Abstract We propose a method that uses neural embeddings to improve the performance of any given LDA-style topic model. Our method, called embedding allocation (NEA), deconstructs models (LDA or otherwise) into interpretable vector-space words, topics, documents, authors, and so on, by learning mimic demonstrate NEA improves coherence scores original model smoothing out noisy topics when number...

Word embeddings have become widelyused in document analysis. While a large number of models for mapping words to vector spaces have been developed, it remains undetermined how much net gain can be achieved over traditional approaches based on bag-of-words. In this paper, we propose a new document clustering approach by combining any word embedding with a state-of-the-art algorithm for clusterin...

This paper proposes an incremental learning strategy for neural word embedding methods, such as SkipGrams and Global Vectors. Since our method iteratively generates embedding vectors one dimension at a time, obtained vectors equip a unique property. Namely, any right-truncated vector matches the solution of the corresponding lower-dimensional embedding. Therefore, a single embedding vector can ...

The paper deals with text document retrieval from the given document collection by using neural networks, namely cascade neural network, linear and nonlinear Hebbian neural networks and linear autoassociative neural network. With using neural networks it is possible to reduce the dimension of the document search space with preserving the highest retrieval accuracy.

Most word embedding models typically represent each word using a single vector, which makes these models indiscriminative for ubiquitous homonymy and polysemy. In order to enhance discriminativeness, we employ latent topic models to assign topics for each word in the text corpus, and learn topical word embeddings (TWE) based on both words and their topics. In this way, contextual word embedding...

In this study, we consider a summarization method using the document level similarity based on embeddings, or distributed representations of words, where we assume that an embedding of each word can represent its “meaning.” We formalize our task as the problem of maximizing a submodular function defined by the negative summation of the nearest neighbors’ distances on embedding distributions, ea...

Electronic documents, similarly as printed documents, need to be secured by adding some specific features that allow efficient copyright protection, authentication, document tracking or investigation of counterfeiting and forgeries. Microsoft Word is one of the most popular word processors, and several methods exist for embedding data specially in documents produced by it. We present a new type...