We propose a neural probabilistic structured-prediction method for transition-based natural language processing, which integrates beam search and contrastive learning. The method uses a global optimization model, which can leverage arbitrary features over non-local context. Beam search is used for efficient heuristic decoding, and contrastive learning is performed for adjusting the model according to search errors. When evaluated on both chunking and dependency parsing tasks, the proposed method achieves significant accuracy improvements over the locally normalized greedy baseline on the two tasks, respectively.

Games with large branching factors pose a significant challenge for game tree search algorithms. In this paper, we address this problem with a sampling strategy for Monte Carlo Tree Search (MCTS) algorithms called "naive sampling", based on a variant of the Multi-armed Bandit problem called "Combinatorial Multi-armed Bandits" (CMAB). We analyze the theoretical properties of several variants of naive sampling, and empirically compare it against the other existing strategies in the literature for CMABs. We then evaluate these strategies in the context of real-time strategy (RTS) games, a genre of computer games characterized by their very large branching factors. Our results show that as the branching factor grows, naive sampling outperforms the other sampling strategies.

Google is using a 10,000-strong army of independent contractors to flag "offensive or upsetting" content, in order to ensure that queries like "did the Holocaust happen" don't push users to misinformation, propaganda and hate speech. The review of search terms is being done by the company's "quality raters", a little-known corps of worldwide contractors that Google uses to assess the quality of its systems. The raters are given searches based on real queries to conduct, and are asked to score the results on whether they meet the needs of users. These contractors, introduced to the company's review process in 2013, work from a huge manual describing every potential problem they could find with a given search query: whether or not it meets the user's expectations, whether the result offered is low or high quality, and whether it's spam, porn or illegal. In a new update to the rating system, rolled out on Tuesday, Google introduced another flag raters could use: the "upsetting-offensive" mark.

In this paper we look into the problem of planning over hybrid domains, where change can be both discrete and instantaneous, or continuous over time. In addition, it is required that each state on the trajectory induced by the execution of plans complies with a given set of global constraints. We approach the computation of plans for such domains as the problem of searching over a deterministic state model. In this model, some of the successor states are obtained by solving numerically the so-called initial value problem over a set of ordinary differential equations (ODE) given by the current plan prefix. These equations hold over time intervals whose duration is determined dynamically, according to whether zero crossing events take place for a set of invariant conditions. The resulting planner, FS+, incorporates these features together with effective heuristic guidance. FS+ does not impose any of the syntactic restrictions on process effects often found on the existing literature on Hybrid Planning. A key concept of our approach is that a clear separation is struck between planning and simulation time steps. The former is the time allowed to observe the evolution of a given dynamical system before committing to a future course of action, whilst the later is part of the model of the environment. FS+ is shown to be a robust planner over a diverse set of hybrid domains, taken from the existing literature on hybrid planning and systems.

Context: One of the black arts of data mining is learning the magic parameters which control the learners. In software analytics, at least for defect prediction, several methods, like grid search and differential evolution (DE), have been proposed to learn these parameters, which has been proved to be able to improve the performance scores of learners. Objective: We want to evaluate which method can find better parameters in terms of performance score and runtime cost. Methods: This paper compares grid search to differential evolution, which is an evolutionary algorithm that makes extensive use of stochastic jumps around the search space. Results: We find that the seemingly complete approach of grid search does no better, and sometimes worse, than the stochastic search. When repeated 20 times to check for conclusion validity, DE was over 210 times faster than grid search to tune Random Forests on 17 testing data sets with F-Measure Conclusions: These results are puzzling: why does a quick partial search be just as effective as a much slower, and much more, extensive search? To answer that question, we turned to the theoretical optimization literature. Bergstra and Bengio conjecture that grid search is not more effective than more randomized searchers if the underlying search space is inherently low dimensional. This is significant since recent results show that defect prediction exhibits very low intrinsic dimensionality-- an observation that explains why a fast method like DE may work as well as a seemingly more thorough grid search. This suggests, as a future research direction, that it might be possible to peek at data sets before doing any optimization in order to match the optimization algorithm to the problem at hand.

When coming across the term "text search", one usually thinks of a large body of text, which is indexed in a way that makes it possible to quickly look up one or more search terms when they are entered by a user. This is a classic problem for computer scientists, to which many solutions exist. What if what's available for indexing beforehand is a group of search phrases, and only at runtime is a large body of text presented for searching? These questions are what this trie data structure tutorial seeks to address. A real world application for this scenario is matching a number of medical theses against a list of medical conditions and finding out which theses discuss which conditions.

Greedy algorithms are widely used for problems in machine learning such as feature selection and set function optimization. Unfortunately, for large datasets, the running time of even greedy algorithms can be quite high. This is because for each greedy step we need to refit a model or calculate a function using the previously selected choices and the new candidate. Two algorithms that are faster approximations to the greedy forward selection were introduced recently ([Mirzasoleiman et al. 2013, 2015]). They achieve better performance by exploiting distributed computation and stochastic evaluation respectively. Both algorithms have provable performance guarantees for submodular functions. In this paper we show that divergent from previously held opinion, submodularity is not required to obtain approximation guarantees for these two algorithms. Specifically, we show that a generalized concept of weak submodularity suffices to give multiplicative approximation guarantees. Our result extends the applicability of these algorithms to a larger class of functions. Furthermore, we show that a bounded submodularity ratio can be used to provide data dependent bounds that can sometimes be tighter also for submodular functions. We empirically validate our work by showing superior performance of fast greedy approximations versus several established baselines on artificial and real datasets.

We consider the problem of learning a causal graph over a set of variables with interventions. We study the cost-optimal causal graph learning problem: For a given skeleton (undirected version of the causal graph), design the set of interventions with minimum total cost, that can uniquely identify any causal graph with the given skeleton. We show that this problem is solvable in polynomial time. Later, we consider the case when the number of interventions is limited. For this case, we provide polynomial time algorithms when the skeleton is a tree or a clique tree. For a general chordal skeleton, we develop an efficient greedy algorithm, which can be improved when the causal graph skeleton is an interval graph.

The facility location problem is widely used for summarizing large datasets and has additional applications in sensor placement, image retrieval, and clustering. One difficulty of this problem is that submodular optimization algorithms require the calculation of pairwise benefits for all items in the dataset. This is infeasible for large problems, so recent work proposed to only calculate nearest neighbor benefits. One limitation is that several strong assumptions were invoked to obtain provable approximation guarantees. In this paper we establish that these extra assumptions are not necessary---solving the sparsified problem will be almost optimal under the standard assumptions of the problem. We then analyze a different method of sparsification that is a better model for methods such as Locality Sensitive Hashing to accelerate the nearest neighbor computations and extend the use of the problem to a broader family of similarities. We validate our approach by demonstrating that it rapidly generates interpretable summaries.

The Rubik's cube was devised by Hungarian architect Erno Rubik more than 30 years ago, but he likely never envisioned his puzzle being cracked this quickly. The machine, known as'Sub1 Reloaded' and developed by German tech company Infineon, was aided by one of the world's most powerful microcomputers, solved a Rubik's cube in 0.637 seconds at the Electronica Trade Fair in Munich, Germany earlier this year. The machine, known as'Sub1 Reloaded' and developed by German tech company Infineon, was aided by one of the world's most powerful microcomputers'Guinness World Records has spent some time carefully reviewing the evidence, including ensuring that the cube and the pre-scrambling met all WCA standards, before confirming the new record today,' the organisation said. The robot took a fraction of a second to analyse the cube and make 21 moves to solve the puzzle. Its time of 0.637 seconds beat the previous world record of 0.887 seconds, set by an earlier prototype of the same machine.