Recently, several works in the domain of natural language processing presented successful methods for word embedding. Among them, the Skip-Gram (SG) with negative sampling, known also as word2vec, advanced the stateof-the-art of various linguistics tasks. In this paper, we propose a scalable Bayesian neural word embedding algorithm that can be beneficial to general item similarity tasks as well...

In this paper we present Document analysis and classification system to segment and classify contents of Arabic document images. This system includes preprocessing, document segmentation, feature extraction and document classification. A document image is enhanced in the preprocessing by removing noise, binarization, and detecting and correcting image skew. In document segmentation, an algorith...

This paper proposes word clustering using word embedding. We used a neural net-based continuous skip-gram method for generating word embedding in continuous space. The proposed word clustering method represents each word in the vector space using a neural network. The K-means clustering method partitions word embedding into predetermined K-word

In the context of natural language processing, representation learning has emerged as a newly active research subject because of its excellent performance in many applications. Learning representations of words is a pioneering study in this school of research. However, paragraph (or sentence and document) embedding learning is more suitable/reasonable for some tasks, such as sentiment classific...

We propose a novel method that exploits visual information of ideograms and logograms in analyzing Japanese review documents. Our method first converts font images of Japanese characters into character embeddings using convolutional neural networks. It then constructs document embeddings from the character embeddings based on Hierarchical Attention Networks, which represent the documents based ...

In this paper we study the problem of answering cloze-style questions over documents. Our model, the Gated-Attention (GA) Reader1, integrates a multi-hop architecture with a novel attention mechanism, which is based on multiplicative interactions between the query embedding and the intermediate states of a recurrent neural network document reader. This enables the reader to build query-specific...

This paper presents a new semi-supervised framework with convolutional neural networks (CNNs) for text categorization. Unlike the previous approaches that rely on word embeddings, our method learns embeddings of small text regions from unlabeled data for integration into a supervised CNN. The proposed scheme for embedding learning is based on the idea of two-view semi-supervised learning, which...

In prediction-based reversible watermarking schemes, watermark bits are embedded in the prediction errors. An accurate prediction results in smaller prediction errors, more efficient embedding, and less distortion for the watermarked image. In this paper, an accurate prediction is made using artificial neural networks. Before the embedding operation, 2 neural networks are trained by the pixel v...