Knowledge base question answering (KBQA) is an important task in Natural Language Processing. Existing approaches face significant challenges including complex question understanding, necessity for reasoning, and lack of large end-to-end training datasets. In this work, we propose Neuro-Symbolic Question Answering (NSQA), a modular KBQA system, that leverages (1) Abstract Meaning Representation (AMR) parses for task-independent question understanding; (2) a simple yet effective graph transformation approach to convert AMR parses into candidate logical queries that are aligned to the KB; (3) a pipeline-based approach which integrates multiple, reusable modules that are trained specifically for their individual tasks (semantic parser, entity and relationship linkers, and neuro-symbolic reasoner) and do not require end-to-end training data. NSQA achieves state-of-the-art performance on two prominent KBQA datasets based on DBpedia (QALD-9 and LC-QuAD 1.0). Furthermore, our analysis emphasizes that AMR is a powerful tool for KBQA systems.

No abstract

Background: The utilization of deceased donor kidneys to initiate chains of living donor kidney paired donation (KPD) has been proposed, although the potential gain of this practice needs to be quantified and the ethical implications must be addressed before starting its application. Methods: The gain of implementing deceased donor-initiated chains has been measured through a mathematical algorithm, using retrospective data on the pool of donor/recipient incompatible pairs at a single Center. Allocation rules of chain ending kidneys and characteristics/quality of the chain initiating kidney (CIK) are described. Results: the quantification of benefit analysis showed that with a pool of 69 kidneys from deceased donors and 16 pairs enrolled in the KPD program, over a period of 3 years it is possible to transplant 8/16 recipients (50%). Following the approval of the Bioethical Committee of the Veneto Region and the revision of the allocation policies by the Italian National Transplant Center, the first successful case has been performed. The waiting time of the recipient (male, 53 yo) after entering the program for the CIK with a kidney donor risk index (KDRI) equal to 0.61 and a kidney donor profile index (KDPI) of 3%, was 4 days. His willing donor (female, 53 yo) with a living kidney donor profile index (LKDPI) of 2, donated 2 days later to a chain ending recipient (male, 47 yo,) who had been on dialysis for 5 years. Conclusions: This is the first report of a deliberate deceased donor-initiated chain, which has been successfully performed. This has been made possible thanks to an extensive phase of evaluation of the ethical issues and allocation policy impact. This paper includes a preliminary efficacy assessment and the development a dedicated algorithm.

Scientists aim to discover meaningful formulae that accurately describe experimental data. Mathematical models of natural phenomena can be manually created from domain knowledge and fitted to data, or, in contrast, created automatically from large datasets with machine-learning algorithms. The problem of incorporating prior knowledge expressed as constraints on the functional form of a learned model has been studied before, while finding models that are consistent with prior knowledge expressed via general logical axioms is an open problem. We develop a method to enable principled derivations of models of natural phenomena from axiomatic knowledge and experimental data by combining logical reasoning with symbolic regression. We demonstrate these concepts for Kepler’s third law of planetary motion, Einstein’s relativistic time-dilation law, and Langmuir’s theory of adsorption. We show we can discover governing laws from few data points when logical reasoning is used to distinguish between candidate formulae having similar error on the data.

In many machine learning scenarios, looking for the best classifier that fits a particular dataset can be very costly in terms of time and resources. Moreover, it can require deep knowledge of the specific domain. We propose a new technique which does not require profound expertise in the domain and avoids the commonly used strategy of hyper-parameter tuning and model selection. Our method is an innovative ensemble technique that uses voting rules over a set of randomly-generated classifiers. Given a new input sample, we interpret the output of each classifier as a ranking over the set of possible classes. We then aggregate these output rankings using a voting rule, which treats them as preferences over the classes. We show that our approach obtains good results compared to the state-of-the-art, both providing a theoretical analysis and an empirical evaluation of the approach on several datasets.