We propose an unsupervised method to obtain cross-lingual embeddings without any parallel data or pre-trained word embeddings. The proposed model, which we call multilingual neural language models, takes sentences of multiple languages as an input. The proposed model contains bidirectional LSTMs that perform as forward and backward language models, and these networks are shared among all the languages. The other parameters, i.e. word embeddings and linear transformation between hidden states and outputs, are specific to each language. The shared LSTMs can capture the common sentence structure among all languages. Accordingly, word embeddings of each language are mapped into a common latent space, making it possible to measure the similarity of words across multiple languages. We evaluate the quality of the cross-lingual word embeddings on a word alignment task. Our experiments demonstrate that our model can obtain cross-lingual embeddings of much higher quality than existing unsupervised models when only a small amount of monolingual data (i.e.

MixUp (Zhang et al. 2017), a data augmentation approach through mixing random samples, has been shown to be able to significantly improve the predictive accuracy of the current art of deep neural networks. The power of MixUp, however, is mostly established empirically and its working and effectiveness have not been explained in any depth. In this paper, we develop a theoretical understanding for MixUp as a form of out-of-manifold regularization, which constrains the model on the input space beyond the data manifold. This analytical study also enables us to identify MixUp's limitation caused by manifold intrusion, where synthetic samples collide with real examples of the manifold. Such intrusion gives rise to over regularization and thereby under-fitting. To address this issue, we further propose a novel regularizer, where mixing policies are adaptively learned from the data and a manifold intrusion loss is embraced as to avoid collision with the data manifold. We empirically show, using several benchmark datasets, our regularizer's effectiveness in terms of over regularization avoiding and accuracy improvement upon current art of deep classification models and MixUp.

Monte Carlo Tree Search (MCTS) is particularly adapted to domains where the potential actions can be represented as a tree of sequential decisions. For an effective action selection, MCTS performs many simulations to build a reliable tree representation of the decision space. As such, a bottleneck to MCTS appears when enough simulations cannot be performed between action selections. This is particularly highlighted in continuously running tasks, for which the time available to perform simulations between actions tends to be limited due to the environment's state constantly changing. In this paper, we present an approach that takes advantage of the anytime characteristic of MCTS to increase the simulation time when allowed. Our approach is to effectively balance the prospect of selecting an action with the time that can be spared to perform MCTS simulations before the next action selection. For that, we considered the simulation time as a decision variable to be selected alongside an action. We extended the Hierarchical Optimistic Optimization applied to Tree (HOOT) method to adapt our approach to environments with a continuous decision space. We evaluated our approach for environments with a continuous decision space through OpenAI gym's Pendulum and Continuous Mountain Car environments and for environments with discrete action space through the arcade learning environment (ALE) platform. The evaluation results show that, with variable simulation times, the proposed approach outperforms the conventional MCTS in the evaluated continuous decision space tasks and improves the performance of MCTS in most of the ALE tasks.

Training a neural network for a classification task typically assumes that the data to train are given from the beginning. However, in the real world, additional data accumulate gradually and the model requires additional training without accessing the old training data. This usually leads to the catastrophic forgetting problem which is inevitable for the traditional training methodology of neural networks. In this paper, we propose a memory-based continual learning method that is able to learn additional tasks while retaining the performance of previously learned tasks. Composed of two complementary networks, the Hippocampus-Net (H-Net) and the Cortex-Net (C-Net), our model estimates the index of the corresponding task for an input sample and utilizes a particular portion of itself with the estimated index. The C-Net guarantees no degradation in the performance of the previously learned tasks and the H-Net shows high confidence in finding the origin of an input sample.

We propose a hierarchically structured reinforcement learning approach to address the challenges of planning for generating coherentmulti-sentence stories for the visual storytelling task. Within our framework, the task of generating a story given a sequence of images is divided across a two-level hierarchical decoder.The high-level decoder constructs a plan by generating a semantic concept (i.e., topic) for each image in sequence. The low-level decoder generates a sentence for each image using a semantic compositional network, which effectively grounds the sentence generation conditioned on the topic. The two decoders are jointly trained end-to-end using reinforcement learning. We evaluate our model on the visual storytelling (VIST) dataset. Empirical results from both automatic and human evaluations demonstrate that the proposed hierarchicallystructured reinforced training achieves significantly better performance compared to a strong flat deep reinforcement learning baseline.

Abstract--Increasingly fast development and update cycle of online course contents, and diverse demographics of students in each online classroom, make student performance prediction in real-time (before the course finishes) an interesting topic for both industrial research and practical needs. In that, we tackle the problem of real-time student performance prediction with ongoing courses in a domain adaptation framework, which is a system trained on students' labeled outcome from one previous coursework but is meant to be deployed on another. In particular, we first review recently-developed GritNet architecture [1] which is the current state of the art for student performance prediction problem, and introduce a new unsupervised domain adaptation method to transfer a GritNet trained on a past course to a new course without any (students' outcome) label. Our results for real Udacity students' graduation predictions show that the GritNet not only generalizes well from one course to another across different Nanodegree programs, but enhances real-time predictions explicitly in the first few weeks when accurate predictions are most challenging. With the growing need for people to keep learning throughout their careers, massive open online course (MOOCs) companies, such as Udacity and Coursera, not only aggressively design new courses that are relevant (e.g., self-driving cars and flying cars) but refresh existing courses' content frequently to keep them up-to-date.

Despite that accelerating convolutional neural network (CNN) receives an increasing research focus, the save on resource consumption always comes with a decrease in accuracy. To both increase accuracy and decrease resource consumption, we explore an environment information, called class skew, which is easily available and exists widely in daily life. Since the class skew may switch as time goes, we bring up probability layer to utilize class skew without any overhead during the runtime. Further, we observe class skew dichotomy that some class skew may appear frequently in the future, called hot class skew, and others will never appear again or appear seldom, called cold class skew. Inspired by techniques from source code optimization, two modes, i.e., interpretation and compilation, are proposed. The interpretation mode pursues efficient adaption during runtime for cold class skew and the compilation mode aggressively optimize on hot ones for more efficient deployment in the future. Aggressive optimization is processed by class-specific pruning and provides extra benefit. Finally, we design a systematic framework, SECS, to dynamically detect class skew, processing interpretation and compilation, as well as select the most accurate architectures under the runtime resource budget. Extensive evaluations show that SECS can realize end-to-end classification speedups by a factor of 3x to 11x relative to state-of-the-art convolutional neural networks, at a higher accuracy.

Recent neural models for data-to-text generation are mostly based on data-driven end-to-end training over encoder-decoder networks. Even though the generated texts are mostly fluent and informative, they often generate descriptions that are not consistent with the input structured data. This is a critical issue especially in domains that require inference or calculations over raw data. In this paper, we attempt to improve the fidelity of neural data-to-text generation by utilizing pre-executed symbolic operations. We propose a framework called Operation-guided Attention-based sequence-to-sequence network (OpAtt), with a specifically designed gating mechanism as well as a quantization module for operation results to utilize information from pre-executed operations. Experiments on two sports datasets show our proposed method clearly improves the fidelity of the generated texts to the input structured data.

Nature language inference (NLI) task is a predictive task of determining the inference relationship of a pair of natural language sentences. With the increasing popularity of NLI, many state-of-the-art predictive models have been proposed with impressive performances. However, several works have noticed the statistical irregularities in the collected NLI data set that may result in an over-estimated performance of these models and proposed remedies. In this paper, we further investigate the statistical irregularities, what we refer as confounding factors, of the NLI data sets. With the belief that some NLI labels should preserve under swapping operations, we propose a simple yet effective way (swapping the two text fragments) of evaluating the NLI predictive models that naturally mitigate the observed problems. Further, we continue to train the predictive models with our swapping manner and propose to use the deviation of the model's evaluation performances under different percentages of training text fragments to be swapped to describe the robustness of a predictive model. Our evaluation metrics leads to some interesting understandings of recent published NLI methods. Finally, we also apply the swapping operation on NLI models to see the effectiveness of this straightforward method in mitigating the confounding factor problems in training generic sentence embeddings for other NLP transfer tasks.

Understanding and analyzing graphs is an essential topic that has been widely studied over the past decades. Many real world problems can be formulated as link predictions in graphs (Gehrke, Ginsparg, and Kleinberg 2003; Freeman 2000; Theocharidis et al. 2009; Goyal, Sapienza, and Ferrara 2018). For example, link prediction in an author collaboration network (Gehrke, Ginsparg, and Kleinberg 2003) can be used to predict potential future author collaboration. Similarly, new connections between proteins can be discovered using protein interaction networks (Pavlopoulos, Wegener, and Schneider 2008), and new friendships can be predicted using social networks (Wasserman and Faust 1994). Recent work on obtaining such predictions use graph representation learning. These methods represent each node in the network with a fixed dimensional embedding, and map link prediction in the network space to a nearest neighbor search in the embedding space (Goyal and Ferrara 2018). It has been shown that such techniques can outperform traditional link prediction methods on graphs (Grover and Leskovec 2016; Ou et al. 2016a).