Text clustering and classification are two main tasks of text mining. Feature selection plays the key role in the quality of the clustering and classification results. Although word-based features such as term frequency-inverse document frequency (TF-IDF) vectors have been widely used in different applications, their shortcoming in capturing semantic concepts of text motivated researches to use...

We propose a new model for unsupervised document embedding. Existing approaches either require complex inference or use recurrent neural networks that are difficult to parallelize. We take a different route and use recent advances in language modeling to develop a convolutional neural network embedding model. This allows us to train deeper architectures that are fully parallelizable. Stacking l...

We introduce Deep Semantic Embedding (DSE), a supervised learning algorithm which computes semantic representation for text documents by respecting their similarity to a given query. Unlike other methods that use singlelayer learning machines, DSE maps word inputs into a lowdimensional semantic space with deep neural network, and achieves a highly nonlinear embedding to model the human percepti...

This paper investigates the popular neural word embedding method Word2vec as a source of evidence in document ranking. In contrast to NLP applications of word2vec, which tend to use only the input embeddings, we retain both the input and the output embeddings, allowing us to calculate a different word similarity that may be more suitable for document ranking. We map the query words into the inp...

We describe a portable system for e cient semantic indexing of documents via neural networks with dynamic supervised feedback. We initially represent each document as a modified TF-IDF sparse vector and then apply a learned mapping to a compact embedding space. This mapping is produced by a shallow neural network which learns a latent representation for the textual graph linking words to nearby...

A fundamental goal of search engines is to identify, given a query, documents that have relevant text. This is intrinsically difficult because the query and the document may use different vocabulary, or the document may contain query words without being relevant. We investigate neural word embeddings as a source of evidence in document ranking. We train a word2vec embedding model on a large unl...

We present StarSpace, a general-purpose neural embedding model that can solve a wide variety of problems: labeling tasks such as text classification, ranking tasks such as information retrieval/web search, collaborative filtering-based or content-based recommendation, embedding of multirelational graphs, and learning word, sentence or document level embeddings. In each case the model works by e...