The increasing volume of information generated on micro-blogging sites such as Twitter raises several challenges to traditional text mining techniques. First, most texts from those sites are abbreviated due to the constraints of limited characters in one post; second, the input usually comes in streams of large-volumes. Therefore, it is of significant importance to develop effective and efficient representations of abbreviated texts for better filtering and mining. In this paper, we introduce a novel transfer learning approach, namely transfer latent semantic learning, that utilizes a large number of related tagged documents with rich information from other sources (source domain) to help build a robust latent semantic space for the abbreviated texts (target domain). This is achieved by simultaneously minimizing the document reconstruction error and the classification error of the labeled examples from the source domain by building a classifier with hinge loss in the latent semantic space. We demonstrate the effectiveness of our method by applying them to the task of classifying and tagging abbreviated texts. Experimental results on both synthetic datasets and real application datasets, including Reuters-21578 and Twitter data, suggest substantial improvements using our approach over existing ones.

From an automated planning perspective the problem of practical mobile robot control in realistic environments poses many important and contrary challenges. On the one hand, the planning process must be lightweight, robust, and timely. Over the lifetime of the robot it must always respond quickly with new plans that accommodate exogenous events, changing objectives, and the underlying unpredictability of the environment. On the other hand, in order to promote efficient behaviours the planning process must perform computationally expensive reasoning about contingencies and possible revisions of subjective beliefs according to quantitatively modelled uncertainty in acting and sensing. Towards addressing these challenges, we develop a continual planning approach that switches between using a fast satisficing "classical" planner, to decide on the overall strategy, and decision-theoretic planning to solve small abstract subproblems where deeper consideration of the sensing model is both practical, and can significantly impact overall performance. We evaluate our approach in large problems from a realistic robot exploration domain.

It has been argued that causal rules are necessary for representing both implicit side-effects of actions and action qualifications, and there have been a number different approaches for representing causal rules in the area of formal theoriesof actions. These different approaches in general agree on rules without cycles. However, they differ on causal rules with mutual cyclic dependencies, both in terms of how these rules are supposed to be represented and their semantics. In this paper we show that by adding one more minimization to Lin's circumscriptive causal theory in the situation calculus, we can have a uniform representation of causal rules including those with cyclic dependencies. We also demonstrate that sometimes causal rules can be compiled into logically equivalent successor state axioms even in the presence of cyclical dependencies between fluents.

Anytime variants of Dijkstra's and A* shortest path algorithms quickly produce a suboptimal solution and then improve it over time. For example, ARA* introduces a weighting value "epsilon" to rapidly find an initial suboptimal path and then reduces "epsilon" to improve path quality over time. In ARA*, "epsilon" is based on a linear trajectory with ad-hoc parameters chosen by each user. We propose a new Anytime A* algorithm, Anytime Nonparametric A* (ANA*), that does not require ad-hoc parameters, and adaptively reduces varepsilon to expand the most promising node per iteration, adapting the greediness of the search as path quality improves. We prove that each node expanded by ANA* provides an upper bound on the suboptimality of the current-best solution. We evaluate the performance of ANA* with experiments in the domains of robot motion planning, gridworld planning, and multiple sequence alignment. The results suggest that ANA* is as efficient as ARA* and in most cases: (1) ANA* finds an initial solution faster, (2) ANA* spends less time between solution improvements, (3) ANA* decreases the suboptimality bound of the current-best solution more gradually, and (4) ANA* finds the optimal solution faster. ANA* is freely available from Maxim Likhachev's Search-based Planning Library (SBPL).

Peer reviewing is the key ingredient of evaluating the quality of scientific work. Based on the review scores assigned by the individual reviewers to the submissions, program committees of conferences and journal editors decide which papers to accept for publication and which to reject. However, some reviewers may be more rigorous than others, they may be biased one way or the other, and they often have highly subjective preferences over the papers they review. Moreover, each reviewer usually has only a very local view, as he or she evaluates only a small fraction of the submissions. Despite all these shortcomings, the review scores obtained need to be aggregrated in order to globally rank all submissions and to make the acceptance/rejection decision. A common method is to simply take the average of each submission's review scores, possibly weighted by the reviewers' confidence levels. Unfortunately, the global ranking thus produced often suffers a certain unfairness, as the reviewers' biases and limitations are not taken into account. We propose a method for calibrating the scores of reviewers that are potentially biased and blindfolded by having only partial information. Our method uses a maximum likelihood estimator, which estimates both the bias of each individual reviewer and the unknown "ideal" score of each submission. This yields a quadratic program whose solution transforms the individual review scores into calibrated, globally comparable scores. We argue why our method results in a fairer and more reasonable global ranking than simply taking the average of scores. To show its usefulness, we test our method empirically using real-world data.

This paper describes a new model for understanding natural language commands given to autonomous systems that perform navigation and mobile manipulation in semi-structured environments. Previous approaches have used models with fixed structure to infer the likelihood of a sequence of actions given the environment and the command. In contrast, our framework, called Generalized Grounding Graphs, dynamically instantiates a probabilistic graphical model for a particular natural language command according to the command's hierarchical and compositional semantic structure. Our system performs inference in the model to successfully find and execute plans corresponding to natural language commands such as "Put the tire pallet on the truck." The model is trained using a corpus of commands collected using crowdsourcing. We pair each command with robot actions and use the corpus to learn the parameters of the model. We evaluate the robot's performance by inferring plans from natural language commands, executing each plan in a realistic robot simulator, and asking users to evaluate the system's performance. We demonstrate that our system can successfully follow many natural language commands from the corpus.

Strategy mining is a new area of research about discovering strategies in decision-making. In this paper, we formulate the strategy-mining problem as a clustering problem, called the latent-strategy problem. In a latent-strategy problem, a corpus of data instances is given, each of which is represented by a set of features and a decision label. The inherent dependency of the decision label on the features is governed by a latent strategy. The objective is to find clusters, each of which contains data instances governed by the same strategy. Existing clustering algorithms are inappropriate to cluster dependency because they either assume feature independency (e.g., K-means) or only consider the co-occurrence of features without explicitly modeling the special dependency of the decision label on other features (e.g., Latent Dirichlet Allocation (LDA)). In this paper, we present a baseline unsupervised learning algorithm for dependency clustering. Our model-based clustering algorithm iterates between an assignment step and a minimization step to learn a mixture of decision tree models that represent latent strategies. Similar to the Expectation Maximization algorithm, our algorithm is grounded in the statistical learning theory. Different from other clustering algorithms, our algorithm is irrelevant-feature resistant and its learned clusters (modeled by decision trees) are strongly interpretable and predictive. We systematically evaluate our algorithm using a common law dataset comprised of actual cases. Experimental results show that our algorithm significantly outperforms K-means and LDA on clustering dependency.

Approval-like voting rules, such as Sincere-Strategy Preference-Based Approval voting (SP-AV), the Bucklin rule (an adaptive variant of k-Approval voting), and the Fallback rule (an adaptive variant of SP-AV) have many desirable properties: for example, they are easy to understand and encourage the candidates to choose electoral platforms that have a broad appeal. In this paper, we investigate both classic and parameterized computational complexity of electoral campaign management under such rules. We focus on two methods that can be used to promote a given candidate: asking voters to move this candidate upwards in their preference order or asking them to change the number of candidates they approve of. We show that finding an optimal campaign management strategy of the first type is easy for both Bucklin and Fallback. In contrast, the second method is computationally hard even if the degree to which we need to affect the votes is small. Nevertheless, we identify a large class of scenarios that admit a fixed-parameter tractable algorithm.

The number of elderly people is constantly increasing in the developed countries. Elderly tend to lead an isolated life away from their offspring; however, they may fear being unable to obtain help if they are injured or ill. During the last decades, this fear has generated research attempts to find assistive technologies for making living of elderly people at homes easier and independent, as is the aim of this research work. Research study proposes a generalized approach to an intelligent and ubiquitous care system to recognize a few of the most common and important health problems of the elderly, which can be detected by analyzing their movement. In the event that the system was to recognize a health problem, it would automatically notify a physician with an included explanation of the automatic diagnosis. It is two-step approach; in the first step it classifies person's activities into five activities: fall, unconscious fall, walking, standing/sitting, lying down/lying. In the second step, it classifies walking patterns into five different health states; one healthy and four unhealthy: hemiplegia (usually the result of stroke), Parkinson’s disease, leg pain and back pain. Moreover, since elderly having these health problems are less stable and more prone to falls, recognizing them leads not only to detection but indirectly also to prevention of falls of elderly people. In the initial approach movement of the user is captured with the motion capture system, which consists of the tags attached to the body, whose coordinates are acquired by the sensors situated in the apartment. In the current approach wearable inertial sensors are used, allowing monitoring inside or outside of the buildings. Output time-series of coordinates are modeled with the proposed data mining approach to recognize the specific health problem.

We propose a novel technique for proving the consistency of large, complex and heterogeneous theories for which ‘standard’ automated reasoning methods are considered insufficient. In particular, we exemplify the applicability of the method by establishing the consistency of the foundational ontology DOLCE, a large, first-order ontology. The approach we advocate constructs a global model for a theory, in our case DOLCE, built from smaller models of subtheories together with amalgamability properties between such models. The proof proceeds by (i) hand-crafting a so-called architectural specification of DOLCE which reflects the way models of the theory can be built, (ii) an automated verification of the amalgamability conditions, and (iii) a (partially automated) series of relative consistency proofs.