Semi-supervised Formality Style Transfer using Language Model Discriminator and Mutual Information Maximization
Kunal Chawla, Diyi Yang
Abstract
Formality style transfer is the task of converting informal sentences to grammaticallycorrect formal sentences, which can be used to improve performance of many downstream NLP tasks. In this work, we propose a semisupervised formality style transfer model that utilizes a language model-based discriminator to maximize the likelihood of the output sentence being formal, which allows us to use maximization of token-level conditional probabilities for training. We further propose to maximize mutual information between source and target styles as our training objective instead of maximizing the regular likelihood that often leads to repetitive and trivial generated responses. Experiments showed that our model outperformed previous state-of-theart baselines significantly in terms of both automated metrics and human judgement. We further generalized our model to unsupervised text style transfer task, and achieved significant improvements on two benchmark sentiment style transfer datasets.