Wikipedia provides an enormous amount of background knowledge to reason about the semantic relatedness between two entities. We propose Wikipedia-based Distributional Semantics for Entity Relatedness (DiSER), which represents the semantics of an entity by its distribution in the high dimensional concept space derived from Wikipedia. DiSER measures the semantic relatedness between two entities by quantifying the distance between the corresponding high-dimensional vectors. DiSER builds the model by taking the annotated entities only, therefore it improves over existing approaches, which do not distinguish between an entity and its surface form. We evaluate the approach on a benchmark that contains the relative entity relatedness scores for 420 entity pairs. Our approach improves the accuracy by 12% on state of the art methods for computing entity relatedness. We also show an evaluation of DiSER in the Entity Disambiguation task on a dataset of 50 sentences with highly ambiguous entity mentions. It shows an improvement of 10% in precision over the best performing methods. In order to provide the resource that can be used to find out all the related entities for a given entity, a graph is constructed, where the nodes represent Wikipedia entities and the relatedness scores are reflected by the edges. Wikipedia contains more than 4.1 millions entities, which required efficient computation of the relatedness scores between the corresponding 17 trillions of entity-pairs.

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 propose an online scheduling algorithm for posting crowdsourcing tasks which maximizes a novel metric called task viewership. This metric is computed using stochastic model based on coverage process and it measures the likelihood that a task is viewed by multiple crowd workers, which is correlated to the likelihood that it will be selected and completed.

Recommending media objects to users typically requires users to rate existing media objects so as to understand their preferences. The number of ratings required to produce good suggestions can be reduced through collaborative filtering. Collaborative filtering is more difficult when prior users have not rated the same set of media objects as the current user or each other. In this work, we describe an approach to applying prior user data in a way that does not require users to rate the same media objects and that does not require imputation (estimation) of prior user ratings of objects they have not rated. This approach is applied to the problem of finding good equalizer settings for music audio and is shown to greatly reduce the number of ratings the current user must make to find a good equalization setting.

Personalization is a way for computers to support people’s diverse interests and needs by providing content tailored to the individual. While strides have been made in algorithmic approaches to personalization, most require access to a significant amount of data. However, even when data is limited online crowds can be used to infer an individual’s personal preferences. Aided by the diversity of tastes among online crowds and their ability to understand others, we show that crowdsourcing is an effective on-demand tool for personalization. Unlike typical crowdsourcing approaches that seek a ground truth, we present and evaluate two crowdsourcing approaches designed to capture personal preferences. The first, taste-matching , identifies workers with similar taste to the requester and uses their taste to infer the requester’s taste. The second, taste-grokking , asks workers to explicitly predict the requester’s taste based on training examples. These techniques are evaluated on two subjective tasks, personalized image recommendation and tailored textual summaries. Taste-matching and taste-grokking both show improvement over the use of generic workers, and have different benefits and drawbacks depending on the complexity of the task and the variability of the taste space.

Despite the prevalence of collaborative filtering in recommendation systems, there has been little theoretical development on why and how well it works, especially in the "online" setting, where items are recommended to users over time. We address this theoretical gap by introducing a model for online recommendation systems, cast item recommendation under the model as a learning problem, and analyze the performance of a cosine-similarity collaborative filtering method. In our model, each of $n$ users either likes or dislikes each of $m$ items. We assume there to be $k$ types of users, and all the users of a given type share a common string of probabilities determining the chance of liking each item. At each time step, we recommend an item to each user, where a key distinction from related bandit literature is that once a user consumes an item (e.g., watches a movie), then that item cannot be recommended to the same user again. The goal is to maximize the number of likable items recommended to users over time. Our main result establishes that after nearly $\log(km)$ initial learning time steps, a simple collaborative filtering algorithm achieves essentially optimal performance without knowing $k$. The algorithm has an exploitation step that uses cosine similarity and two types of exploration steps, one to explore the space of items (standard in the literature) and the other to explore similarity between users (novel to this work).

Rating Prediction is a basic problem in Recommender System, and one of the most widely used method is Factorization Machines(FM). However, traditional matrix factorization methods fail to utilize the benefit of implicit feedback, which has been proved to be important in Rating Prediction problem. In this work, we consider a specific situation, movie rating prediction, where we assume that a user's watching history has a big influence on his/her rating behavior on an item. We introduce two models, Latent Dirichlet Allocation(LDA) and word2vec, both of which perform state-of-the-art results in training latent features. Based on that, we propose two feature based models. One is the Topic-based FM Model which provides the implicit feedback to the matrix factorization, the other is the Vector-based FM Model which exploits the order info of a user's watching history resulting in better performance. Empirical results on three datasets demonstrate that our method performs better than the baseline model and confirm that Vector-based FM Model usually works better as it contains the order info.

Advancements in parallel processing have lead to a surge in multilayer perceptrons' (MLP) applications and deep learning in the past decades. Recurrent Neural Networks (RNNs) give additional representational power to feedforward MLPs by providing a way to treat sequential data. However, RNNs are hard to train using conventional error backpropagation methods because of the difficulty in relating inputs over many time-steps. Regularization approaches from MLP sphere, like dropout and noisy weight training, have been insufficiently applied and tested on simple RNNs. Moreover, solutions have been proposed to improve convergence in RNNs but not enough to improve the long term dependency remembering capabilities thereof. In this study, we aim to empirically evaluate the remembering and generalization ability of RNNs on polyphonic musical datasets. The models are trained with injected noise, random dropout, norm-based regularizers and their respective performances compared to well-initialized plain RNNs and advanced regularization methods like fast-dropout. We conclude with evidence that training with noise does not improve performance as conjectured by a few works in RNN optimization before ours.

The problem of Poisson denoising appears in various imaging applications, such as low-light photography, medical imaging and microscopy. In cases of high SNR, several transformations exist so as to convert the Poisson noise into an additive i.i.d. Gaussian noise, for which many effective algorithms are available. However, in a low SNR regime, these transformations are significantly less accurate, and a strategy that relies directly on the true noise statistics is required. A recent work by Salmon et al. took this route, proposing a patch-based exponential image representation model based on GMM (Gaussian mixture model), leading to state-of-the-art results. In this paper, we propose to harness sparse-representation modeling to the image patches, adopting the same exponential idea. Our scheme uses a greedy pursuit with boot-strapping based stopping condition and dictionary learning within the denoising process. The reconstruction performance of the proposed scheme is competitive with leading methods in high SNR, and achieving state-of-the-art results in cases of low SNR.

The matrix-completion problem has attracted a lot of attention, largely as a result of the celebrated Netflix competition. Two popular approaches for solving the problem are nuclear-norm-regularized matrix approximation (Candes and Tao, 2009, Mazumder, Hastie and Tibshirani, 2010), and maximum-margin matrix factorization (Srebro, Rennie and Jaakkola, 2005). These two procedures are in some cases solving equivalent problems, but with quite different algorithms. In this article we bring the two approaches together, leading to an efficient algorithm for large matrix factorization and completion that outperforms both of these. We develop a software package "softImpute" in R for implementing our approaches, and a distributed version for very large matrices using the "Spark" cluster programming environment.