We seek to better understand the difference in quality of the several publicly released embeddings. We propose several tasks that help to distinguish the characteristics of different embeddings. Our evaluation of sentiment polarity and synonym/antonym relations shows that embeddings are able to capture surprisingly nuanced semantics even in the absence of sentence structure. Moreover, benchmarking the embeddings shows great variance in quality and characteristics of the semantics captured by the tested embeddings. Finally, we show the impact of varying the number of dimensions and the resolution of each dimension on the effective useful features captured by the embedding space. Our contributions highlight the importance of embeddings for NLP tasks and the effect of their quality on the final results.

The availability of massive amounts of raw domain data has created an urgent need for sophisticated AI systems with capabilities to find complex and useful information in big-data repositories in real-time. Such systems should have capabilities to process and extract significant information from natural language documents, search and answer complex questions, make sophisticated predictions about future events, and generally interact with users in much more powerful and intuitive ways. To be effective, these systems need a significant amount of domain-specific knowledge in addition to the general-domain knowledge. Ontologies/Knowledge-Bases represent knowledge about domains of interest and serve as the backbone for semantic technologies and applications. However, creating such domain models is time consuming, error prone, and the end product is difficult to maintain. In this paper, we present a novel methodology to automatically build semantically rich knowledge models for specific domains using domain-relevant unstructured data from resources such as web articles, manuals, e-books, blogs, etc. We also present evaluation results for our automatic ontology/knowledge-base generation methodology using freely-available textual resources from the World Wide Web.

This paper addresses Trace-Based Reasoning (TBR) by using Case-Based Reasoning (CBR) as a descriptive framework. TBR is a reasoning paradigm in which inferences are made on specific objects called traces. Traces are sequential records of events observed and stored during an interactive process. We report two contributions. First, we propose a review of the current researches related to TBR. Then, we compare CBR and TBR. From this comparison, we show that the exploitation of traces instead of cases as knowledge sources raises very specific challenges. More precisely, new methods for defining similarity measures and for performing adaptation of traces are required. These new methods have to take into account the sequential properties of traces. We emphasis the benefits of using traces as a knowledge container in a reasoning process and we pinpoint promising applications of TBR.

The difference between typical instances and atypical instances in a natural categorization process has been introduced by E. Rosh and studied by cognitive psychology and AI. A lot of the knowledge representation systems are expressed in using fuzzy concepts but a degree of membership raises some problem for natural categorizations (especially to classification problems in anthropology, ethnology, archeology, linguistics but also in ontologies), but atypical instances of a concept cannot be apprehended adequately by different degrees from a prototype. Other formal approaches, as paraconsistent logics or non monotonic logics, conceptualize often atypical objects as exceptions. It had yet been developed an alternative way with the logics of determination of the objects (LDO). In this paper, we present the logics of typical and atypical (LTA) in order to give directly a logical approach of typicality / atypicality associated to a concept by a more common way than in LDO, in using only classes and not determination operators. It is introduced a distinction between predicative property and concept defined with its intension and its essence, a part of intension. A typical instance of a concept inherits all properties of intension; a typical instance inherits only properties of essence but it is a full member of the category associated to a concept and not a member with a weak degree of membership. In natural categorization, there are often instances (the exceptions) which do not inherit some properties of the essence; they cannot be considered as atypical instance and belong to the boundary of the category.

In two recent papers, I have proposed a description of decision analysis that differs from the Bayesian picture painted by Savage, Jeffrey and other classic authors. Response to this view has been either overly enthusiastic or unduly pessimistic. In this paper I try to place the idea in its proper place, which must be somewhere in between. Looking at decision analysis as defeasible reasoning produces a framework in which planning and decision theory can be integrated, but work on the details has barely begun. It also produces a framework in which the meta-decision regress can be stopped in a reasonable way, but it does not allow us to ignore meta-level decisions. The heuristics for producing arguments that I have presented are only supposed to be suggestive; but they are not open to the egregious errors about which some have worried. And though the idea is familiar to those who have studied heuristic search, it is somewhat richer because the control of dialectic is more interesting than the deepening of search.

We introduce and analyze the problem of the compilation of decision models from a decision-theoretic perspective. The techniques described allow us to evaluate various configurations of compiled knowledge given the nature of evidential relationships in a domain, the utilities associated with alternative actions, the costs of run-time delays, and the costs of memory. We describe procedures for selecting a subset of the total observations available to be incorporated into a compiled situation-action mapping, in the context of a binary decision with conditional independence of evidence. The methods allow us to incrementally select the best pieces of evidence to add to the set of compiled knowledge in an engineering setting. After presenting several approaches to compilation, we exercise one of the methods to provide insight into the relationship between the distribution over weights of evidence and the preferred degree of compilation.

BPS, the Bayesian Problem Solver, applies probabilistic inference and decision-theoretic control to flexible, resource-constrained problem-solving. This paper focuses on the Bayesian inference mechanism in BPS, and contrasts it with those of traditional heuristic search techniques. By performing sound inference, BPS can outperform traditional techniques with significantly less computational effort. Empirical tests on the Eight Puzzle show that after only a few hundred node expansions, BPS makes better decisions than does the best existing algorithm after several million node expansions

We consider the relation between knowledge and certainty, where a fact is known if it is true at all worlds an agent considers possible and is certain if it holds with probability 1. We identify certainty with probabilistic belief. We show that if we assume one fixed probability assignment, then the logic KD45, which has been identified as perhaps the most appropriate for belief, provides a complete axiomatization for reasoning about certainty. Just as an agent may believe a fact although phi is false, he may be certain that a fact phi, is true although phi is false. However, it is easy to see that an agent can have such false (probabilistic) beliefs only at a set of worlds of probability 0. If we restrict attention to structures where all worlds have positive probability, then S5 provides a complete axiomatization. If we consider a more general setting, where there might be a different probability assignment at each world, then by placing appropriate conditions on the support of the probability function (the set of worlds which have non-zero probability), we can capture many other well-known modal logics, such as T and S4. Finally, we consider which axioms characterize structures satisfying Miller's principle.

Unaided human decision making appears to systematically violate consistency constraints imposed by normative theories; these biases in turn appear to justify the application of formal decision-analytic models. It is argued that both claims are wrong. In particular, we will argue that the "confirmation bias" is premised on an overly narrow view of how conflicting evidence is and ought to be handled. Effective decision aiding should focus on supporting the contral processes by means of which knowledge is extended into novel situations and in which assumptions are adopted, utilized, and revised. The Non- Monotonic Probabilist represents initial work toward such an aid.

Rather than discussing the isolated merits of a nominative theory of uncertainty, this paper focuses on a class of problems, referred to as Dynamic Classification Problem (DCP), which requires the integration of many theories, including a prescriptive theory of uncertainty. We start by analyzing the Dynamic Classification Problem and by defining its induced requirements on a supporting (plausible) reasoning system. We provide a summary of the underlying theory (based on the semantics of many-valed logics) and illustrate the constraints imposed upon it to ensure the modularity and computational performance required by the applications. We describe the technologies used for knowledge engineering (such as object-based simulator to exercise requirements, and development tools to build the Knowledge Base and functionally validate it). We emphasize the difference between development environment and run-time system, describe the rule cross-compiler, and the real-time inference engine with meta-reasoning capabilities. Finally, we illustrate how our proposed technology satisfies the pop's requirements and analyze some of the lessons reamed from its applications to situation assessment problems for Pilot's Associate and Submarine Commander Associate.