DialoGPT project header - chat boxes on a dark purple background

DialoGPT

成立时间：November 1, 2019

新闻与深度文章

Diagram showing GODEL’s architecture. The environment of the dialog system consists of both structured and unstructured content, which it uses to retrieve information. This source content, which we term “grounding,” is updated and repeatedly used by GODEL to produce a new response after each user input.
微软研究院博客

| Baolin Peng, Michel Galley, Lars Liden, Chris Brockett, Zhou Yu, 和 Jianfeng Gao

They make restaurant recommendations, help us pay bills, and remind us of appointments. Many people have come to rely on virtual assistants and chatbots to perform a wide range of routine tasks. But what if a single dialog agent, the…

simulated aerial drone navigating course
微软研究院博客

“This is a game changer for the big data community. Initiatives like Microsoft Research Open Data reduce barriers to data sharing and encourage reproducibility by leveraging the power of cloud computing” —Sam Madden, Professor, Massachusetts Institute of Technology An open…

新闻报道 | InfoQ

Microsoft Research's Natural Language Processing Group released the dialogue generative pre-trained transformer (DialoGPT), a pre-trained deep-learning natural language processing (NLP) model for automatic conversation response generation. The model was trained on over 147M dialogues and achieves state-of-the-art results on several benchmarks.