In this article, we report on a multiphase R&D effort to develop a conversational second screen application for TV program discovery. Our goal is to share with the community the breadth of artificial intelligence (AI) and natural language (NL) technologies required to develop such an application along with learnings from target end-users. We first give an overview of our application from the perspective of the end-user. We then present the architecture of our application along with the main AI and NL components, which were developed over multiple phases. The first phase focuses on enabling core functionality such as effectively finding programs matching the user’s intent. The second phase focuses on enabling dialog with the user. Finally, we present two user studies, corresponding to these two phases. The results from both studies demonstrate the effectiveness of our application in the target domain.

Static analysis is a core task in query optimization and knowledge base verification. We study static analysis techniques for SPARQL, the standard language for querying Semantic Web data. Specifically, we investigate the query containment problem and query-update independence analysis. We are interested in developing techniques through reductions to the validity problem in logic.

The standard way of answering queries over incomplete databases is to compute certain answers, defined as the intersection of query answers on all complete databases that the incomplete database represents. But is this universally accepted definition correct? We argue that this ``one-size-fits-all'' definition can often lead to counterintuitive or just plain wrong results, and propose an alternative framework for defining certain answers. We combine three previously used approaches, based on the semantics and representation systems, on ordering incomplete databases in terms of their informativeness, and on viewing databases as knowledge expressed in a logical language, to come up with a well justified and principled notion of certain answers. Using it, we show that for queries satisfying some natural conditions (like not losing information if a more informative input is given), computing certain answers is surprisingly easy, and avoids the complexity issues that have been associated with the classical definition.

The paper presents an approach for optimizing the evaluation of SPARQL queries over OWL ontologies using SPARQL's OWL Direct Semantics entailment regime. The approach is based on the computation of lower and upper bounds, but we allow for much more expressive queries than related approaches. In order to optimize the evaluation of possible query answers in the upper but not in the lower bound, we present a query extension approach that uses schema knowledge from the queried ontology to extend the query with additional parts. We show that the resulting query is equivalent to the original one and we use the additional parts that are simple to evaluate for restricting the bounds of subqueries of the initial query. In an empirical evaluation we show that the proposed query extension approach can lead to a significant decrease in the query execution time of up to four orders of magnitude.

In view of the paradigm shift that makes science ever more data-driven, in this thesis we propose a synthesis method for encoding and managing large-scale deterministic scientific hypotheses as uncertain and probabilistic data. In the form of mathematical equations, hypotheses symmetrically relate aspects of the studied phenomena. For computing predictions, however, deterministic hypotheses can be abstracted as functions. We build upon Simon's notion of structural equations in order to efficiently extract the (so-called) causal ordering between variables, implicit in a hypothesis structure (set of mathematical equations). We show how to process the hypothesis predictive structure effectively through original algorithms for encoding it into a set of functional dependencies (fd's) and then performing causal reasoning in terms of acyclic pseudo-transitive reasoning over fd's. Such reasoning reveals important causal dependencies implicit in the hypothesis predictive data and guide our synthesis of a probabilistic database. Like in the field of graphical models in AI, such a probabilistic database should be normalized so that the uncertainty arisen from competing hypotheses is decomposed into factors and propagated properly onto predictive data by recovering its joint probability distribution through a lossless join. That is motivated as a design-theoretic principle for data-driven hypothesis management and predictive analytics. The method is applicable to both quantitative and qualitative deterministic hypotheses and demonstrated in realistic use cases from computational science.

An approach to query optimization is described that draws on two sources of knowledge: real world constraints on the values for the application domain served by the database; and knowledge about the current structure of the database and the cost of available retrieval processes. Real world knowledge is embodied in rules that are much like semantic integrity rules. The approach, called "query rephrasing", is to generate semantic equivalents of user queries that cost less to process than the original queries. The operation of a prototype system based on this approach is discussed in the context 0. simple queries which restrict a single file. The need for heuristics to limit the generation of equivalent queries is also discussed, and a method ut g "constraint thresholds" derived from

In this paper, we present an approach to mine large-scale knowledge graphs to discover inference paths for query expansion in NLIDB (Natural Language Interface to Databases). Addressing this problem is important in order for NLIDB applications to effectively handle relevant concepts in the domain of interest that do not correspond to any structured fields in the target database. We also present preliminary observations on the performance of our approach applied to Freebase, and conclude with discussions on next steps to further evaluate and extend our approach.

We present an implemented approach to transform natural language sentences into SPARQL, using background knowledge from ontologies and lexicons. Therefore, eligible technologies and data storage possibilities are analyzed and evaluated. The contributions of this paper are twofold. Firstly, we describe the motivation and current needs for a natural language access to industry data. We describe several scenarios where the proposed solution is required. Resulting in an architectural approach based on automatic SPARQL query construction for effective natural language queries. Secondly, we analyze the performance of RDBMS, RDF and Triple Stores for the knowledge representation. The proposed approach will be evaluated on the basis of a query catalog by means of query efficiency, accuracy, and data storage performance. The results show, that natural language access to industry data using ontologies and lexicons, is a simple but effective approach to improve the diagnosis process and the data search for a broad range of users. Furthermore, virtual RDF graphs do support the DB-driven knowledge graph representation process, but do not perform efficient under industry conditions in terms of performance and scalability.

In this paper we revisit the problem of generating query plans using AI automated planning with a view to leveraging significant recent advances in state-of-the-art planning techniques. Our efforts focus on the specific problem of cost-based join-order optimization for conjunctive relational queries, a critical component of production-quality query optimizers. We characterize the general query-planning problem as a delete-free planning problem, and query plan optimization as a context-sensitive cost-optimal planning problem. We propose algorithms that generate high-quality query plans, guaranteeing optimality under certain conditions. Our approach is general, supporting the use of a broad suite of domain-independent and domain-specific optimization criteria. Experimental results demonstrate the effectiveness of AI planning techniques for query plan generation and optimization.

In web search, users queries are formulated using only few terms and term-matching retrieval functions could fail at retrieving relevant documents. Given a user query, the technique of query expansion (QE) consists in selecting related terms that could enhance the likelihood of retrieving relevant documents. Selecting such expansion terms is challenging and requires a computational framework capable of encoding complex semantic relationships. In this paper, we propose a novel method for learning, in a supervised way, semantic representations for words and phrases. By embedding queries and documents in special matrices, our model disposes of an increased representational power with respect to existing approaches adopting a vector representation. We show that our model produces high-quality query expansion terms. Our expansion increase IR measures beyond expansion from current word-embeddings models and well-established traditional QE methods.