We present a novel approach to learning word embeddings by exploring subword information (character n-gram, root/affix and inflections) and capturing the structural information of their context with convolutional feature learning. Specifically, we introduce a convolutional neural network architecture that allows us to measure structural information of context words and incorporate subword features conveying semantic, syntactic and morphological information related to the words. To assess the effectiveness of our model, we conduct extensive experiments on the standard word similarity and word analogy tasks. We showed improvements over existing state-of-the-art methods for learning word embeddings, including skipgram, GloVe, char n-gram and DSSM.

Math word problems provide a natural abstraction to a range of natural language understanding problems that involve reasoning about quantities, such as interpreting election results, news about casualties, and the financial section of a newspaper. Units associated with the quantities often provide information that is essential to support this reasoning. This paper proposes a principled way to capture and reason about units and shows how it can benefit an arithmetic word problem solver. This paper presents the concept of Unit Dependency Graphs (UDGs), which provides a compact representation of the dependencies between units of numbers mentioned in a given problem. Inducing the UDG alleviates the brittleness of the unit extraction system and allows for a natural way to leverage domain knowledge about unit compatibility, for word problem solving. We introduce a decomposed model for inducing UDGs with minimal additional annotations, and use it to augment the expressions used in the arithmetic word problem solver of (Roy and Roth 2015) via a constrained inference framework. We show that introduction of UDGs reduces the error of the solver by over 10 %, surpassing all existing systems for solving arithmetic word problems. In addition, it also makes the system more robust to adaptation to new vocabulary and equation forms .

We present SummaRuNNer, a Recurrent Neural Network (RNN) based sequence model for extractive summarization of documents and show that it achieves performance better than or comparable to state-of-the-art. Our model has the additional advantage of being very interpretable, since it allows visualization of its predictions broken up by abstract features such as information content, salience and novelty. Another novel contribution of our work is abstractive training of our extractive model that can train on human generated reference summaries alone, eliminating the need for sentence-level extractive labels.

Bag-of-ngrams (BoN) models are commonly used for representing text. One of the main drawbacks of traditional BoN is the ignorance of n-gram's semantics. In this paper, we introduce the concept of Neural Bag-of-ngrams (Neural-BoN), which replaces sparse one-hot n-gram representation in traditional BoN with dense and rich-semantic n-gram representations. We first propose context guided n-gram representation by adding n-grams to word embeddings model. However, the context guided learning strategy of word embeddings is likely to miss some semantics for text-level tasks. Text guided n-gram representation and label guided n-gram representation are proposed to capture more semantics like topic or sentiment tendencies. Neural-BoN with the latter two n-gram representations achieve state-of-the-art results on 4 document-level classification datasets and 6 semantic relatedness categories. They are also on par with some sophisticated DNNs on 3 sentence-level classification datasets. Similar to traditional BoN, Neural-BoN is efficient, robust and easy to implement. We expect it to be a strong baseline and be used in more real-world applications.

This paper shows that simply prescribing "none of the above" labels to unlabeled data has a beneficial regularization effect to supervised learning. We call it universum prescription by the fact that the prescribed labels cannot be one of the supervised labels. In spite of its simplicity, universum prescription obtained competitive results in training deep convolutional networks for CIFAR-10, CIFAR-100, STL-10 and ImageNet datasets. A qualitative justification of these approaches using Rademacher complexity is presented. The effect of a regularization parameter — probability of sampling from unlabeled data — is also studied empirically.

This paper proposes a learning strategy that embeds object-part concepts into a pre-trained convolutional neural network (CNN), in an attempt to 1) explore explicit semantics hidden in CNN units and 2) gradually transform the pre-trained CNN into a semantically interpretable graphical model for hierarchical object understanding. Given part annotations on very few (e.g., 3-12) objects, our method mines certain latent patterns from the pre-trained CNN and associates them with different semantic parts. We use a four-layer And-Or graph to organize the CNN units, so as to clarify their internal semantic hierarchy. Our method is guided by a small number of part annotations, and it achieves superior part-localization performance (about 13%-107% improvement in part center prediction on the PASCAL VOC and ImageNet datasets)

As a new way of training generative models, Generative Adversarial Net (GAN) that uses a discriminative model to guide the training of the generative model has enjoyed considerable success in generating real-valued data. However, it has limitations when the goal is for generating sequences of discrete tokens. A major reason lies in that the discrete outputs from the generative model make it difficult to pass the gradient update from the discriminative model to the generative model. Also, the discriminative model can only assess a complete sequence, while for a partially generated sequence, it is non-trivial to balance its current score and the future one once the entire sequence has been generated. In this paper, we propose a sequence generation framework, called SeqGAN, to solve the problems. Modeling the data generator as a stochastic policy in reinforcement learning (RL), SeqGAN bypasses the generator differentiation problem by directly performing gradient policy update. The RL reward signal comes from the GAN discriminator judged on a complete sequence, and is passed back to the intermediate state-action steps using Monte Carlo search. Extensive experiments on synthetic data and real-world tasks demonstrate significant improvements over strong baselines.

Multi-label classification is a practical yet challenging task in machine learning related fields, since it requires the prediction of more than one label category for each input instance. We propose a novel deep neural networks (DNN) based model, Canonical Correlated AutoEncoder (C2AE), for solving this task. Aiming at better relating feature and label domain data for improved classification, we uniquely perform joint feature and label embedding by deriving a deep latent space, followed by the introduction of label-correlation sensitive loss function for recovering the predicted label outputs. Our C2AE is achieved by integrating the DNN architectures of canonical correlation analysis and autoencoder, which allows end-to-end learning and prediction with the ability to exploit label dependency. Moreover, our C2AE can be easily extended to address the learning problem with missing labels. Our experiments on multiple datasets with different scales confirm the effectiveness and robustness of our proposed method, which is shown to perform favorably against state-of-the-art methods for multi-label classification.

Model reuse attempts to construct a model by utilizing existing available models, mostly trained for other tasks, rather than building a model from scratch. It is helpful to reduce the time cost, data amount, and expertise required. Deep learning has achieved great success in various tasks involving images, voices and videos. There are several studies have the sense of model reuse, by trying to reuse pre-trained deep networks architectures or deep model features to train a new deep model. They, however, neglect the fact that there are many other fixed models or features available. In this paper, we propose a more thorough model reuse scheme, FMR (Fixed Model Reuse). FMR utilizes the learning power of deep models to implicitly grab the useful discriminative information from fixed model/features that have been widely used in general tasks. We firstly arrange the convolution layers of a deep network and the provided fixed model/features in parallel, fully connecting to the output layer nodes. Then, the dependencies between the output layer nodes and the fixed model/features are knockdown such that only the raw feature inputs are needed when the model is being used for testing, though the helpful information in the fixed model/features have already been incorporated into the model. On one hand, by the FMR scheme, the required amount of training data can be significantly reduced because of the reuse of fixed model/features. On the other hand, the fixed model/features are not explicitly used in testing, and thus, the scheme can be quite useful in applications where the fixed model/features are protected by patents or commercial secrets. Experiments on five real-world datasets validate the effectiveness of FMR compared with state-of-the-art deep methods.

Link prediction is a fundamental task in such areas as social network analysis, information retrieval, and bioinformatics. Usually link prediction methods use the link structures or node attributes as the sources of information. Recently, the relational topic model (RTM) and its variants have been proposed as hybrid methods that jointly model both sources of information and achieve very promising accuracy. However, the representations (features) learned by them are still not effective enough to represent the nodes (items). To address this problem, we generalize recent advances in deep learning from solely modeling i.i.d. sequences of attributes to jointly modeling graphs and non-i.i.d. sequences of attributes. Specifically, we follow the Bayesian deep learning framework and devise a hierarchical Bayesian model, called relational deep learning (RDL), to jointly model high-dimensional node attributes and link structures with layers of latent variables. Due to the multiple nonlinear transformations in RDL, standard variational inference is not applicable. We propose to utilize the product of Gaussians (PoG) structure in RDL to relate the inferences on different variables and derive a generalized variational inference algorithm for learning the variables and predicting the links. Experiments on three real-world datasets show that RDL works surprisingly well and significantly outperforms the state of the art.