Document level sentiment classification remains a challenge: encoding the intrinsic relations between sentences in the semantic meaning of a document. To address this, we introduce a neural network model to learn vector-based document representation in a unified, bottom-up fashion. The model first learns sentence representation with convolutional neural network or long short-term memory. Afterw...

Nowadays, neural networks play an important role in the task of relation classification. In this paper, we propose a novel attention-based convolutional neural network architecture for this task. Our model makes full use of word embedding, part-of-speech tag embedding and position embedding information. Word level attention mechanism is able to better determine which parts of the sentence are m...

Distributional models that learn rich semantic word representations are a success story of recent NLP research. However, developing models that learn useful representations of phrases and sentences has proved far harder. We propose using the definitions found in everyday dictionaries as a means of bridging this gap between lexical and phrasal semantics. Neural language embedding models can be e...

Handwriting recognition has been one of the active and challenging research areas in the field of image processing and pattern recognition. It has numerous applications that includes, reading aid for blind, bank cheques and conversion of any hand written document into structural text form. Neural Network (NN) with its inherent learning ability offers promising solutions for handwritten characte...

Keyphrases: Intrinsic and extrinsic evaluations. Effect of hyperparameters on analogy evaluation tasks. Correlation of human judgment with word vector distances. Dealing with ambiguity in word using contexts. Window classification. This set of notes extends our discussion of word vectors (interchangeably called word embeddings) by seeing how they can be evaluated intrinsically and extrinsically...

This study examined the use of neural word embeddings for clinical abbreviation disambiguation, a special case of word sense disambiguation (WSD). We investigated three different methods for deriving word embeddings from a large unlabeled clinical corpus: one existing method called Surrounding based embedding feature (SBE), and two newly developed methods: Left-Right surrounding based embedding...

Most of spectral embedding algorithms such as Isomap, LLE and Laplacian Eigenmap only give map on training samples. One main problem of these methods is to find the embedding of new samples, which is known as the outof-sample problem of spectral embedding. In this paper, we propose a neural network based method to solve this problem. Neural network is used to train and perform both the forward ...

The Fisher information metric is an important foundation of information geometry, wherein it allows us to approximate the local geometry of a probability distribution. Recurrent neural networks such as the Sequence-to-Sequence (Seq2Seq) networks that have lately been used to yield state-of-the-art performance on speech translation or image captioning have so far ignored the geometry of the late...

We develop a Multimodal Spatiotemporal Neural Fusion network for MTL (MSNF-MTCL) to predict 5 important students' retention risks: future dropout, next semester type of duration dropout and cause dropout. First, we general purpose multi-modal neural fusion model MSNF learning academic information representation by fusing spatial temporal unstructured advising notes with spatiotemporal structure...

numerical analyses have shown that successful flow simulations and the accuracy of solution noticeably depend on the number of nodes used in computational meshing. a suitable meshing should have the capability of adapting with main flow parameters. because the number of total nodes that can be used in numerical simulation is limited, making such grid for complex flows is almost difficult, if it...