Mobile applications can be greatly enhanced if they have information about the situation of the user. Situations may be inferred by analyzing several types of contextual information drawn from device sensors, such as location, motion, ambiance and proximity. To capture a richer understanding of users’ situations, we introduce an ontology describing the relations between background knowledge about the user and contexts inferred from sensor data. With the right combination of machine learning and semantic modeling, it is possible to create high-level interpretations of user behaviors and situations. However, the potential of understanding and interpreting behavior with such detailed granularity poses significant threats to personal privacy. We propose a framework to mitigate privacy risks by filtering sensitive data in a context-aware way, and maintain provenance of inferred situations as well as relations between existing contexts when sharing information with other parties.

Poor quality data is a growing and costly problem that affects many enterprises across all aspects of their business ranging from operational efficiency to revenue protection. In this paper, we present an application -- Data Quality Rules Accelerator (DQRA) -- that accelerates Data Quality (DQ) efforts (e.g. data profiling and cleansing) by automatically discovering DQ rules for detecting inconsistencies in data. We then present two evaluations. The first evaluation compares DQRA to existing solutions; and shows that DQRA either outperformed or achieved performance comparable with these solutions on metrics such as precision, recall, and runtime. The second evaluation is a case study where DQRA was piloted at a large utilities company to improve data quality as part of a legacy migration effort. DQRA was able to discover rules that detected data inconsistencies directly impacting revenue and operational efficiency. Moreover, DQRA was able to significantly reduce the amount of effort required to develop these rules compared to the state of the practice. Finally, we describe ongoing efforts to deploy DQRA.

In this paper, we propose a bottom-up approach to generating short descriptive sentences from images, to enhance scene understanding. We demonstrate automatic methods for mapping the visual content in an image to natural spoken or written language. We also introduce a human-in-the-loop evaluation strategy that quantitatively captures the meaningfulness of the generated sentences. We recorded a correctness rate of 60.34% when human users were asked to judge the meaningfulness of the sentences generated from relatively challenging images. Also, our automatic methods compared well with the state-of-the-art techniques for the related computer vision tasks.

The Game Description Language is a high-level, rule-based formalisms for communicating the rules of arbitrary  games to general game-playing systems, whose challenging task is to learn to play previously unknown games without human intervention. Originally designed for deterministic games with complete information about the game state, the language was recently extended to include randomness and imperfect information. However, determining the extent to which this enhancement allows to describe truly arbitrary games was left as an open problem. We provide a positive answer to this question by relating the extended Game Description Language to the universal, mathematical concept of extensive-form games, proving that indeed just any such game can be described faithfully.

Existential rules, i.e. Datalog extended with existential quantifiers in rule heads, are currently studied under a variety of names such as Datalog +/-, ∀∃-rules, and tuple-generating dependencies. The renewed interest in this formalism is fuelled by a wealth of recently discovered language fragments for which query answering is decidable. This paper extends and consolidates two of the main approaches in this field — acyclicity and guardedness — by providing (1) complexity-preserving generalisations of weakly acyclic and weakly (frontier-)guarded rules, and (2) a novel formalism of glut-(frontier-)guarded rules that subsumes both. This builds on an insight that acyclicity can be used to extend any existential rule language while retaining decidability. Besides decidability, combined query complexities are established in all cases.

In this paper, to support more precise Chinese Out-of-Vocabulary (OOV) term detection and Part-of-Speech (POS) guessing, a unified mechanism is proposed and formulated based on the fusion of multiple features and supervised learning. Besides all the traditional features, the new features for statistical information and global contexts are introduced, as well as some constraints and heuristic rules, which reveal the relationships among OOV term candidates. Our experiments on the Chinese corpora from both People’s Daily and SIGHAN 2005 have achieved the consistent results, which are better than those acquired by pure rule-based or statistics-based models. From the experimental results for combining our model with Chinese monolingual retrieval on the data sets of TREC-9, it is found that the obvious improvement for the retrieval performance can also be obtained.

We establish complexities of the conjunctive query entailment problem for classes of existential rules (i.e. Tuple-Generating Dependencies or Datalog+/- rules). Our contribution is twofold. First, we introduce the class of greedy bounded treewidth sets (gbts), which covers guarded rules, and their known generalizations, namely (weakly) frontier-guarded rules. We provide a generic algorithm for query entailment with gbts, which is worst-case optimal for combined complexity with bounded predicate arity, as well as for data complexity. Second, we classify several gbts classes, whose complexity was unknown, namely frontier-one, frontier-guarded and weakly frontier-guarded rules, with respect to combined complexity (with bounded and unbounded predicate arity) and data complexity.

In this paper, we propose a novel approach for learning regression rules by transforming the regression problem into a classification problem. Unlike previous approaches to regression by classification, in our approach the discretization of the class variable is tightly integrated into the rule learning algorithm. The key idea is to dynamically define a region around the target value predicted by the rule, and considering all examples within that region as positive and all examples outside that region as negative. In this way, conventional rule learning heuristics may be used for inducing regression rules. Our results show that our heuristic algorithm outperforms approaches that use a static discretization of the target variable, and performs en par with other comparable rule-based approaches, albeit without reaching the performance of statistical approaches.

In this paper we present a graph-based approach aimed at learning a lexical taxonomy automatically starting from a domain corpus and the Web. Unlike many taxonomy learning approaches in the literature, our novel algorithm learns both concepts and relations entirely from scratch via the automated extraction of terms, definitions and hypernyms. This results in a very dense, cyclic and possibly disconnected hypernym graph. The algorithm then induces a taxonomy from the graph. Our experiments show that we obtain high-quality results, both when building brand-new taxonomies and when reconstructing WordNet sub-hierarchies.

Entity linking maps name mentions in the documents to entries in a knowledge base through resolving the name variations and ambiguities. In this paper, we propose three advancements for entity linking. Firstly, expanding acronyms can effectively reduce the ambiguity of the acronym mentions. However, only rule-based approaches relying heavily on the presence of text markers have been used for entity linking. In this paper, we propose a supervised learning algorithm to expand more complicated acronyms encountered, which leads to 15.1% accuracy improvement over state-of-the-art acronym expansion methods. Secondly, as entity linking annotation is expensive and labor intensive, to automate the annotation process without compromise of accuracy, we propose an instance selection strategy to effectively utilize the automatically generated annotation. In our selection strategy, an informative and diverse set of instances are selected for effective disambiguation. Lastly, topic modeling is used to model the semantic topics of the articles. These advancements give statistical significant improvement to entity linking individually. Collectively they lead the highest performance on KBP-2010 task.