Winter news from the Association for Advancement of Artificial Intelligence. Includes the Independent Auditor's Report.

This article is devoted to the study of methods to change defeasible logic programs (de.l.p.s) which are the knowledge bases used by the Defeasible Logic Programming (DeLP) interpreter. DeLP is an argumentation formalism that allows to reason over potentially inconsistent de.l.p.s. Argument Theory Change (ATC) studies certain aspects of belief revision in order to make them suitable for abstract argumentation systems. In this article, abstract arguments are rendered concrete by using the particular rule-based defeasible logic adopted by DeLP. The objective of our proposal is to define prioritized argument revision operators \`a la ATC for de.l.p.s, in such a way that the newly inserted argument ends up undefeated after the revision, thus warranting its conclusion. In order to ensure this warrant, the de.l.p. has to be changed in concordance with a minimal change principle. To this end, we discuss different minimal change criteria that could be adopted. Finally, an algorithm is presented, implementing the argument revision operations.

In this paper we analyze judgement aggregation problems in which a group of agents independently votes on a set of complex propositions that has some interdependency constraint between them(e.g., transitivity when describing preferences). We consider the issue of judgement aggregation from the perspective of approximation. That is, we generalize the previous results by studying approximate judgement aggregation. We relax the main two constraints assumed in the current literature, Consistency and Independence and consider mechanisms that only approximately satisfy these constraints, that is, satisfy them up to a small portion of the inputs. The main question we raise is whether the relaxation of these notions significantly alters the class of satisfying aggregation mechanisms. The recent works for preference aggregation of Kalai, Mossel, and Keller fit into this framework. The main result of this paper is that, as in the case of preference aggregation, in the case of a subclass of a natural class of aggregation problems termed `truth-functional agendas', the set of satisfying aggregation mechanisms does not extend non-trivially when relaxing the constraints. Our proof techniques involve Boolean Fourier transform and analysis of voter influences for voting protocols. The question we raise for Approximate Aggregation can be stated in terms of Property Testing. For instance, as a corollary from our result we get a generalization of the classic result for property testing of linearity of Boolean functions. An updated version (RePEc:huj:dispap:dp574R) is available at http://www.ratio.huji.ac.il/dp_files/dp574R.pdf

Machine learning approaches to multi-label document classification have to date largely relied on discriminative modeling techniques such as support vector machines. A drawback of these approaches is that performance rapidly drops off as the total number of labels and the number of labels per document increase. This problem is amplified when the label frequencies exhibit the type of highly skewed distributions that are often observed in real-world datasets. In this paper we investigate a class of generative statistical topic models for multi-label documents that associate individual word tokens with different labels. We investigate the advantages of this approach relative to discriminative models, particularly with respect to classification problems involving large numbers of relatively rare labels. We compare the performance of generative and discriminative approaches on document labeling tasks ranging from datasets with several thousand labels to datasets with tens of labels. The experimental results indicate that probabilistic generative models can achieve competitive multi-label classification performance compared to discriminative methods, and have advantages for datasets with many labels and skewed label frequencies.

The ViewGen model of belief ascription assumes that each agent involved in a conversation has a belief space which includes models of what other parties to the conversation believe. The distinctive notion is that a basic procedure, called belief ascription, allows belief spaces to be amalgamated so as to model the updating and augmentation of belief environments. In this paper we extend the ViewGen model to a more general account of reference phenomena, in particular by the notion of a reachable ascription set (RAS) that links intensional objects across belief environments so as to locate the most heuristically plausible referent at a given point in a conversation. The key notion is the location and attachment of entities that may be under different descriptions, the consequent updating of the system's beliefs about other agents by default, and the role in that process of a speaker's and hearer's protocols that ensure that the choice is the appropriate one. An important characteristic of this model is that each communicator considers nothing beyond his own belief space. A conclusion we shall draw is that traditional binary distinctions in this area (like de dicto/de re and attributive/referential) neither classify the examples effectively nor do they assist in locating referents, whereas the single procedure we suggest does both. We also suggest ways in which this analysis can also illuminate other traditional distinctions such as referential and attributive use. The description here is not on an implemented system with results but a theoretical tool to be implemented within an established dialogue platform (such as Wilks et al. 2011).

This paper investigates spatiotemporal interpolation methods for the application of air pollution assessment. The air pollutant of interest in this paper is fine particulate matter PM2.5. The choice of the time scale is investigated when applying the shape function-based method. It is found that the measurement scale of the time dimension has an impact on the interpolation results. Based upon the comparison between the accuracies of interpolation results, the most effective time scale out of four experimental ones was selected for performing the PM2.5 interpolation. The paper also evaluates the population exposure to the ambient air pollution of PM2.5 at the county-level in the contiguous U.S. in 2009. The interpolated county-level PM2.5 has been linked to 2009 population data and the population with a risky PM2.5 exposure has been estimated. The risky PM2.5 exposure means the PM2.5 concentration exceeding the National Ambient Air Quality Standards. The geographic distribution of the counties with a risky PM2.5 exposure is visualized. This work is essential to understanding the associations between ambient air pollution exposure and population health outcomes.

Organizations play a pivotal role in the dynamics of social, economic, and ecological systems. Current organizational life-cycle models do not adequately consider the impact of propensities (deeply ingrained preferences and patterns of behavior) on organizational culture and evolution. On a global basis, the predominant thinking modes in organizations are driven by senior executives, marketers, financial experts, legal resources, and the engineers and scientists that create our technology-rich world. Each of these groups has, in aggregate, embedded propensities or tendencies that profoundly shape decision-making patterns and overall social dynamics. Dominant propensities can make organizations vulnerable to risks by inhibiting the level of systems thinking and networking necessary to ensure integration within a global socio-ecological context. The spectrum of propensities within an organization shapes the relative resilience of its human and management systems, and ultimately determines organizational effectiveness. This paper proposes a model for organizational evolution that links the role of propensities to adaptability and resilience. Conscious effort to expand the intelligence of organizations through diversification of propensities better equips organizations to achieve adaptability and sustainability.

Annotated corpora have stimulated great advances in the language sciences. The time is ripe to bring that same stimulation, and consequent benefits, to computational approaches to narrative. I describe an effort to construct a corpus of semantically annotated stories. I outline the structure of the corpus, a structure which colloquially can be described as a "handful of handfuls." One handful of the corpus has already been constructed, viz., 18k words of Russian folktales. There are two handfuls under construction: legal cases focused on the area of probable cause, and stories from Islamist Extremist Jihadists. Four more handfuls are being planned: folktales from Chinese, English, and a West Asian culture, and stories of international conventional and cyber conflicts. There are numerous additional handfuls under discussion. The main focus of the corpus so far has been on textual materials that are annotated for their surface semantics using conventional annotation tools and techniques; nonetheless, there are numerous novel dimensions along which the corpus might grow and become useful for different communities. In particular I propose for discussion the outlines of a few novel sources, annotation schemes, and collection methodologies that could potentially make the corpus of great use to the interactive narrative or narrative generation communities.

In this paper we propose a data intensive approach for inferring sentence-internal temporal relations. Temporal inference is relevant for practical NLP applications which either extract or synthesize temporal information (e.g., summarisation, question answering). Our method bypasses the need for manual coding by exploiting the presence of markers like after", which overtly signal a temporal relation. We first show that models trained on main and subordinate clauses connected with a temporal marker achieve good performance on a pseudo-disambiguation task simulating temporal inference (during testing the temporal marker is treated as unseen and the models must select the right marker from a set of possible candidates). Secondly, we assess whether the proposed approach holds promise for the semi-automatic creation of temporal annotations. Specifically, we use a model trained on noisy and approximate data (i.e., main and subordinate clauses) to predict intra-sentential relations present in TimeBank, a corpus annotated rich temporal information. Our experiments compare and contrast several probabilistic models differing in their feature space, linguistic assumptions and data requirements. We evaluate performance against gold standard corpora and also against human subjects.

We study an approach to policy selection for large relational Markov Decision Processes (MDPs). We consider a variant of approximate policy iteration (API) that replaces the usual value-function learning step with a learning step in policy space. This is advantageous in domains where good policies are easier to represent and learn than the corresponding value functions, which is often the case for the relational MDPs we are interested in. In order to apply API to such problems, we introduce a relational policy language and corresponding learner. In addition, we introduce a new bootstrapping routine for goal-based planning domains, based on random walks. Such bootstrapping is necessary for many large relational MDPs, where reward is extremely sparse, as API is ineffective in such domains when initialized with an uninformed policy. Our experiments show that the resulting system is able to find good policies for a number of classical planning domains and their stochastic variants by solving them as extremely large relational MDPs. The experiments also point to some limitations of our approach, suggesting future work.