Towards facilitating empathic conversations in online mental health support: A reinforcement learning approach
Online peer-to-peer support platforms enable conversations between millions of people who
seek and provide mental health support. If successful, web-based mental health …
seek and provide mental health support. If successful, web-based mental health …
Mix and match: Learning-free controllable text generation using energy language models
Recent work on controlled text generation has either required attribute-based fine-tuning of
the base language model (LM), or has restricted the parameterization of the attribute …
the base language model (LM), or has restricted the parameterization of the attribute …
Extracting latent steering vectors from pretrained language models
Prior work on controllable text generation has focused on learning how to control language
models through trainable decoding, smart-prompt design, or fine-tuning based on a desired …
models through trainable decoding, smart-prompt design, or fine-tuning based on a desired …
Towards practical plug-and-play diffusion models
Diffusion-based generative models have achieved remarkable success in image generation.
Their guidance formulation allows an external model to plug-and-play control the generation …
Their guidance formulation allows an external model to plug-and-play control the generation …
A distributional lens for multi-aspect controllable text generation
Multi-aspect controllable text generation is a more challenging and practical task than single-
aspect control. Existing methods achieve complex multi-aspect control by fusing multiple …
aspect control. Existing methods achieve complex multi-aspect control by fusing multiple …
Plug-and-blend: a framework for plug-and-play controllable story generation with sketches
Large pre-trained neural language models (LM) have very powerful text generation
capabilities. However, in practice, they are hard to control for creative purposes. We …
capabilities. However, in practice, they are hard to control for creative purposes. We …
Composable text controls in latent space with odes
Real-world text applications often involve composing a wide range of text control operations,
such as editing the text wrt an attribute, manipulating keywords and structure, and …
such as editing the text wrt an attribute, manipulating keywords and structure, and …
Sentence bottleneck autoencoders from transformer language models
Representation learning for text via pretraining a language model on a large corpus has
become a standard starting point for building NLP systems. This approach stands in contrast …
become a standard starting point for building NLP systems. This approach stands in contrast …
Transductive learning for unsupervised text style transfer
Unsupervised style transfer models are mainly based on an inductive learning approach,
which represents the style as embeddings, decoder parameters, or discriminator parameters …
which represents the style as embeddings, decoder parameters, or discriminator parameters …
Feature-aware conditional GAN for category text generation
Category text generation receives considerable attentions since it is beneficial for various
natural language processing tasks. Recently, the generative adversarial network (GAN) has …
natural language processing tasks. Recently, the generative adversarial network (GAN) has …