive experiments show that our solution, requiring zero expert annotations, performs competitively with models trained on expert annotated data.

Advances in mobile computing have paved the way for the development of several health applications using smartphone as a platform for data acquisition, analysis and presentation. Such areas where mhealth systems have been extensively deployed include monitoring of long term health conditions like Cardio Vascular Diseases and pulmonary disorders, as well as detection of changes from baseline measurements of such conditions. Asthma is one of the respiratory conditions with growing concern across the globe due to the economic, social and emotional burden associated with the ailment. The management and control of asthma can be improved by consistent monitoring of the condition in realtime since attack could occur anytime and anywhere. This paper proposes the use of smartphone equipped with embedded sensors, to capture and analyze early symptoms of asthma triggered by exercise. The system design is based on Decision Support System techniques for measuring and analyzing the level and type of patients physical activity as well as weather conditions that predispose asthma attack. Preliminary results show that smartphones can be used to monitor and detect asthma symptoms without other networked devices. This would enhance the usability of the health system while ensuring users data privacy, and reducing the overall cost of system deployment. Further, the proposed system can serve as a handy tool for a quick medical response for asthmatics in low income countries where there are limited access to specialized medical devices and shortages of health professionals. Development of such monitoring systems signals a positive response to lessen the global burden of asthma.

In the process industry, condition monitoring systems with automated fault diagnosis methods assisthuman experts and thereby improve maintenance efficiency, process sustainability, and workplace safety.Improving the automated fault diagnosis methods using data and machine learning-based models is a centralaspect of intelligent fault diagnosis (IFD). A major challenge in IFD is to develop realistic datasets withaccurate labels needed to train and validate models, and to transfer models trained with labeled lab datato heterogeneous process industry environments. However, fault descriptions and work-orders written bydomain experts are increasingly digitized in modern condition monitoring systems, for example in the contextof rotating equipment monitoring. Thus, domain-specific knowledge about fault characteristics and severitiesexists as technical language annotations in industrial datasets. Furthermore, recent advances in naturallanguage processing enable weakly supervised model optimization using natural language annotations, mostnotably in the form ofnatural language supervision(NLS). This creates a timely opportunity to developtechnical language supervision(TLS) solutions for IFD systems grounded in industrial data, for exampleas a complement to pre-training with lab data to address problems like overfitting and inaccurate out-of-sample generalisation. We surveyed the literature and identify a considerable improvement in the maturityof NLS over the last two years, facilitating applications beyond natural language; a rapid development ofweak supervision methods; and transfer learning as a current trend in IFD which can benefit from thesedevelopments. Finally, we describe a framework for integration of TLS in IFD which is inspired by recentNLS innovations.

Knowledge Base Question Answering (KBQA) aims to answer natural language questions with the help of an external knowledge base. The core idea is to find the link between the internal knowledge behind questions and known triples of the knowledge base. The KBQA task pipeline contains several steps, including entity recognition, entity linking, answering selection, etc. This kind of pipeline method means that errors in any procedure will inevitably propagate to the final prediction. To address this challenge, this paper proposes a Corpus Generation - Retrieve Method (CGRM) with Pre-training Language Model (PLM) for the KBQA task. The major novelty lies in the design of the new method, wherein our approach, the knowledge enhanced T5 (kT5) model aims to generate natural language QA pairs based on Knowledge Graph triples and directly solve the QA by only retrieving the synthetic dataset. The new method can extract more information about the entities from PLM to improve accuracy and simplify the processes. We test our method on NLPCC-ICCPOL 2016 KBQA dataset, and the results show that our method improves the performance of KBQA and the out straight-forward method is competitive with the state-of-the-art.

The idea of representing symbolic knowledge in connectionist systems has been a long-standing endeavour which has attracted much attention recently with the objective of combining machine learning and scalable sound reasoning. Early work has shown a correspondence between propositional logic and symmetrical neural networks which nevertheless did not scale well with the number of variables and whose training regime was inefficient. In this paper, we introduce Logical Boltzmann Machines (LBM), a neurosymbolic system that can represent any propositional logic formula in strict disjunctive normal form. We prove equivalence between energy minimization in LBM and logical satisfiability thus showing that LBM is capable of sound reasoning. We evaluate reasoning empirically to show that LBM is capable of finding all satisfying assignments of a class of logical formulae by searching fewer than 0.75% of the possible (approximately 1 billion) assignments. We compare learning in LBM with a symbolic inductive logic programming system, a state-of-the-art neurosymbolic system and a purely neural network-based system, achieving better learning performance in five out of seven data sets.

In this paper, we discuss Semantic Construction Grammar (SCG), a system developed over the past several years to facilitate translation between natural language and logical representations. Crucially, SCG is designed to support a variety of different methods of representation, ranging from those that are fairly close to the NL structure (e.g. so-called 'logical forms'), to those that are quite different from the NL structure, with higher-order and high-arity relations. Semantic constraints and checks on representations are integral to the process of NL understanding with SCG, and are easily carried out due to the SCG's integration with Cyc's Knowledge Base and inference engine.

Today's battlefield environment is complex, dynamic and uncertain, and requires efficient support to ensure mission success. This relies on a proper support strategy to provide supported equipment able to fulfill the mission. In the context of defense where both systems and organization are complex, having a holistic approach is challenging by nature, forces and support agencies need to rely on an efficient decision support system. Logistics, readiness and sustainability are critical factors for asset management, which can benefit from AI to reach "Smart In Service" level relying especially on predictive and prescriptive approaches and on effective management of operational re-sources. Smart Support capacities can be then monitored by appropriate metrics and improved by multi-criteria decision support and knowledge management system. Depending on the operational context in terms of information and the objective, different AI paradigms (data-driven AI, knowledge-based AI) are suitable even a combination through hybrid AI.

In the first article of this series, we have established a patient centric semantic net and discussed structure and possible content of such a net. In this article, we are going to discuss frames and thematic role systems and why they are important in the functioning of an intelligent agent. They are typically top-down knowledge-based structures that sets expectation about one or more events. For example, consider the Diabetes type 2 drug Thiazolidinediones. As a result this medication should not be prescribed to patients with kidney disease or heart problems.

Web-based technology holds great potential for enabling the rapid dissemination of information and facilitating distributed decision-making. This paper presents a novel knowledge-based multi-agent system for remote fault diagnosis, which is composed of diagnostic and learning agents (DLAs), machine agents (MAs) and a central management agent (CMA). Machines are remotely diagnosed by the DLAs through the communication channels between the MAs and the DLAs. In addition, the DLAs can learn new expertise from the users, and the CMA can update the central knowledge base (CKB) shared by all the DLAs with the valuable expertise. When faults that cannot be solved with the present knowledge base occur, the DLA can acquire new knowledge, translate it into rules using a rule builder, and update the rules into the CKB.