Xiujun Li

Deep Dyna-Q: Integrating Planning for Task-Completion Dialogue Policy Learning

2018

Training a task-completion dialogue agent via reinforcement learning (RL) is costly because it requires many interactions with real users. One common alternative is to use a user simulator. However, a user simulator usually lacks the …

End-to-End Joint Learning of Natural Language Understanding and Dialogue Manager

2016 · arXiv (Cornell University)

Natural language understanding and dialogue policy learning are both essential in conversational systems that predict the next system actions in response to a current user utterance. Conventional approaches aggregate separate models of natural language understanding …

Towards End-to-End Reinforcement Learning of Dialogue Agents for Information Access

2017

Bhuwan Dhingra, Lihong Li, Xiujun Li, Jianfeng Gao, Yun-Nung Chen, Faisal Ahmed, Li Deng. Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2017.

Multimodal Autoregressive Pre-training of Large Vision Encoders

2024 · arXiv (Cornell University)

We introduce a novel method for pre-training of large-scale vision encoders. Building on recent advancements in autoregressive pre-training of vision models, we extend this framework to a multimodal setting, i.e., images and text. In this …

Optimus: Organizing Sentences via Pre-trained Modeling of a Latent Space

2020

When trained effectively, the Variational Autoencoder (VAE) In this paper, we propose the first large-scale language VAE model OPTIMUS 1 . A universal latent embedding space for sentences is first pre-trained on large text corpus, …