Recently, several Web-scale knowledge harvesting systems have been built, each of which is competent at extracting information from certain types of data (e.g., unstructured text, structured tables on the web, etc.). In order to determine the response to a new query posed to such systems (e.g., is sugar a healthy food?), it is useful to integrate opinions from multiple systems. If a response is desired within a specific time budget (e.g., in less than 2 seconds), then maybe only a subset of these resources can be queried. In this paper, we address the problem of knowledge integration for on-demand time-budgeted query answering. We propose a new method, AskWorld, which learns a policy that chooses which queries to send to which resources, by accommodating varying budget constraints that are available only at query (test) time. Through extensive experiments on real world datasets, we demonstrate AskWorld’s capability in selecting most informative resources to query within test-time constraints, resulting in improved performance compared to competitive baselines.

Product review sites such as TripAdvisor, Yelp or Amazon provide a single, non personalized ranking of products. The sparse review data makes personalizing recommendations difficult. Topic Profile Collaborative Filtering exploits review texts to identify user profiles as a basis for similarity. We show that careful use of the available data and separating users into classes can greatly improve the performance of such techniques. We significantly improve MAE, RMSE, and Kendall tau, compared to the previous best results. In addition, we show that personalization does not benefit all the users to the same extent. We propose switching between a personalized and a non personalized method based on the user opinion profile. We show that the user's opinionatedness is a good indicator of whether the personalization will work or not.

The popularization and quick growth of Linked Open Data (LOD) has led to challenging aspects regarding quality assessment and data exploration of the RDF triples that shape the LOD cloud.Particularly, we are interested in the completeness of data and its potential to provide concept definitions in terms of necessary and sufficient conditions.In this work we propose a novel technique based on Formal Concept Analysis which organizes RDF data into a concept lattice.This allows data exploration as well as the discovery of implications, which are used to automatically detect missing information and then to complete RDF data.Moreover, this is a way of reconciling syntax and semantics in the LOD cloud.Finally, experiments on the DBpedia knowledge base show that the approach is well-founded and effective.

Computing the set of optimal solutions for a multi-objective constraint optimisation problem can be computationally very challenging. Also, when solutions are only partially ordered, there can be a number of different natural notions of optimality, one of the most important being the notion of Possibly Optimal, i.e., optimal in at least one scenario compatible with the inter-objective tradeoffs. We develop an AND/OR Branch-and-Bound algorithm for computing the set of Possibly Optimal solutions, and compare variants of the algorithm experimentally.

An author’s profile on Google Scholar consists of indexed articles and associated data, such as the number of citations and the H-index. The author is allowed to merge articles, which may affect the H-index. We analyze the parameterized complexity of maximizing the H-index using article merges. Herein, to model realistic manipulation scenarios, we define a compatability graph whose edges correspond to plausible merges. Moreover, we consider multiple possible measures for computing the citation count of a merged article. For the measure used by Google Scholar, we give an algorithm that maximizes the H-index in linear time if the compatibility graph has constant-size connected components. In contrast, if we allow to merge arbitrary articles, then already increasing the H-index by one is NP-hard. Experiments on Google Scholar profiles of AI researchers show that the H-index can be manipulated substantially only by merging articles with highly dissimilar titles, which would be easy to discover.

We propose a method to guide a Monte Carlo search in the initial moves of the game of Go. Our method matches the current state of a Go board against clusters of board configurations that are derived from a large number of games played by experts. The main advantage of this method is that it does not require an exact match of the current board, and hence is effective for a longer sequence of moves compared to traditional opening books. We apply this method to two different open-source Go-playing programs. Our experiments show that this method, through its filtering or biasing the choice of a next move to a small subset of possible moves, improves play effectively in the initial moves of a game.

Compositionality is a fundamental notion in computation whereby complex abstractions can be constructed from simpler ones, but this property has so far escaped the paradigm of end-user programming from examples or natural language. Existing approaches restrict end users to only give holistic end-to-end specifications, which limits the expressivity and scalability of these approaches to relatively simple programs in very restricted domains. In this paper we propose a new approach to end-user program synthesis in which input can be given in a compositional manner through a combination of natural language and examples. We present a domain-agnostic program synthesis algorithm and demonstrate its application to an expressive string manipulation language. We evaluate on a range of complex examples from help forums that are beyond the scope of previous systems.

Recently, a number of papers have shown that for many domains, using multiple heuristics in independent searches performs better than combining them into a single heuristic. Furthermore, using a large number of “weak” heuristics could potentially eliminate the need for the careful design of a few. The standard approach to distribute computation in these multi-heuristic searches is to rotate through the heuristics in a round-robin fashion. However, this strategy can be inefficient especially in the case when only a few of the heuristics are leading to progress. In this paper, we present two principled methods to adaptively distribute computation time among the different searches of the Multi- Heuristic A* algorithm. The first method, Meta-A*, constructs and searches a meta-graph, which represents the problem of finding the best heuristic as the problem of minimizing the total number of expansions. The second treats the scheduling of searches with different heuristics as a multi-armed bandit problem. It applies Dynamic Thompson Sampling (DTS) to keep track of what searches are making progress the most and continuously re-computes the schedule of searches based on this information. We provide a theoretical analysis and compare our new strategies with the round-robin method on a 12-DOF full-body motion planning problem and on sliding tile puzzle problems. In these experiments, we used up to 20 heuristics and observed a several times speedup without loss in solution quality.

Several applications including text-to-speech require some normalized format of non-standard words in various domains such as numbers, dates, and currencies and in various human languages. The traditional approach of manually constructing a program for such a normalization task requires expertise in both programming and target (human) language and further does not scale to a large number of domain, format, and target language combinations. We propose to learn programs for such normalization tasks through examples. We present a domain-specific programming language that offers appropriate abstractions for succinctly describing such normalization tasks, and then present a novel search algorithm that can effectively learn programs in this language from input-output examples. We also briefly describe domain-specific heuristics for guiding users of our system to provide representative examples for normalization tasks related to that domain. Our experiments show that weare able to effectively learn desired programs for a variety of normalization tasks.

Planning an interplanetary trajectory is a very complex task, traditionally accomplished by domain experts using computer-aided design tools. Recent advances in trajectory optimization allow automation of part of the trajectory design but have yet to provide an efficient way to select promising planetary encounter sequences. In this work, we present a heuristic-free approach to automated trajectory planning (including the encounter sequence planning) based on Monte Carlo Tree Search (MCTS). We discuss a number of modifications to traditional MCTS unique to the domain of interplanetary trajectory planning and provide results on the Rosetta and Cassini-Huygens interplanetary mission design problems. The resulting heuristic-free method is found to be orders of magnitude more efficient with respect to a standard tree search with heuristic-based pruning which is the current state-of-the art in this domain.