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

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Sungjin Lee

AUGNLG: Few-shot Natural Language Generation using Self-trained Data Augmentation


Jun 10, 2021
Xinnuo Xu, Guoyin Wang, Young-Bum Kim, Sungjin Lee

* Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics (ACL2021) 

  Access Paper or Ask Questions

Learning Slice-Aware Representations with Mixture of Attentions


Jun 04, 2021
Cheng Wang, Sungjin Lee, Sunghyun Park, Han Li, Young-Bum Kim, Ruhi Sarikaya

* Findings of the ACL: ACL-IJCNLP 2021 

  Access Paper or Ask Questions

Handling Long-Tail Queries with Slice-Aware Conversational Systems


Apr 26, 2021
Cheng Wang, Sun Kim, Taiwoo Park, Sajal Choudhary, Sunghyun Park, Young-Bum Kim, Ruhi Sarikaya, Sungjin Lee

* Published at ICLR 2021 Workshop on Weakly Supervised Learning 

  Access Paper or Ask Questions

Neural model robustness for skill routing in large-scale conversational AI systems: A design choice exploration


Mar 04, 2021
Han Li, Sunghyun Park, Aswarth Dara, Jinseok Nam, Sungjin Lee, Young-Bum Kim, Spyros Matsoukas, Ruhi Sarikaya


  Access Paper or Ask Questions

A Data-driven Approach to Estimate User Satisfaction in Multi-turn Dialogues


Mar 01, 2021
Ziming Li, Dookun Park, Julia Kiseleva, Young-Bum Kim, Sungjin Lee

* 12 pages 

  Access Paper or Ask Questions

A Scalable Framework for Learning From Implicit User Feedback to Improve Natural Language Understanding in Large-Scale Conversational AI Systems


Oct 23, 2020
Sunghyun Park, Han Li, Ameen Patel, Sidharth Mudgal, Sungjin Lee, Young-Bum Kim, Spyros Matsoukas, Ruhi Sarikaya


  Access Paper or Ask Questions

Self-Supervised Contrastive Learning for Efficient User Satisfaction Prediction in Conversational Agents


Oct 21, 2020
Mohammad Kachuee, Hao Yuan, Young-Bum Kim, Sungjin Lee


  Access Paper or Ask Questions

Large-scale Hybrid Approach for Predicting User Satisfaction with Conversational Agents


May 29, 2020
Dookun Park, Hao Yuan, Dongmin Kim, Yinglei Zhang, Matsoukas Spyros, Young-Bum Kim, Ruhi Sarikaya, Edward Guo, Yuan Ling, Kevin Quinn, Pham Hung, Benjamin Yao, Sungjin Lee


  Access Paper or Ask Questions

Guided Dialog Policy Learning without Adversarial Learning in the Loop


Apr 07, 2020
Ziming Li, Sungjin Lee, Baolin Peng, Jinchao Li, Shahin Shayandeh, Jianfeng Gao

* 10 pages 

  Access Paper or Ask Questions

The Eighth Dialog System Technology Challenge


Nov 14, 2019
Seokhwan Kim, Michel Galley, Chulaka Gunasekara, Sungjin Lee, Adam Atkinson, Baolin Peng, Hannes Schulz, Jianfeng Gao, Jinchao Li, Mahmoud Adada, Minlie Huang, Luis Lastras, Jonathan K. Kummerfeld, Walter S. Lasecki, Chiori Hori, Anoop Cherian, Tim K. Marks, Abhinav Rastogi, Xiaoxue Zang, Srinivas Sunkara, Raghav Gupta

* Submitted to NeurIPS 2019 3rd Conversational AI Workshop 

  Access Paper or Ask Questions

Generating a Common Question from Multiple Documents using Multi-source Encoder-Decoder Models


Oct 25, 2019
Woon Sang Cho, Yizhe Zhang, Sudha Rao, Chris Brockett, Sungjin Lee

* Accepted at EMNLP-IJCNLP 2019 - The 3rd Workshop on Neural Generation and Translation 

  Access Paper or Ask Questions

Data-Efficient Goal-Oriented Conversation with Dialogue Knowledge Transfer Networks


Oct 03, 2019
Igor Shalyminov, Sungjin Lee, Arash Eshghi, Oliver Lemon

* EMNLP 2019 

  Access Paper or Ask Questions

Structuring Latent Spaces for Stylized Response Generation


Sep 03, 2019
Xiang Gao, Yizhe Zhang, Sungjin Lee, Michel Galley, Chris Brockett, Jianfeng Gao, Bill Dolan

* EMNLP 2019 
* accepted to appear at EMNLP 2019 (long) 

  Access Paper or Ask Questions

Few-Shot Dialogue Generation Without Annotated Data: A Transfer Learning Approach


Aug 16, 2019
Igor Shalyminov, Sungjin Lee, Arash Eshghi, Oliver Lemon

* Accepted at SigDial 2019 

  Access Paper or Ask Questions

Contextual Out-of-Domain Utterance Handling With Counterfeit Data Augmentation


May 24, 2019
Sungjin Lee, Igor Shalyminov

* ICASSP 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

Jointly Optimizing Diversity and Relevance in Neural Response Generation


Apr 04, 2019
Xiang Gao, Sungjin Lee, Yizhe Zhang, Chris Brockett, Michel Galley, Jianfeng Gao, Bill Dolan

* Long paper accepted at NAACL 2019 

  Access Paper or Ask Questions

Consistent Dialogue Generation with Self-supervised Feature Learning


Mar 27, 2019
Yizhe Zhang, Xiang Gao, Sungjin Lee, Chris Brockett, Michel Galley, Jianfeng Gao, Bill Dolan


  Access Paper or Ask Questions

Improving Robustness of Neural Dialog Systems in a Data-Efficient Way with Turn Dropout


Nov 29, 2018
Igor Shalyminov, Sungjin Lee

* NeurIPS 2018 workshop on Conversational AI 

  Access Paper or Ask Questions

Nudging Neural Conversational Model with Domain Knowledge


Nov 15, 2018
Sungjin Lee


  Access Paper or Ask Questions

Zero-Shot Adaptive Transfer for Conversational Language Understanding


Aug 29, 2018
Sungjin Lee, Rahul Jha


  Access Paper or Ask Questions

OneNet: Joint Domain, Intent, Slot Prediction for Spoken Language Understanding


Jan 16, 2018
Young-Bum Kim, Sungjin Lee, Karl Stratos

* 5 pages conference paper accepted to IEEE ASRU 2017. Will be published in December 2017 

  Access Paper or Ask Questions

Toward Continual Learning for Conversational Agents


Jan 09, 2018
Sungjin Lee


  Access Paper or Ask Questions

Speaker-Sensitive Dual Memory Networks for Multi-Turn Slot Tagging


Nov 29, 2017
Young-Bum Kim, Sungjin Lee, Ruhi Sarikaya

* 5 pages conference paper accepted to IEEE ASRU 2017. Will be published in December 2017 

  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