Sotabase
Home
Researchers
Career
·
Research Scientist
,
Google
2010–
·
PhD Student
,
Massachusetts Institute of Technology
2010–2014
·
Research Assistant
,
Columbia University
2008–2010
Publications
(14)
Training and Testing Low-degree Polynomial Data Mappings via Linear SVM
Journal of machine learning research · 2010
578
cited
Pre-training Tasks for Embedding-based Large-scale Retrieval
International Conference on Learning Representations · 2020
322
cited
Feature Ranking Using Linear SVM
WCCI Causation and Prediction Challenge · 2008
281
cited
$O(n)$ Connections are Expressive Enough: Universal Approximability of Sparse Transformers
Neural Information Processing Systems · 2020
94
cited
A Simple and Effective Positional Encoding for Transformers
Conference on Empirical Methods in Natural Language Processing · 2021
75
cited
Exact Decoding of Phrase-Based Translation Models through Lagrangian Relaxation
Conference on Empirical Methods in Natural Language Processing · 2011
60
cited
Leveraging redundancy in attention with Reuse Transformers
arXiv.org · 2021
38
cited
Optimal Beam Search for Machine Translation
Conference on Empirical Methods in Natural Language Processing · 2013
19
cited
A Constrained Viterbi Relaxation for Bidirectional Word Alignment
Annual Meeting of the Association for Computational Linguistics · 2014
13
cited
Demystifying the Better Performance of Position Encoding Variants for Transformer
arXiv.org · 2021
10
cited
Low-degree Polynomial Mapping of Data for SVM
2009
5
cited
A Polynomial-Time Dynamic Programming Algorithm for Phrase-Based Decoding with a Fixed Distortion Limit
Transactions of the Association for Computational Linguistics · 2017
3
cited
Exact and Approximate Methods for Machine Translation Decoding
2015
Source-Side Left-to-Right or Target-Side Left-to-Right? An Empirical Comparison of Two Phrase-Based Decoding Algorithms
Conference on Empirical Methods in Natural Language Processing · 2017
Sotabase
Yin-Wen Chang | Researcher Profile | Sotabase | Sotabase