Training and testing low-degree polynomial data mappings via linear SVM. YW Chang, CJ Hsieh, KW Chang, M Ringgaard, CJ Lin
Journal of Machine Learning Research 11 (4), 2010
751 2010 Feature ranking using linear SVM YW Chang, CJ Lin
Causation and prediction challenge, 53-64, 2008
390 2008 Pre-training tasks for embedding-based large-scale retrieval WC Chang, FX Yu, YW Chang, Y Yang, S Kumar
arXiv preprint arXiv:2002.03932, 2020
322 2020 O (n) connections are expressive enough: Universal approximability of sparse transformers C Yun, YW Chang, S Bhojanapalli, AS Rawat, S Reddi, S Kumar
Advances in Neural Information Processing Systems 33, 13783-13794, 2020
74 2020 A simple and effective positional encoding for transformers PC Chen, H Tsai, S Bhojanapalli, HW Chung, YW Chang, CS Ferng
arXiv preprint arXiv:2104.08698, 2021
68 2021 Exact decoding of phrase-based translation models through lagrangian relaxation YW Chang
Massachusetts Institute of Technology, 2012
59 2012 Optimal beam search for machine translation AM Rush, YW Chang, M Collins
Proceedings of the 2013 Conference on Empirical Methods in Natural Language …, 2013
36 2013 Leveraging redundancy in attention with reuse transformers S Bhojanapalli, A Chakrabarti, A Veit, M Lukasik, H Jain, F Liu, YW Chang, ...
arXiv preprint arXiv:2110.06821, 2021
21 2021 A constrained viterbi relaxation for bidirectional word alignment YW Chang, AM Rush, J DeNero, M Collins
Proceedings of the 52nd Annual Meeting of the Association for Computational …, 2014
14 2014 Demystifying the better performance of position encoding variants for transformer PC Chen, H Tsai, S Bhojanapalli, HW Chung, YW Chang, CS Ferng
arXiv preprint arXiv:2104.08698 3 (7), 2021
7 2021 A polynomial-time dynamic programming algorithm for phrase-based decoding with a fixed distortion limit YW Chang, M Collins
Transactions of the Association for Computational Linguistics 5, 59-71, 2017
5 2017 Low-degree polynomial mapping of data for svm Y Chang, C Hsieh, K Chang, M Ringgaard, C Lin
Journal of Machine Learning Research 11, 1-21, 2010
5 2010 BEVOLO, AJ, 176 JC BOIVIN, WE BROWN, C CARCALY, A CHANG, R CHEVREL, ...
Journal of Solid State Chemistry 35, 407-408, 1980
1 1980 Leveraging Redundancy in Attention with Reuse Transformers VS Bhojanapalli, A Veit, A Chakrabarti, F Liu, H Jain, M Lukasik, S Kumar, ...
US Patent App. 17/960,380, 2023
2023 Connections are Expressive Enough: Universal Approximability of Sparse TransformersAS Rawat, C Yun, S Kumar, S Reddi, S Bhojanapalli, YW Chang
2020 Source-Side Left-to-Right or Target-Side Left-to-Right? An Empirical Comparison of Two Phrase-Based Decoding Algorithms YW Chang, M Collins
Proceedings of the 2017 Conference on Empirical Methods in Natural Language …, 2017
2017 Exact Decoding of Phrase-Based Translation Models through Lagrangian Relaxation: Supplementary Material YW Chang, M Collins