Text classification in general is a well studied area. However, classifying short and noisy text remains challenging. Feature sparsity is a major issue. The quality of document representation here has a great impact on the classification accuracy. Existing methods represent text using bag-of-word model, with TFIDF or other weighting schemes. Recently word embedding and even document embedding a...

At present, depression is the main reason for suicidal death. Depression also causes different kinds of diseases. Nowadays, people are deeply involved in social media and like to share their feelings on media. So, it becomes easy analyze through In this paper, a combination two CNN (Convolutional Neural Network) LSTM (Long Short-Term Memory) models has been proposed make hybrid CNN-LSTM model, ...

In this work we leverage recent advances in context-sensitive language models to improve the task of query expansion. Contextualized word representation models, such as ELMo and BERT, are rapidly replacing static embedding models. We propose a new model, Embeddings for Query Expansion (CEQE), that utilizes query-focused contextualized vectors. study behavior contextual representations generated...

Text classification is a fundamental task in NLP applications. Most existing work relied on either explicit or implicit text representation to address this problem. While these techniques work well for sentences, they can not easily be applied to short text because of its shortness and sparsity. In this paper, we propose a framework based on convolutional neural networks that combines explicit ...

We demonstrate the use of neural networks to model and analyze time series of nonlinear dynamical systems. Based on recent results concerning the embedding of attractors from scalar time series, we use the neural models to estimate the embedding dimension and the nonnegative Lyapunov exponents of the system.

Printer identification based on printed documents can provide forensic information to protect copyright and verify authenticity. In addition to intrinsic features (intrinsic signatures) of the printer, modulating the printing process to embed specific signature (extrinsic signatures) will further extend the encoding capacity. In this paper we describe the use of laser modulation in electrophoto...

Information hiding techniques allow a player to hide secret information in some innocent-looking document. In this paper we present a novel approach to information hiding. We investigate the possibility of embedding information using the intrinsic entropy of some classes of cover-documents. In particular we provide algorithms for embedding any binary string in an image mosaic (i.e. an image con...

We introduce Gaussian Process Topic Models (GPTMs), a new family of topic models which can leverage a kernel among documents while extracting correlated topics. GPTMs can be considered a systematic generalization of the Correlated Topic Models (CTMs) using ideas from Gaussian Process (GP) based embedding. Since GPTMs work with both a topic covariance matrix and a document kernel matrix, learnin...