Get our free extension to see links to code for papers anywhere online!

 Add to Chrome

 Add to Firefox

CatalyzeX Code Finder - Browser extension linking code for ML papers across the web! | Product Hunt Embed
Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks

May 18, 2020
Xiujun Li, Xi Yin, Chunyuan Li, Pengchuan Zhang, Xiaowei Hu, Lei Zhang, Lijuan Wang, Houdong Hu, Li Dong, Furu Wei, Yejin Choi, Jianfeng Gao

* Code and pre-trained models are released: https://github.com/microsoft/Oscar 

  Access Paper or Ask Questions

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

Apr 05, 2020
Chunyuan Li, Xiang Gao, Yuan Li, Xiujun Li, Baolin Peng, Yizhe Zhang, Jianfeng Gao


  Access Paper or Ask Questions

Multi-View Learning for Vision-and-Language Navigation

Mar 09, 2020
Qiaolin Xia, Xiujun Li, Chunyuan Li, Yonatan Bisk, Zhifang Sui, Jianfeng Gao, Yejin Choi, Noah A. Smith

* 16 pages, 8 figures 

  Access Paper or Ask Questions

Few-shot Natural Language Generation for Task-Oriented Dialog

Feb 27, 2020
Baolin Peng, Chenguang Zhu, Chunyuan Li, Xiujun Li, Jinchao Li, Michael Zeng, Jianfeng Gao

* Project website: https://aka.ms/scgpt ; Code and data: https://github.com/pengbaolin/SC-GPT 

  Access Paper or Ask Questions

Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-training

Feb 25, 2020
Weituo Hao, Chunyuan Li, Xiujun Li, Lawrence Carin, Jianfeng Gao

* To appear at CVPR 2020. The first two authors contributed equally to this manuscript. Code: https://github.com/weituo12321/PREVALENT 

  Access Paper or Ask Questions

Robust Navigation with Language Pretraining and Stochastic Sampling

Sep 05, 2019
Xiujun Li, Chunyuan Li, Qiaolin Xia, Yonatan Bisk, Asli Celikyilmaz, Jianfeng Gao, Noah Smith, Yejin Choi

* 8 pages, 4 figures, EMNLP 2019 

  Access Paper or Ask Questions

Budgeted Policy Learning for Task-Oriented Dialogue Systems

Jun 02, 2019
Zhirui Zhang, Xiujun Li, Jianfeng Gao, Enhong Chen

* 10 pages, 7 figures, ACL 2019 

  Access Paper or Ask Questions

ConvLab: Multi-Domain End-to-End Dialog System Platform

Apr 18, 2019
Sungjin Lee, Qi Zhu, Ryuichi Takanobu, Xiang Li, Yaoqin Zhang, Zheng Zhang, Jinchao Li, Baolin Peng, Xiujun Li, Minlie Huang, Jianfeng Gao


  Access Paper or Ask Questions

Tactical Rewind: Self-Correction via Backtracking in Vision-and-Language Navigation

Apr 02, 2019
Liyiming Ke, Xiujun Li, Yonatan Bisk, Ari Holtzman, Zhe Gan, Jingjing Liu, Jianfeng Gao, Yejin Choi, Siddhartha Srinivasa

* CVPR 2019 Oral, video demo: https://youtu.be/AD9TNohXoPA 

  Access Paper or Ask Questions

Switch-based Active Deep Dyna-Q: Efficient Adaptive Planning for Task-Completion Dialogue Policy Learning

Nov 19, 2018
Yuexin Wu, Xiujun Li, Jingjing Liu, Jianfeng Gao, Yiming Yang

* 8 pages, 9 figures, AAAI 2019 

  Access Paper or Ask Questions

Generating Informative and Diverse Conversational Responses via Adversarial Information Maximization

Nov 03, 2018
Yizhe Zhang, Michel Galley, Jianfeng Gao, Zhe Gan, Xiujun Li, Chris Brockett, Bill Dolan

* NIPS 2018 

  Access Paper or Ask Questions

A bird's-eye view on coherence, and a worm's-eye view on cohesion

Nov 01, 2018
Woon Sang Cho, Pengchuan Zhang, Yizhe Zhang, Xiujun Li, Michel Galley, Mengdi Wang, Jianfeng Gao


  Access Paper or Ask Questions

Subgoal Discovery for Hierarchical Dialogue Policy Learning

Sep 22, 2018
Da Tang, Xiujun Li, Jianfeng Gao, Chong Wang, Lihong Li, Tony Jebara

* 11 pages, 6 figures, EMNLP 2018 

  Access Paper or Ask Questions

Microsoft Dialogue Challenge: Building End-to-End Task-Completion Dialogue Systems

Sep 14, 2018
Xiujun Li, Yu Wang, Siqi Sun, Sarah Panda, Jingjing Liu, Jianfeng Gao

* SLT 2018 Special Session: http://www.slt2018.org/news/ 

  Access Paper or Ask Questions

Discriminative Deep Dyna-Q: Robust Planning for Dialogue Policy Learning

Sep 06, 2018
Shang-Yu Su, Xiujun Li, Jianfeng Gao, Jingjing Liu, Yun-Nung Chen

* 11 pages, 10 figures, EMNLP 2018 long paper 

  Access Paper or Ask Questions

Interactive Semantic Parsing for If-Then Recipes via Hierarchical Reinforcement Learning

Aug 21, 2018
Ziyu Yao, Xiujun Li, Jianfeng Gao, Brian Sadler, Huan Sun

* 13 pages, 2 figures 

  Access Paper or Ask Questions

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

May 23, 2018
Baolin Peng, Xiujun Li, Jianfeng Gao, Jingjing Liu, Kam-Fai Wong, Shang-Yu Su

* 11 pages, 8 figures, Accepted in ACL 2018 

  Access Paper or Ask Questions

End-to-End Task-Completion Neural Dialogue Systems

Feb 11, 2018
Xiujun Li, Yun-Nung Chen, Lihong Li, Jianfeng Gao, Asli Celikyilmaz

* 11 pages, IJCNLP 2017, arXiv admin note: substantial text overlap with arXiv:1703.07055 

  Access Paper or Ask Questions

Adversarial Advantage Actor-Critic Model for Task-Completion Dialogue Policy Learning

Feb 08, 2018
Baolin Peng, Xiujun Li, Jianfeng Gao, Jingjing Liu, Yun-Nung Chen, Kam-Fai Wong

* 5 pages, 3 figures, ICASSP 2018 

  Access Paper or Ask Questions

BBQ-Networks: Efficient Exploration in Deep Reinforcement Learning for Task-Oriented Dialogue Systems

Nov 23, 2017
Zachary C. Lipton, Xiujun Li, Jianfeng Gao, Lihong Li, Faisal Ahmed, Li Deng

* 13 pages, 9 figures 

  Access Paper or Ask Questions

A User Simulator for Task-Completion Dialogues

Nov 13, 2017
Xiujun Li, Zachary C. Lipton, Bhuwan Dhingra, Lihong Li, Jianfeng Gao, Yun-Nung Chen

* 14 pages, 2 Figures 

  Access Paper or Ask Questions

Composite Task-Completion Dialogue Policy Learning via Hierarchical Deep Reinforcement Learning

Jul 22, 2017
Baolin Peng, Xiujun Li, Lihong Li, Jianfeng Gao, Asli Celikyilmaz, Sungjin Lee, Kam-Fai Wong

* 12 pages, 8 figures 

  Access Paper or Ask Questions

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

Apr 20, 2017
Bhuwan Dhingra, Lihong Li, Xiujun Li, Jianfeng Gao, Yun-Nung Chen, Faisal Ahmed, Li Deng

* Accepted at ACL 2017 

  Access Paper or Ask Questions

Investigation of Language Understanding Impact for Reinforcement Learning Based Dialogue Systems

Mar 21, 2017
Xiujun Li, Yun-Nung Chen, Lihong Li, Jianfeng Gao, Asli Celikyilmaz

* 5 pages, 5 figures 

  Access Paper or Ask Questions

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

Jan 04, 2017
Xuesong Yang, Yun-Nung Chen, Dilek Hakkani-Tur, Paul Crook, Xiujun Li, Jianfeng Gao, Li Deng

* Accepted in The 42nd IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP2017) 

  Access Paper or Ask Questions

Recurrent Reinforcement Learning: A Hybrid Approach

Nov 19, 2015
Xiujun Li, Lihong Li, Jianfeng Gao, Xiaodong He, Jianshu Chen, Li Deng, Ji He

* 11 pages, 6 figures 

  Access Paper or Ask Questions