DeepAI AI Chat
Log In Sign Up

SHAPED: Shared-Private Encoder-Decoder for Text Style Adaptation

by   Ye Zhang, et al.
The University of Texas at Austin

Supervised training of abstractive language generation models results in learning conditional probabilities over language sequences based on the supervised training signal. When the training signal contains a variety of writing styles, such models may end up learning an 'average' style that is directly influenced by the training data make-up and cannot be controlled by the needs of an application. We describe a family of model architectures capable of capturing both generic language characteristics via shared model parameters, as well as particular style characteristics via private model parameters. Such models are able to generate language according to a specific learned style, while still taking advantage of their power to model generic language phenomena. Furthermore, we describe an extension that uses a mixture of output distributions from all learned styles to perform on-the fly style adaptation based on the textual input alone. Experimentally, we find that the proposed models consistently outperform models that encapsulate single-style or average-style language generation capabilities.


Multi-dimensional Style Transfer for Partially Annotated Data using Language Models as Discriminators

Style transfer has been widely explored in natural language generation w...

Separating Style and Content for Generalized Style Transfer

Neural style transfer has drawn broad attention in recent years. However...

Steering Output Style and Topic in Neural Response Generation

We propose simple and flexible training and decoding methods for influen...

Audience-Centric Natural Language Generation via Style Infusion

Adopting contextually appropriate, audience-tailored linguistic styles i...

Towards Writing Style Adaptation in Handwriting Recognition

One of the challenges of handwriting recognition is to transcribe a larg...

ByGPT5: End-to-End Style-conditioned Poetry Generation with Token-free Language Models

State-of-the-art poetry generation systems are often complex. They eithe...

Chinese Poetry Generation with Flexible Styles

Research has shown that sequence-to-sequence neural models, particularly...