Despite the vast amount of research related to Chinese typo detection, we still lack a publicly available benchmark dataset for evaluation. Furthermore, no precise evaluation schema for Chinese typo detection has been defined. In response to these problems: (1) we release a benchmark dataset to assist research on Chinese typo correction; (2) we present an evaluation schema which was adopted in our NLPTEA 2017 Shared Task on Chinese Spelling Check; and (3) we report new improvements to our Chinese typo detection system ACT.

Heterogeneous Transfer Learning (HTL) algorithms leverage knowledge from a heterogeneous source domain to perform a task in a target domain. We present a novel HTL algorithm that works even where there are no shared features, instance correspondences and further, the two domains do not have identical labels. We utilize the label relationships via web-distance to align the data of the domains in the projected space, while preserving the structure of the original data.

We propose a method to generate explainable recommendation rules on cross-domain problems. Our two main contributions are: i) using relational learning to generate the rules which are able to explain clearly why the items were recommended to the particular user, ii) using the user's preferences of items on different domains and item attributes to generate novel or unexpected recommendations for the user. To illustrate that our method is indeed feasible and applicable, we conducted experiments on music and movie domains.

Support Vector Machines (SVMs) are popular for many machine learning tasks. With rapid growth of dataset size, the high cost of training limits the wide use of SVMs. Several SVM implementations on GPUs have been proposed to accelerate SVMs. However, they support only classification (SVC) or regression (SVR). In this work, we propose a simple and effective SVM training algorithm on GPUs which can be used for SVC, SVR and one-class SVM. Initial experiments show that our implementation outperforms existing ones. We are in the process of encapsulating our algorithm into an easy-to-use library which has Python, R and MATLAB interfaces.

Inspired by the Bayesian brain hypothesis and deep learning, we develop a Bayesian autoencoder, a method of constructing recognition systems using a Bayesian network. We construct hierarchical Bayesian networks based on feature extraction and implement pooling to achieve invariance within a Bayesian network framework. The constructed networks propagate information bidirectionally between layers. We expect they will be able to achieve brain-like recognition using local features and global information such as their environments.

In this paper, we propose an adversarial process for abstractive text summarization, in which we simultaneously train a generative model G and a discriminative model D. In particular, we build the generator G as an agent of reinforcement learning, which takes the raw text as input and predicts the abstractive summarization. We also build a discriminator which attempts to distinguish the generated summary from the ground truth summary. Extensive experiments demonstrate that our model achieves competitive ROUGE scores with the state-of-the-art methods on CNN/Daily Mail dataset. Qualitatively, we show that our model is able to generate more abstractive, readable and diverse summaries.

The minimum weighted vertex cover (MWVC) problem is a well known combinatorial optimization problem with important applications. This paper introduces a novel local search algorithm called NuMWVC for MWVC based on three ideas. First, four reduction rules are introduced during the initial construction phase. Second, the configuration checking with aspiration is proposed to reduce cycling problem. Moreover, a self-adaptive vertex removing strategy is proposed to save time.

Deep neural networks have gained great success recently for sentiment classification. However, these approaches do not fully exploit the linguistic knowledge. In this paper, we propose a novel sentiment lexicon enhanced attention-based LSTM (SLEA-LSTM) model to improve the performance of sentence-level sentiment classification. Our method successfully integrates sentiment lexicon into deep neural networks via single-head or multi-head attention mechanisms. We conduct extensive experiments on MR and SST datasets. The experimental results show that our model achieved comparable or better performance than the state-of-the-art methods.

They used character n-grams as sub-word units that were obtained The evolution of social media texts such as blogs, microblogs as convolutions over characters and passed to a LSTM layer (e.g., Twitter), WhatsApp, and informal chats have followed by softmax layer. For Hi-En code-mixed text (Joshi created many new opportunities for information access and et al. 2016) address the problem of rare or out-of-vocabulary language technologies, but have also presented many new words without any text normalization. In this paper, we propose challenges. This makes it one of the primary research areas a novel approach, without any need of explicit text normalization, of the present era. In social media, non-English speakers for creating sub-word units and a new hierarchical [according to statistics half of messages on Twitter arent model that efficiently learns sentence representations in English (Schroeder, Minocha, and Schneider 2010)] from these units.

Because of breakthroughs in the field of deep learning, the accuracy of image classification and multimedia recognition in Artificial Intelligence (AI) research has improved rapidly. In this study, the objective is the classification of high-dimensional data, and, in particular, the screening of very rare entries from a large population. In general, the initial Figure 2: Examples of skylines in multidimensional spaces set of vectors is divided into several groups by using a (left: two dimensions and right: three dimensions); the yellow clustering method, and an outlier detection method identifies and blue points denote the skyline and non-skyline distinct entries such as noise. Our focus is on a new cognitive points, respectively. Serendipiter (Guo et al. 2017) is a fast cell sorter that discovers Points that are not dominated by the other points are called very rare cells with atypical ability from an enormous skyline or pareto-optimal points.