Yun-hsuan Sung
Yun-hsuan Sung
Research Scientist, Google
Verified email at
Cited by
Cited by
Scaling up visual and vision-language representation learning with noisy text supervision
C Jia, Y Yang, Y Xia, YT Chen, Z Parekh, H Pham, Q Le, YH Sung, Z Li, ...
International conference on machine learning, 4904-4916, 2021
Universal sentence encoder
D Cer, Y Yang, S Kong, N Hua, N Limtiaco, RS John, N Constant, ...
arXiv preprint arXiv:1803.11175, 2018
Multilingual universal sentence encoder for semantic retrieval
Y Yang, D Cer, A Ahmad, M Guo, J Law, N Constant, GH Abrego, S Yuan, ...
arXiv preprint arXiv:1907.04307, 2019
Efficient natural language response suggestion for smart reply
M Henderson, R Al-Rfou, B Strope, YH Sung, L Lukács, R Guo, S Kumar, ...
arXiv preprint arXiv:1705.00652, 2017
LongT5: Efficient text-to-text transformer for long sequences
M Guo, J Ainslie, D Uthus, S Ontanon, J Ni, YH Sung, Y Yang
arXiv preprint arXiv:2112.07916, 2021
Learning semantic textual similarity from conversations
Y Yang, S Yuan, D Cer, S Kong, N Constant, P Pilar, H Ge, YH Sung, ...
arXiv preprint arXiv:1804.07754, 2018
Learning cross-lingual sentence representations via a multi-task dual-encoder model
M Chidambaram, Y Yang, D Cer, S Yuan, YH Sung, B Strope, R Kurzweil
arXiv preprint arXiv:1810.12836, 2018
Conversational contextual cues: The case of personalization and history for response ranking
R Al-Rfou, M Pickett, J Snaider, YH Sung, B Strope, R Kurzweil
arXiv preprint arXiv:1606.00372, 2016
Effective parallel corpus mining using bilingual sentence embeddings
M Guo, Q Shen, Y Yang, H Ge, D Cer, GH Abrego, K Stevens, N Constant, ...
arXiv preprint arXiv:1807.11906, 2018
Improving multilingual sentence embedding using bi-directional dual encoder with additive margin softmax
Y Yang, GH Abrego, S Yuan, M Guo, Q Shen, D Cer, YH Sung, B Strope, ...
arXiv preprint arXiv:1902.08564, 2019
Recognizing speech in multiple languages
Y Sung, F Beaufays, B Strope, H Lin, JT Huang
US Patent 9,129,591, 2015
Hidden conditional random fields for phone recognition
YH Sung, D Jurafsky
2009 IEEE Workshop on Automatic Speech Recognition & Understanding, 107-112, 2009
Freshllms: Refreshing large language models with search engine augmentation
T Vu, M Iyyer, X Wang, N Constant, J Wei, J Wei, C Tar, YH Sung, D Zhou, ...
arXiv preprint arXiv:2310.03214, 2023
Colt5: Faster long-range transformers with conditional computation
J Ainslie, T Lei, M de Jong, S Ontańón, S Brahma, Y Zemlyanskiy, ...
arXiv preprint arXiv:2303.09752, 2023
Cooperatively training and/or using separate input and response neural network models for determining response (s) for electronic communications
B Strope, Y Sung, M Henderson, R Al-Rfou, R Kurzweil
US Patent 11,373,086, 2022
Recognizing different versions of a language
F Beaufays, B Strope, Y Sung
US Patent 9,275,635, 2016
Regularization, adaptation, and non-independent features improve hidden conditional random fields for phone classification
YH Sung, C Boulis, C Manning, D Jurafsky
2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU …, 2007
Written-domain language modeling with decomposition
H Sak, Y Sung, CGL Allauzen
US Patent 9,460,088, 2016
Applying name entity recognition to informal text
Y Chang, YH Sung
Recall 1 (1), 2005
Hierarchical document encoder for parallel corpus mining
M Guo, Y Yang, K Stevens, D Cer, H Ge, Y Sung, B Strope, R Kurzweil
arXiv preprint arXiv:1906.08401, 2019
The system can't perform the operation now. Try again later.
Articles 1–20