Adversarial Training Methods For Semi-Supervised Text Classification

Introduction This paper is the first work that applies adversarial training and virtual adversarial training to sequence models, and it greatly improved text classification tasks. In applying the adversarial training, this paper adopts distributed word representation, or word embedding, as the input, rather than the traditional one-hot representation. The reason lies in the fact that […]

Continue reading


Word2vec: Google’s New Leap Forward on the Vectorized Representation of Words

Introduction Word2vec is an open source tool developed by a group of Google researchers led by Tomas Mikolov in 2013. It describes several efficient ways to represent words as M-dimensional real vectors, also known as word embedding, which is of great importance in many natural language processing applications. Word2vec also expresses the quality of the […]

Continue reading