Follow
Phillip Keung
Phillip Keung
Senior Machine Learning Scientist, Amazon
Verified email at amazon.com
Title
Cited by
Cited by
Year
The multilingual amazon reviews corpus
P Keung, Y Lu, G Szarvas, NA Smith
arXiv preprint arXiv:2010.02573, 2020
1802020
A neural interlingua for multilingual machine translation
Y Lu, P Keung, F Ladhak, V Bhardwaj, S Zhang, J Sun
Proceedings of the Third Conference on Machine Translation: Research Papers …, 2018
1132018
Language based solution agent
VSR Bhardwaj, JK Kramer, HCP Keung, K Chahal, T Agarwal, J Sun, ...
US Patent 10,013,416, 2018
1002018
Adversarial learning with contextual embeddings for zero-resource cross-lingual classification and NER
P Keung, Y Lu, V Bhardwaj
arXiv preprint arXiv:1909.00153, 2019
972019
Don't Use English Dev: On the Zero-Shot Cross-Lingual Evaluation of Contextual Embeddings
P Keung, Y Lu, J Salazar, V Bhardwaj
arXiv preprint arXiv:2004.15001, 2020
402020
Improving non-autoregressive neural machine translation with monolingual data
J Zhou, P Keung
arXiv preprint arXiv:2005.00932, 2020
302020
Unsupervised bitext mining and translation via self-trained contextual embeddings
P Keung, J Salazar, Y Lu, NA Smith
Transactions of the Association for Computational Linguistics 8, 828-841, 2021
292021
A practical approach to dialogue response generation in closed domains
Y Lu, P Keung, S Zhang, J Sun, V Bhardwaj
arXiv preprint arXiv:1703.09439, 2017
172017
Automated service agents
T Labarre, HCP Keung, Y Lu, R Parvathaneni
US Patent 10,382,370, 2019
142019
Attentional speech recognition models misbehave on out-of-domain utterances
P Keung, W Niu, Y Lu, J Salazar, V Bhardwaj
arXiv preprint arXiv:2002.05150, 2020
102020
Narrowbert: Accelerating masked language model pretraining and inference
H Li, P Keung, D Cheng, J Kasai, NA Smith
arXiv preprint arXiv:2301.04761, 2023
42023
Neural networks for insurance fraud detection
P Keung, J Karel, C Bright
32009
Domain mismatch doesn't always prevent cross-lingual transfer learning
D Edmiston, P Keung, NA Smith
arXiv preprint arXiv:2211.16671, 2022
22022
The engage corpus: A social media dataset for text-based recommender systems
D Cheng, K Yan, P Keung, NA Smith
Proceedings of the Thirteenth Language Resources and Evaluation Conference …, 2022
22022
ACID: Abstractive, Content-Based IDs for Document Retrieval with Language Models
H Li, P Keung, D Cheng, J Kasai, NA Smith
arXiv preprint arXiv:2311.08593, 2023
12023
Accurate individual queue level metric forecasting for virtual contact center queues with insufficient data, using models trained at higher granularity level
Y Li, W Niu, TC Lung, YC Lin, TB Johnston, M Donthi, RJ Rodriguez, ...
US Patent 12,073,340, 2024
2024
The system can't perform the operation now. Try again later.
Articles 1–16