Artificial Intelligence models are becoming increasingly more powerful and accurate, supporting or even replacing humans' decision making. But with increased power and accuracy also comes higher complexity, making it hard for users to understand how the model works and what the reasons behind its predictions are. Humans must explain and justify their decisions, and so do the AI models supporting them in this process, making semantic interpretability an emerging field of study. In this work, we look at interpretability from a broader point of view, going beyond the machine learning scope and covering different AI fields such as distributional semantics and fuzzy logic, among others. We examine and classify the models according to their nature and also based on how they introduce interpretability features, analyzing how each approach affects the final users and pointing to gaps that still need to be addressed to provide more human-centered interpretability solutions.

Lack of labeled training data is a major bottleneck for neural network based aspect and opinion term extraction on product reviews. To alleviate this problem, we first propose an algorithm to automatically mine extraction rules from existing training examples based on dependency parsing results. The mined rules are then applied to label a large amount of auxiliary data. Finally, we study training procedures to train a neural model which can learn from both the data automatically labeled by the rules and a small amount of data accurately annotated by human. Experimental results show that although the mined rules themselves do not perform well due to their limited flexibility, the combination of human annotated data and rule labeled auxiliary data can improve the neural model and allow it to achieve performance better than or comparable with the current state-of-the-art.

In this paper, we introduce a novel method to generate interpretable regression function estimators. The idea is based on called data-dependent coverings. The aim is to extract from the data a covering of the feature space instead of a partition. The estimator predicts the empirical conditional expectation over the cells of the partitions generated from the coverings. Thus, such estimator has the same form as those issued from data-dependent partitioning algorithms. We give sufficient conditions to ensure the consistency, avoiding the sufficient condition of shrinkage of the cells that appears in the former literature. Doing so, we reduce the number of covering elements. We show that such coverings are interpretable and each element of the covering is tagged as significant or insignificant. The proof of the consistency is based on a control of the error of the empirical estimation of conditional expectations which is interesting on its own.

Fuzzy cognitive maps (FCMs) model feedback causal relations in interwoven webs of causality and policy variables. FCMs are fuzzy signed directed graphs that allow degrees of causal influence and event occurrence. Such causal models can simulate a wide range of policy scenarios and decision processes. Their directed loops or cycles directly model causal feedback. Their nonlinear dynamics permit forward-chaining inference from input causes and policy options to output effects. Users can add detailed dynamics and feedback links directly to the causal model or infer them with statistical learning laws. Users can fuse or combine FCMs from multiple experts by weighting and adding the underlying fuzzy edge matrices and do so recursively if needed. The combined FCM tends to better represent domain knowledge as the expert sample size increases if the expert sample approximates a random sample. Many causal models use more restrictive directed acyclic graphs (DAGs) and Bayesian probabilities. DAGs do not model causal feedback because they do not contain closed loops. Combining DAGs also tends to produce cycles and thus tends not to produce a new DAG. Combining DAGs tends to produce a FCM. FCM causal influence is also transitive whereas probabilistic causal influence is not transitive in general. Overall: FCMs trade the numerical precision of probabilistic DAGs for pattern prediction, faster and scalable computation, ease of combination, and richer feedback representation. We show how FCMs can apply to problems of public support for insurgency and terrorism and to US-China conflict relations in Graham Allison's Thucydides-trap framework. The appendix gives the textual justification of the Thucydides-trap FCM. It also extends our earlier theorem [Osoba-Kosko2017] to a more general result that shows the transitive and total causal influence that upstream concept nodes exert on downstream nodes.

Rule-based systems play a critical role in health and safety, where policies created by experts are usually formalised as rules. When dealing with increasingly large and dynamic sources of data, as in the case of Internet of Things (IoT) applications, it becomes important not only to efficiently apply rules, but also to reason about their applicability on datasets confined by a certain schema. In this paper we define the notion of a triplestore schema which models a set of RDF graphs. Given a set of rules and such a schema as input we propose a method to determine rule applicability and produce output schemas. Output schemas model the graphs that would be obtained by running the rules on the graph models of the input schema. We present two approaches: one based on computing a canonical (critical) instance of the schema, and a novel approach based on query rewriting. We provide theoretical, complexity and evaluation results that show the superior efficiency of our rewriting approach.

Specifically, we use hunger and loneliness as a basis Foraging [1] is a collective robotics problem that derives to design rules of interaction for the swarm. The paper is biological inspiration from the behavior of ants [2]. Ants organized as follows: In the next section, we first present engaged in foraging, scout for prey, recruit nest mates when the biological foundations that our metaheuristic is founded prey has been located, and work together as a group to upon. We continue by describing the metaheuristic in detail bring back food to the nest. Foraging belongs to a class of and a broader description of the different behaviors exhibited problems known as coverage problems [3].

It was only a few weeks ago that Microsoft announced enhancements heading to Power BI and PowerApps, its no-code business analytics service and web apps design platforms, respectively. But that didn't stop it from unveiling yet another set of features during the Microsoft Business Applications Summit in Atlanta, Georgia this week, where the company took the wraps off a new look for Power BI and improvements in Microsoft Flow, a service which lets users create rule-based workflows that automatically trigger actions, along with improvements in Power BI and PowerApps. "We are getting tremendous feedback and energy from our customers and developers. That feedback helps us develop products that are tailored to their needs," said Microsoft corporate vice president James Phillips. "From there we get to see them innovate and thrive. It's been amazing to see us growing across the board, but there is nothing more rewarding than seeing our customers, partners, and developers in action."

One challenge in fact checking is the ability to improve the transparency of the decision. We present a fact checking method that uses reference information in knowledge graphs (KGs) to assess claims and explain its decisions. KGs contain a formal representation of knowledge with semantic descriptions of entities and their relationships. We exploit such rich semantics to produce interpretable explanations for the fact checking output. As information in a KG is inevitably incomplete, we rely on logical rule discovery and on Web text mining to gather the evidence to assess a given claim. Uncertain rules and facts are turned into logical programs and the checking task is modeled as an inference problem in a probabilistic extension of answer set programs. Experiments show that the probabilistic inference enables the efficient labeling of claims with interpretable explanations, and the quality of the results is higher than state of the art baselines.

In 1965, Herbert Simon predicted that "within twenty years, machines would be capable of doing any work a man can do." Five years later, Marvin Minsky forecasted that "in from three to eight years we would have a machine with the general intelligence of an average human being." Bringing up these predictions is not necessarily meant to emphasize that roughly 50 years later they're still a long way from turning real – in spite of the obvious breakthroughs. It's more about acknowledging the fact that the early founders of AI were overly optimistic about the future of AI. This optimism fueled not only the hype, but also their own dismissal of any criticism – particularly coming from philosophers.

Knowledge graph reasoning, which aims at predicting the missing facts through reasoning with the observed facts, is critical to many applications. Such a problem has been widely explored by traditional logic rule-based approaches and recent knowledge graph embedding methods. A principled logic rule-based approach is the Markov Logic Network (MLN), which is able to leverage domain knowledge with first-order logic and meanwhile handle their uncertainty. However, the inference of MLNs is usually very difficult due to the complicated graph structures. Different from MLNs, knowledge graph embedding methods (e.g. TransE, DistMult) learn effective entity and relation embeddings for reasoning, which are much more effective and efficient. However, they are unable to leverage domain knowledge. In this paper, we propose the probabilistic Logic Neural Network (pLogicNet), which combines the advantages of both methods. A pLogicNet defines the joint distribution of all possible triplets by using a Markov logic network with first-order logic, which can be efficiently optimized with the variational EM algorithm. In the E-step, a knowledge graph embedding model is used for inferring the missing triplets, while in the M-step, the weights of logic rules are updated based on both the observed and predicted triplets. Experiments on multiple knowledge graphs prove the effectiveness of pLogicNet over many competitive baselines.