Ненаблюдаемый перенос стиля текста
Related Papers
Cycle-Consistent Adversarial Autoencoders for Unsupervised Text Style Transfer
AbstractUnsupervised text style transfer is full of challenges due to the lack of parallel data and difficulties in content preservation. In this paper, we propose a novel neural approach to …...
How Positive Are You: Text Style Transfer using Adaptive Style Embedding
AbstractThe prevalent approach for unsupervised text style transfer is disentanglement between content and style. However, it is difficult to completely separate style information from the content. Other approaches allow the …...
Collaborative Learning of Bidirectional Decoders for Unsupervised Text Style Transfer
AbstractUnsupervised text style transfer aims to alter the underlying style of the text to a desired value while keeping its style-independent semantics, without the support of parallel training corpora. Existing …...
Don’t Take It Literally: An Edit-Invariant Sequence Loss for Text Generation
AbstractNeural text generation models are typically trained by maximizing log-likelihood with the sequence cross entropy (CE) loss, which encourages an exact token-by-token match between a target sequence with a generated …...
RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning
AbstractPrompting has shown impressive success in enabling large pre-trained language models (LMs) to perform diverse NLP tasks, especially with only few downstream data. Automatically finding the optimal prompt for each …...