Wed Nov 09 2022
Tue Nov 08 2022

Self-conditioned Embedding Diffusion for Text Generation

Machine Learning
Natural Language Processing
Text Generation
Improved chatbot and customer service interactions
Efficient content creation

Proposes a continuous diffusion mechanism that operates on token embeddings, allowing to learn flexible and scalable diffusion models for text generation. Shows that their models generate samples comparable to those produced by standard autoregressive language models while being more efficient on accelerator hardware at inference time.

Can be used to improve text generation models for business operations such as chatbots, automated customer service, and content creation. Implementation of this method can result in faster and more efficient inference times.

Tell Your Story: Task-Oriented Dialogs for Interactive Content Creation

Machine Learning
Natural Language Processing
Content Creation
Enhanced content creation workflows
Improved user experiences

Introduces a new dataset C3 (Conversational Content Creation) consisting of 10k multi-turn dialogs conditioned on media montages simulated from a large media collection. Proposes task-oriented dialogs for montage creation as an interactive tool to seamlessly search, compile, and edit montages from a media collection.

Can be used to improve content creation workflows and enhance user experiences. The proposed method can help automate the manual and time-consuming process of montage creation and improve storytelling capabilities.

Mon Nov 07 2022
Thu Nov 03 2022
Wed Nov 02 2022
Tue Nov 01 2022