@inproceedings{nguyen2022hari,author={Nguyen, Khanh and Bisk, Yonatan and Daum{\'e} III, Hal},title={A Framework for Learning to Request Rich and Contextually Useful Information from Humans},booktitle={ICML},month=jul,year={2022},}
2021
Interactive Learning from Activity Description
Khanh Nguyen, Dipendra Misra, Robert Schapire, and 2 more authors
@inproceedings{nguyen2021iliad,title={Interactive Learning from Activity Description},author={Nguyen, Khanh and Misra, Dipendra and Schapire, Robert and Dud{\'\i}k, Miro and Shafto, Patrick},booktitle={ICML},year={2021},}
2019
Help, Anna! Visual Navigation with Natural Multimodal Assistance via Retrospective Curiosity-Encouraging Imitation Learning
@inproceedings{nguyen2019hanna,author={Nguyen, Khanh and Daum{\'e} III, Hal},title={Help, Anna! Visual Navigation with Natural Multimodal Assistance via Retrospective Curiosity-Encouraging Imitation Learning},booktitle={EMNLP},month={},year={2019},}
Vision-Based Navigation With Language-Based Assistance via Imitation Learning With Indirect Intervention
Khanh Nguyen, Debadeepta Dey, Chris Brockett, and 1 more author
@inproceedings{nguyen2019vnla,author={Nguyen, Khanh and Dey, Debadeepta and Brockett, Chris and Dolan, Bill},title={Vision-Based Navigation With Language-Based Assistance via Imitation Learning With Indirect Intervention},booktitle={CVPR},month={},year={2019},}
Global Voices: Crossing Borders in Automatic News Summarization
Khanh Nguyen, and Hal Daumé III
In New Frontiers in Summarization Workshop at EMNLP, Nov 2019
@inproceedings{nguyen2019gv,title={Global Voices: Crossing Borders in Automatic News Summarization},author={Nguyen, Khanh and Daum{\'e} III, Hal},booktitle={New Frontiers in Summarization Workshop at EMNLP},month=nov,year={2019},}
2017
Reinforcement Learning for Bandit Neural Machine Translation with Simulated Human Feedback
Khanh Nguyen, Hal Daumé III, and Jordan Boyd-Graber
Machine translation is a natural candidate problem for reinforcement learning from human feedback: users provide quick, dirty ratings on candidate translations to guide a system to improve. Yet, current neural machine translation training focuses on expensive human-generated reference translations. We describe a reinforcement learning algorithm that improves neural machine translation systems from simulated human feedback. Our algorithm combines the advantage actor-critic algorithm (Mnih et al., 2016) with the attention-based neural encoder-decoder architecture (Luong et al., 2015). This algorithm (a) is well-designed for problems with a large action space and delayed rewards, (b) effectively optimizes traditional corpus-level machine translation metrics, and (c) is robust to skewed, high-variance, granular feedback modeled after actual human behaviors.
@inproceedings{nguyen2017banditnmt,title={Reinforcement Learning for Bandit Neural Machine Translation with Simulated Human Feedback},author={Nguyen, Khanh and Daum{\'e} III, Hal and Boyd-Graber, Jordan},booktitle={EMNLP},month=sep,year={2017},address={Copenhagen, Denmark},publisher={Association for Computational Linguistics},url={https://www.aclweb.org/anthology/D17-1153},doi={10.18653/v1/D17-1153},pages={1464--1474},}
The UMD Neural Machine Translation Systems at WMT17 Bandit Learning Task
Amr Sharaf, Shi Feng, Khanh Nguyen, and 2 more authors
@inproceedings{sharaf17wmt,title={The UMD Neural Machine Translation Systems at WMT17 Bandit Learning Task},author={Sharaf, Amr and Feng, Shi and Nguyen, Khanh and Brantley, Kiante and Daum{\'e} III, Hal},booktitle={WMT},month=sep,year={2017},address={Copenhagen, Denmark},publisher={Association for Computational Linguistics},url={https://www.aclweb.org/anthology/W17-4778},doi={10.18653/v1/W17-4778},pages={667--673},}
2015
Posterior calibration and exploratory analysis for natural language processing models
@inproceedings{nguyen15calibration,title={Posterior calibration and exploratory analysis for natural language processing models},author={Nguyen, Khanh and O{'}Connor, Brendan},booktitle={EMNLP},month=sep,year={2015},address={Lisbon, Portugal},publisher={Association for Computational Linguistics},url={https://www.aclweb.org/anthology/D15-1182},doi={10.18653/v1/D15-1182},pages={1587--1598},}