Learning word embeddings on large unlabeled corpus has been shown to be successful in improving many natural language tasks.
Our model family consists of a latent-variable generative model and a discriminative labeler.
In this study, we improve grammatical error detection by learning word embeddings that consider grammaticality and error patterns.
In this paper, we propose a low-rank coordinate descent approach to structured semidefinite programming with diagonal constraints.
We present a pointwise mutual information (PMI)-based approach to formalize paraphrasability and propose a variant of PMI, called MIPA, for the paraphrase acquisition.
General-purpose pre-trained word embeddings have become a mainstay of natural language processing, and more recently, methods have been proposed to encode external knowledge into word embeddings to benefit specific downstream tasks.