Neural network-based BOW models reveal that word-embedding vectors encode strong semantic regularities. However, such models are insensitive to word polarity. We show that, coupled with simple information such as word spellings, word-embedding vectors can preserve both semantic regularity and conceptual polarity without supervision. We then describe a nontrivial modification to the t-distributed stochastic neighbor embedding (t-SNE) algorithm that visualizes these semantic- and polarity-preserving vectors in reduced dimensions. On a real Facebook corpus, our experiments show significant improvement in t-SNE visualization as a result of the proposed modification.

Neural Machine Translation (NMT) is a new approach to machine translation that has made great progress in recent years. However, recent studies show that NMT generally produces fluent but inadequate translations (Tu et al. 2016b; 2016a; He et al. 2016; Tu et al. 2017). This is in contrast to conventional Statistical Machine Translation (SMT), which usually yields adequate but non-fluent translations. It is natural, therefore, to leverage the advantages of both models for better translations, and in this work we propose to incorporate SMT model into NMT framework. More specifically, at each decoding step, SMT offers additional recommendations of generated words based on the decoding information from NMT (e.g., the generated partial translation and attention history). Then we employ an auxiliary classifier to score the SMT recommendations and a gating function to combine the SMT recommendations with NMT generations, both of which are jointly trained within the NMT architecture in an end-to-end manner. Experimental results on Chinese-English translation show that the proposed approach achieves significant and consistent improvements over state-of-the-art NMT and SMT systems on multiple NIST test sets.

We propose a neural graphical model for parsing natural language sentences into their logical representations. The graphical model is based on hybrid tree structures that jointly represent both sentences and semantics. Learning and decoding are done using efficient dynamic programming algorithms. The model is trained under a discriminative setting, which allows us to incorporate a rich set of features. Hybrid tree structures have shown to achieve state-of-the-art results on standard semantic parsing datasets. In this work, we propose a novel model that incorporates a rich, nonlinear featurization by a feedforward neural network. The error signals are computed with respect to the conditional random fields (CRFs) objective using an inside-outside algorithm, which are then backpropagated to the neural network. We demonstrate that by combining the strengths of the exact global inference in the hybrid tree models and the power of neural networks to extract high level features, our model is able to achieve new state-of-the-art results on standard benchmark datasets across different languages.

Neural network language models (NNLMs) have attracted a lot of attention recently. In this paper, we present a training method that can incrementally train the hierarchical softmax function for NNMLs. We split the cost function to model old and update corpora separately, and factorize the objective function for the hierarchical softmax. Then we provide a new stochastic gradient based method to update all the word vectors and parameters, by comparing the old tree generated based on the old corpus and the new tree generated based on the combined (old and update) corpus. Theoretical analysis shows that the mean square error of the parameter vectors can be bounded by a function of the number of changed words related to the parameter node. Experimental results show that incremental training can save a lot of time. The smaller the update corpus is, the faster the update training process is, where an up to 30 times speedup has been achieved. We also use both word similarity/relatedness tasks and dependency parsing task as our benchmarks to evaluate the correctness of the updated word vectors.

One of the main goals of natural language processing (NLP) is synthetic understanding of natural language documents, especially reading comprehension (RC). An obstacle to the further development of RC systems is the absence of a synthetic methodology to analyze their performance. It is difficult to examine the performance of systems based solely on their results for tasks because the process of natural language understanding is complex. In order to tackle this problem, we propose in this paper a methodology inspired by unit testing in software engineering that enables the examination of RC systems from multiple aspects. Our methodology consists of three steps. First, we define a set of prerequisite skills for RC based on existing NLP tasks. We assume that RC capability can be divided into these skills. Second, we manually annotate a dataset for an RC task with information regarding the skills needed to answer each question. Finally, we analyze the performance of RC systems for each skill based on the annotation. The last two steps highlight two aspects: the characteristics of the dataset, and the weaknesses in and differences among RC systems. We tested the effectiveness of our methodology by annotating the Machine Comprehension Test (MCTest) dataset and analyzing four existing systems (including a neural system) on it. The results of the annotations showed that answering questions requires a combination of skills, and clarified the kinds of capabilities that systems need to understand natural language. We conclude that the set of prerequisite skills we define are promising for the decomposition and analysis of RC.

Developed so far, multi-document summarization has reached its bottleneck due to the lack of sufficient training data and diverse categories of documents. Text classification just makes up for these deficiencies. In this paper, we propose a novel summarization system called TCSum, which leverages plentiful text classification data to improve the performance of multi-document summarization. TCSum projects documents onto distributed representations which act as a bridge between text classification and summarization. It also utilizes the classification results to produce summaries of different styles. Extensive experiments on DUC generic multi-document summarization datasets show that, TCSum can achieve the state-of-the-art performance without using any hand-crafted features and has the capability to catch the variations of summary styles with respect to different text categories.

This paper studies a criteria-based mechanism for nurturing and enhancing agents' group-benefiting individual efforts whenever the agents are self-interested. The idea is that only those agents that meet the criteria get to benefit from the group effort, giving an incentive to contribute even when it is otherwise individually irrational. Specifically, the paper provides a comprehensive equilibrium analysis of a threshold-based criteria mechanism for the common cooperative information gathering application, where the criteria is set such that only those whose contribution to the group is above some pre-specified threshold can benefit from the contributions of others. The analysis results in a closed form solution for the strategies to be used in equilibrium and facilitates the numerical investigation of different model properties as well as a comparison to the dual mechanism according to only an agent whose contribution is below the specified threshold gets to benefit from the contributions of others. One important contribution enabled through the analysis provided is in showing that, counter-intuitively, for some settings the use of the above-threshold criteria is outperformed by the use of the below-threshold criteria as far as collective and individual performance is concerned.

Many machine learning models, such as logistic regression (LR) and support vector machine (SVM), can be formulated as composite optimization problems. Recently, many distributed stochastic optimization (DSO) methods have been proposed to solve the large-scale composite optimization problems, which have shown better performance than traditional batch methods. However, most of these DSO methods might not be scalable enough. In this paper, we propose a novel DSO method, called scalable composite optimization for learning (SCOPE), and implement it on the fault-tolerant distributed platform Spark. SCOPE is both computation-efficient and communication-efficient. Theoretical analysis shows that SCOPE is convergent with linear convergence rate when the objective function is strongly convex. Furthermore, empirical results on real datasets show that SCOPE can outperform other state-of-the-art distributed learning methods on Spark, including both batch learning methods and DSO methods.

Learning multiple heterogeneous features from different data sources is challenging. One research topic is how to exploit and utilize the correlations among various features across multiple views with the aim of improving the performance of learning tasks, such as classification. In this paper, we propose a new multi-view feature learning algorithm that simultaneously analyzes features from different views. Compared to most of the existing subspace learning methods that only focus on exploiting a shared latent subspace, our algorithm not only learns individual information in each view but also captures feature correlations among multiple views by learning a shared component. By assuming that such a component is shared by all views, we simultaneously exploit the shared component and individual information of each view in a batch mode. Since the objective function is non-smooth and difficult to solve, we propose an efficient iterative algorithm for optimization with guaranteed convergence. Extensive experiments are conducted on several benchmark datasets. The results demonstrate that our proposed algorithm performs better than all the compared multi-view learning algorithms.

The k-fold cross-validation is commonly used to evaluate the effectiveness of SVMs with the selected hyper-parameters. It is known that the SVM k-fold cross-validation is expensive, since it requires training k SVMs. However, little work has explored reusing the h-th SVM for training the (h+1)-th SVM for improving the efficiency of k-fold cross-validation. In this paper, we propose three algorithms that reuse the h-th SVM for improving the efficiency of training the (h+1)-th SVM. Our key idea is to efficiently identify the support vectors and to accurately estimate their associated weights (also called alpha values) of the next SVM by using the previous SVM. Our experimental results show that our algorithms are several times faster than the k-fold cross-validation which does not make use of the previously trained SVM. Moreover, our algorithms produce the same results (hence same accuracy) as the k-fold cross-validation which does not make use of the previously trained SVM.