We introduce the task of identifying information-dense texts,which report important factual information in direct, succinct manner. We describe a procedure that allows us to label automatically a large training corpus of New York Times texts.We train a classifier based on lexical, discourse and unlexicalized syntactic features and test its performance on a set of manually annotated articles from business, U.S. international relations, sports and science domains. Our results indicate that the task is feasible and that both syntactic and lexicalfeatures are highly predictive for the distinction. We observe considerable variation of prediction accuracy across domains and find that domain-specific models are more accurate.

As the rapid growth of online social media attracts a large number of Internet users, the large volume of content generated by these users also provides us with an opportunity to study the lexical variation of people of different ages. In this paper, we present a latent variable model that jointly models the lexical content of tweets and Twitter users’ ages. Our model inherently assumes that a topic has not only a word distribution but also an age distribution. We propose a Gibbs-EM algorithm to perform inference on our model. Empirical evaluation shows that our model can learn meaningful age-specific topics such as “school” for teenagers and “health” for older people. Our model can also be used for age prediction and performs better than a number of baseline methods.

In this paper, we systematically study the problem of dataless hierarchical text classification. Unlike standard text classification schemes that rely on supervised training, dataless classification depends on understanding the labels of the sought after categories and requires no labeled data. Given a collection of text documents and a set of labels, we show that understanding the labels can be used to accurately categorize the documents. This is done by embedding both labels and documents in a semantic space that allows one to compute meaningful semantic similarity between a document and a potential label. We show that this scheme can be used to support accurate multiclass classification without any supervision. We study several semantic representations and show how to improve the classification using bootstrapping. Our results show that bootstrapped dataless classification is competitive with supervised classification with thousands of labeled examples.

Distributed representations of words (aka word embedding) have proven helpful in solving natural language processing (NLP) tasks. Training distributed representations of words with neural networks has lately been a major focus of researchers in the field. Recent work on word embedding, the Continuous Bag-of-Words (CBOW) model and the Continuous Skip-gram (Skip-gram) model, have produced particularly impressive results, significantly speeding up the training process to enable word representation learning from large-scale data. However, both CBOW and Skip-gram do not pay enough attention to word proximity in terms of model or word ambiguity in terms of linguistics. In this paper, we propose Proximity-Ambiguity Sensitive (PAS) models (i.e. PAS CBOW and PAS Skip-gram) to produce high quality distributed representations of words considering both word proximity and ambiguity. From the model perspective, we introduce proximity weights as parameters to be learned in PAS CBOW and used in PAS Skip-gram. By better modeling word proximity, we reveal the strength of pooling-structured neural networks in word representation learning. The proximity-sensitive pooling layer can also be applied to other neural network applications that employ pooling layers. From the linguistics perspective, we train multiple representation vectors per word. Each representation vector corresponds to a particular group of POS tags of the word. By using PAS models, we achieved a 16.9% increase in accuracy over state-of-the-art models.

Image similarity search plays a key role in many multimediaapplications, where multimedia data (such as images and videos) areusually represented in high-dimensional feature space. In thispaper, we propose a novel Sparse Online Metric Learning (SOML)scheme for learning sparse distance functions from large-scalehigh-dimensional data and explore its application to imageretrieval. In contrast to many existing distance metric learningalgorithms that are often designed for low-dimensional data, theproposed algorithms are able to learn sparse distance metrics fromhigh-dimensional data in an efficient and scalable manner. Ourexperimental results show that the proposed method achieves betteror at least comparable accuracy performance than thestate-of-the-art non-sparse distance metric learning approaches, butenjoys a significant advantage in computational efficiency andsparsity, making it more practical for real-world applications.

An important requirement of household energy simulation models is their accuracy in estimating energy demand and its fluctuations. Occupant behavior has a major impact upon energy demand. However, Markov chains, the traditional approach to model occupant behavior, (1) has limitations in accurately capturing the coordinated behavior of occupants and (2) is prone to over-fitting. To address these issues, we propose a novel approach that relies on a combination of data mining techniques. The core idea of our model is to determine the behavior of occupants based on nearest neighbor comparison over a database of sample data. Importantly, the model takes into account features related to the coordination of occupants' activities. We use a customized distance function suited for mixed categorical and numerical data. Further, association rule learning allows us to capture the coordination between occupants. Using real data from four households in Japan we are able to show that our model outperforms the traditional Markov chain model with respect to occupant coordination and generalization of behavior patterns.

This paper focuses on computing general first-order parallel and prioritized circumscription with varying constants. We propose linear translations from general first-order circumscription to first-order theories under stable model semantics over arbitrary structures, including Tr_v for parallel circumscription and Tr^s_v for conjunction of parallel circumscriptions (further for prioritized circumscription). To improve the efficiency, we give an optimization \Gamma_{\exists} to reduce logic programs in size when eliminating existential quantifiers during the translations. Based on these results, a general first-order circumscription solver, named cfo2lp, is developed by calling answer set programming (ASP) solvers. Using circuit diagnosis problem and extended stable marriage problem as benchmarks, we compare cfo2lp with a propositional circumscription solver circ2dlp and an ASP solver with complex optimization metasp on efficiency. Experimental results demonstrate that for problems represented by first-order circumscription naturally and intuitively, cfo2lp can compute all solutions over finite structures. We also apply our approach to description logics with circumscription and repairs in inconsistent databases, which can be handled effectively.

Ontology-based data access (OBDA) is a new paradigm aiming at accessing and managing data by means of an ontology, i.e., a conceptual representation of the domain of interest in the underlying information system. In the last years, this new paradigm has been used for providing users with abstract (independent from technological and system-oriented aspects), effective, and reasoning-intensive mechanisms for querying the data residing at the information system sources. In this paper we argue that OBDA, besides querying data, provides the right principles for devising a formal approach to data quality. In particular, we concentrate on one of the most important dimensions considered both in the literature and in the practice of data quality, namely consistency. We define a general framework for data consistency in OBDA, and present algorithms and complexity analysis for several relevant tasks related to the problem of checking data quality under this dimension, both at the extensional level (content of the data sources), and at the intensional level (schema of the data sources).

The area of cognitive robotics is often subject to the criticism that the proposals investigated in the literature are too far removed from the kind of continuous uncertainty and noise seen in actual real-world robotics. This paper proposes a new language and an implemented system, called PREGO, based on the situation calculus, that is able to reason effectively about degrees of belief against noisy sensors and effectors in continuous domains. It embodies the representational richness of conventional logic-based action languages, such as context-sensitive successor state axioms, but is still shown to be efficient using a number of empirical evaluations. We believe that PREGO is a powerful framework for exploring real-time reactivity and an interesting bridge between logic and probability for cognitive robotics applications.

In this paper we consider the setting of graph-structured data that evolves as a result of operations carried out by users or applications. We study different reasoning problems, which range from ensuring the satisfaction of a given set of integrity constraints after a given sequence of updates, to deciding the (non-)existence of a sequence of actions that would take the data to an (un)desirable state, starting either from a specific data instance or from an incomplete description of it. We consider a simple action language in which actions are finite sequences of insertions and deletions of nodes and labels, and use Description Logics for describing integrity constraints and (partial) states of the data. We then formalize the data management problems mentioned above as a static verification problem and several planning problems. We provide algorithms and tight complexity bounds for the formalized problems, both for an expressive DL and for a variant of DL-Lite.