Showing papers in "Artificial Intelligence in 2016"

TL;DR: A novel multilingual vector representation, called Nasari, is put forward, which not only enables accurate representation of word senses in different languages, but it also provides two main advantages over existing approaches: high coverage and comparability across languages and linguistic levels.

TL;DR: In this article, the authors introduce a standardized format for representing algorithm selection scenarios and a repository that contains a growing number of data sets from the literature, and demonstrate the potential of algorithm selection to achieve significant performance improvements across a broad range of problems and algorithms.

TL;DR: Experimental evaluation of the implemented prototypes shows that the CEGAR-driven solver outperforms existing solvers on a number of benchmark families and that the DPLL solver benefits from the additional type of learning.

TL;DR: This paper reports about the fifth edition of the ASP Competition by covering all aspects of the event, ranging from the new design of the competition to an in-depth analysis of the results, including additional analyses that were conceived for measuring the progress of the state of the art, as well as for studying aspects orthogonal to solving technology, such as the effects of modeling.

TL;DR: In this article, the authors focus on one-pass AUC optimization that requires going through training data only once without having to store the entire training dataset and develop a regression-based algorithm which only needs to maintain the first and second-order statistics of training data in memory.

TL;DR: This work introduces a generalized, highly parameterized solver framework, dubbed SATenstein, that includes components drawn from or inspired by existing high-performance SLS algorithms for SAT, and introduces new solvers that significantly outperformed all automatically tuned variants of previous state-of-the-art algorithms.

TL;DR: Domain Approximation for Reinforcement LearnING (DARLING) is presented, a method that takes advantage of planning to constrain the behavior of the agent to reasonable choices, and of reinforcement learning to adapt to the environment, and increase the reliability of the decision making process.

TL;DR: This work presents a multilingual Named Entity Recognition approach based on a robust and general set of features across languages and datasets that combines shallow local information with clustering semi-supervised features induced on large amounts of unlabeled text.

TL;DR: This work identifies and addresses a spectrum of questions pertaining to belief and truth in hypothesised types, and formulate three basic ways to incorporate evidence into posterior beliefs and show when the resulting beliefs are correct, and when they may fail to be correct.

TL;DR: Experimental evaluations show that the proposed two-stage case-base editing technique significantly improves accuracy compared to other case- base editing approaches on concept drift tasks, while preserving its effectiveness on static tasks.

TL;DR: This paper develops two strategyproof matching mechanisms based on the Deferred Acceptance mechanism that satisfy different versions of nonwastefulness respectively and compares them with an artificial cap mechanism via simulation experiments, which illustrate that they have a clear advantage in terms of non-wastedness and student welfare.

TL;DR: A new representation of the search space of the Complete Set Partitioning problem is developed, which reveals that ODP and IP can actually be combined, leading to the development of ODP-IP-a hybrid algorithm that avoids the limitations of its constituent parts, while retaining and significantly improving upon the advantages of each part.

TL;DR: This work employs the instance-specific algorithm configurator ISAC, and improves it with the latest in portfolio technology, and shows that the resulting solvers consistently outperform the best existing solvers on the respective problem families.

TL;DR: In this article, the authors consider partially observable Markov decision processes (POMDPs) with a set of target states and an integer cost associated with every transition and show that the problem of approximating the optimal cost is decidable.

TL;DR: In this paper, the authors consider the problem of picking a set of items that maximize the total derived utility of all the agents (i.e., in our example we are to pick K movies that we put on the plane's entertainment system).

TL;DR: This paper presents a new approach to handling epistemic negation which is free of unintended world views and thus offers a solution to the long-standing problem of epistemic specifications which were introduced by Gelfond 13 over two decades ago.

TL;DR: A probabilistic and decision-theoretic generalisation of the "affect control principle" that allows the model to generate affectively intelligent interactions with people by learning about their identity, predicting their behaviours using the affect control principle, and taking actions that are simultaneously goal-directed and affect-sensitive.

TL;DR: It is shown that the conjunctive model includes linear combination as a special case, and that the more general model can account for non-compositional behaviours such as overextension, non-commutativity, preservation of necessity and impossibility of attributes and to some extent, attribute loss or emergence.

TL;DR: A new human behavior model, SHARP, is provided, which mitigates three limitations of existing models and demonstrates SHARP's superiority by conducting real-world human subjects experiments at the Bukit Barisan Seletan National Park in Indonesia against wildlife security experts.

TL;DR: The scope and limits of the use of simulation, with respect to AI tasks that involve high-level physical reasoning, are addressed, arguing that, in many cases, simulation can play at most a limited role.

TL;DR: A semantics is given that captures parameterised, generic multi-agent systems and three notable classes that represent different ways in which the agents may interact among themselves and with the environment are identified.

TL;DR: In this paper, a set theory-based negative sequential pattern mining (ST-NSP) algorithm is proposed to find missing medical treatments in large-scale datasets without re-scanning the database.

TL;DR: The 2015 SAT Race that featured the traditional sequential and parallel tracks (with 64 core computers) and introduced the Incremental Library Track, which is particularly interesting for developers of SAT based applications is described.

TL;DR: This paper single out classes of canonical models that are amenable for customary bottom-up evaluation of answer set programs, with an option to switch to a paracoherent mode when lack of an answer set is detected.

TL;DR: This work proposes novel notions of arguments and admissible/grounded extensions for Assumption-Based Argumentation, both defined in terms of graphs, and shows that these new derivations are superior with respect to standard dispute derivations in that they are complete in general, rather than solely for restricted classes of ABA frameworks.

TL;DR: This paper presents an axiomatic analysis of the semantics of structured defeasible argumentation both with and without preferences by introducing a class of ordinary attack relations satisfying a set of simple and intuitive properties.

TL;DR: The approach aims at complementing ongoing discussions on rationality postulates for inconsistency measures by considering expressivity as a desirable property and concludes that the distance-based measure I dalal Σ from Grant and Hunter (2013) 8 and the proof-basedMeasure I P m from Jabbour and Raddaoui ( 2013) 16 have maximal expressivity.

TL;DR: Both novel and existing algorithms that compute strategies for the class of two-player zero-sum simultaneous move games are described, including exact backward induction methods with efficient pruning, as well as Monte Carlo sampling algorithms.

TL;DR: In this paper, a comprehensive account of about thirty computer models, from the 1960s to nowadays, and their relationships, focussing on the range of intelligence test tasks they address, the purpose of the models, how general or specialised these models are, the AI techniques they use in each case, their comparison with human performance, and evaluation of item difficulty.

TL;DR: This article extends the standard definition of betweenness centrality using Semivalues-a family of solution concepts from cooperative game theory that includes, among others, the Shapley value and the Banzhaf power index, and proposes a betweennessCentrality based on the Shapleys value and Semivalue.