A Simple Language Model based on PMI Matrix Approximations

Abstract: In this study, we introduce a new approach for learning LLMs by training them to estimate word-context pointwise mutual information (PMI), and then deriving the desired conditional probabilities from PMI at test time. Specifically, we show that with minor modifications to word2vec's algorithm, we get principled LLMs that are closely related to the well-established Noise Contrastive Estimation (NCE) based LLMs. A compelling aspect of our approach is that our models are trained with the same simple negative sampling objective function that is commonly used in word2vec to learn word embeddings.