While mining topics in a document collection, in order to capture the relationships between words and further improve the effectiveness of discovered topics, this paper proposed a feedback recurrent neural network-based topic model. We represented each word as a one-hot vector and embedded each document into a low-dimensional vector space. During the process of document embedding, we applied th...

The automatic transcription process of spoken document results in several word errors, especially when very noisy conditions are encountered. Document representations based on neural embedding frameworks have recently shown significant improvements in different Spoken and Natural Language Understanding tasks such as denoising and filtering. Nonetheless, these methods mainly need clean represent...

Recently, doc2vec has achieved excellent results in different tasks (Lau and Baldwin, 2016). In this paper, we present a context aware variant of doc2vec. We introduce a novel weight estimating mechanism that generates weights for each word occurrence according to its contribution in the context, using deep neural networks. Our context aware model can achieve similar results compared to doc2vec...

Topic modeling is an unsupervised learning task that discovers the hidden topics in a collection of documents. In turn, discovered can be used for summarizing, organizing, and understanding documents collection. Most existing techniques topic are derivatives Latent Dirichlet Allocation which uses bag-of-word assumption However, bag-of-words models completely dismiss relationships between words....

The character vocabulary can be very large in non-alphabetic languages such as Chinese and Japanese, which makes neural network models huge to process such languages. We explored a model for sentiment classification that takes the embeddings of the radicals of the Chinese characters, i.e, hanzi of Chinese and kanji of Japanese. Our model is composed of a CNN word feature encoder and a bi-direct...

Neural network methods have achieved promising results for sentiment classification of text. However, these models only use semantics of texts, while ignoring users who express the sentiment and products which are evaluated, both of which have great influences on interpreting the sentiment of text. In this paper, we address this issue by incorporating userand productlevel information into a neu...

Recent work exhibited that distributed word representations are good at capturing linguistic regularities in language. This allows vector-oriented reasoning based on simple linear algebra between words. Since many different methods have been proposed for learning document representations, it is natural to ask whether there is also linear structure in these learned representations to allow simil...

Data representation is a fundamental task in machine learning. The representation of data affects the performance of the whole machine learning system. In a long history, the representation of data is done by feature engineering, and researchers aim at designing better features for specific tasks. Recently, the rapid development of deep learning and representation learning has brought new inspi...