Matching a question to its best answer is a common task in community question answering. In this paper, we focus on the non-factoid questions and aim to pick out the best answer from its candidate answers. Most of the existing deep models directly measure the similarity between question and answer by their individual sentence embeddings. In order to tackle the problem of the information lack in question's descriptions and the lexical gap between questions and answers, we propose a novel deep architecture namely SPAN in this paper. Specifically we introduce support answers to help understand the question, which are defined as the best answers of those similar questions to the original one. Then we can obtain two kinds of similarities, one is between question and the candidate answer, and the other one is between support answers and the candidate answer. The matching score is finally generated by combining them. Experiments on Yahoo! Answers demonstrate that SPAN can outperform the baseline models.

Poker is a family of card games that includes many varia- tions. We hypothesize that most poker games can be solved as a pattern matching problem, and propose creating a strong poker playing system based on a unified poker representa- tion. Our poker player learns through iterative self-play, and improves its understanding of the game by training on the results of its previous actions without sophisticated domain knowledge. We evaluate our system on three poker games: single player video poker, two-player Limit Texas Hold’em, and finally two-player 2-7 triple draw poker. We show that our model can quickly learn patterns in these very different poker games while it improves from zero knowledge to a competi- tive player against human experts. The contributions of this paper include: (1) a novel represen- tation for poker games, extendable to different poker vari- ations, (2) a Convolutional Neural Network (CNN) based learning model that can effectively learn the patterns in three different games, and (3) a self-trained system that signif- icantly beats the heuristic-based program on which it is trained, and our system is competitive against human expert players.

In this demo, we build a practical mobile application, Moodee, to help detect and release users' psychological stress by leveraging users' social media data in online social networks, and provide an interactive user interface to present users' and friends' psychological stress states in an visualized and intuitional way. Given users' online social media data as input, Moodee intelligently and automatically detects users' stress states. Moreover, Moodee would recommend users with different links to help release their stress. The main technology of this demo is a novel hybrid model - a factor graph model combined with Deep Neural Network, which can leverage social media content and social interaction information for stress detection. We think that Moodee can be helpful to people's mental health, which is a vital problem in

We consider the task of predicting various traits of a person given an image of their face. We aim to estimate traits such as gender, ethnicity and age, as well as more subjective traits as the emotion a person expresses or whether they are humorous or attractive. Due to the recent surge of research on Deep Convolutional Neural Networks (CNNs), we begin by using a CNN architecture, and corroborate that CNNs are promising for facial attribute prediction. To further improve performance, we propose a novel approach that incorporates facial landmark information for input images as an additional channel, helping the CNN learn face-specific features so that the landmarks across various training images hold correspondence. We empirically analyze the performance of our proposed method, showing consistent improvement over the baselines across traits. We demonstrate our system on a sizeable Face Attributes Dataset (FAD), comprising of roughly 200,000 labels, for 10 most sought-after traits, for over 10,000 facial images.

We propose a system for determining properties of mathematical functions given an image of their graph representation. We demonstrate our approach for two-dimensional graphs (curves of single variable functions) and three-dimensional graphs (surfaces of two variable functions), studying the properties of convexity and symmetry. Our method uses a Convolutional Neural Network which classifies functions according to these properties, without using any hand-crafted features. We propose algorithms for randomly constructing functions with convexity or symmetry properties, and use the images generated by these algorithms to train our network. Our system achieves a high accuracy on this task, even for functions where humans find it difficult to determine the function's properties from its image.

Several discriminative models with latent variables were also explored to learn better alignment models in a wetlab The Conference of the North American Chapter of the Association experiment domain (Naim et al. 2015). As alignment is for Computational Linguistics: Human Language often the first step in many problems involving language and Technology (NAACL HLT) is a premier conference reporting vision, these approaches and empirical results provide important outstanding research on human language technology.

Automated story generation has a long history of pursuit in RNNs are extremely powerful for NLP tasks, having demonstrated artificial intelligence. Early approaches used hand-authored success on tasks like speech recognition (Graves and formal models of a particular story-world domain to generate Jaitly 2014) and machine translation (Sundermeyer et al. narratives pertaining to that domain (Klein, Aeschlimann, 2014). Mikolov et al. (Mikolov et al. 2010) showed that and Balsiger 1973; Lebowitz 1985; Meehan 1977). RNNs encode more accurate language models than traditional With the advent of machine learning, more recent work has n-gram statistics, as measured by performance on a explored how to construct narrative models automatically standard speech recognition task. The simplest RNN architecture from story corpora (Li et al. 2013; McIntyre and Lapata has an input layer, hidden layer, and output layer connected 2009; Swanson and Gordon 2012).

The restricted Boltzmann machine (RBM) has been used as building blocks for many successful deep learning models, e.g., deep belief networks (DBN) and deep Boltzmann machine (DBM) etc. The training of RBM can be extremely slow in pathological regions. The second order optimization methods, such as quasi-Newton methods, were proposed to deal with this problem. However, the non-convexity results in many obstructions for training RBM, including the infeasibility of applying second order optimization methods. In order to overcome this obstruction, we introduce an em-like iterative project quasi-Newton (IPQN) algorithm. Specifically, we iteratively perform the sampling procedure where it is not necessary to update parameters, and the sub-training procedure that is convex. In sub-training procedures, we apply quasi-Newton methods to deal with the pathological problem. We further show that Newton's method turns out to be a good approximation of the natural gradient (NG) method in RBM training. We evaluate IPQN in a series of density estimation experiments on the artificial dataset and the MNIST digit dataset. Experimental results indicate that IPQN achieves an improved convergent performance over the traditional CD method.

Human's cognition system prompts that context information provides potentially powerful clue while recognizing objects. However, for fine-grained image classification, the contribution of context may vary over different images, and sometimes the context even confuses the classification result. To alleviate this problem, in our work, we develop a novel approach, two-stream contextualized Convolutional Neural Network, which provides a simple but efficient context-content joint classification model under deep learning framework. The network merely requires the raw image and a coarse segmentation as input to extract both content and context features without need of human interaction. Moreover, our network adopts a weighted fusion scheme to combine the content and the context classifiers, while a subnetwork is introduced to adaptively determine the weight for each image. According to our experiments on public datasets, our approach achieves considerable high recognition accuracy without any tedious human's involvements, as compared with the state-of-the-art approaches.

The lack of reliable data in developing countries is a major obstacle to sustainable development, food security, and disaster relief. Poverty data, for example, is typically scarce, sparse in coverage, and labor-intensive to obtain. Remote sensing data such as high-resolution satellite imagery, on the other hand, is becoming increasingly available and inexpensive. Unfortunately, such data is highly unstructured and currently no techniques exist to automatically extract useful insights to inform policy decisions and help direct humanitarian efforts. We propose a novel machine learning approach to extract large-scale socioeconomic indicators from high-resolution satellite imagery. The main challenge is that training data is very scarce, making it difficult to apply modern techniques such as Convolutional Neural Networks (CNN). We therefore propose a transfer learning approach where nighttime light intensities are used as a data-rich proxy. We train a fully convolutional CNN model to predict nighttime lights from daytime imagery, simultaneously learning features that are useful for poverty prediction. The model learns filters identifying different terrains and man-made structures, including roads, buildings, and farmlands, without any supervision beyond nighttime lights. We demonstrate that these learned features are highly informative for poverty mapping, even approaching the predictive performance of survey data collected in the field.