Kai-Wei Chang

Prof. Kai-Wei Chang


Research Focus & Metrics

Academic Career Length

19Years (2008-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2019
Verified
Conference Paper
Open access
PDF file
ESEmily Sheng
Emily Sheng
KCKai-Wei Chang
Kai-Wei Chang
PNPremkumar Natarajan
Premkumar Natarajan
NPNanyun Peng
Nanyun Peng
Emily Sheng, Kai-Wei Chang, Premkumar Natarajan, Nanyun Peng. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

1 January 2008
Verified
Conference Paper
Open access
CHCho-Jui Hsieh
Cho-Jui Hsieh
KCKai-Wei Chang
Kai-Wei Chang
CLChih-Jen Lin
Chih-Jen Lin
SKS. Sathiya Keerthi
S. Sathiya Keerthi
SSS. Sundararajan
S. Sundararajan
In many applications, data appear with a huge number of instances as well as features. Linear Support Vector Machines (SVM) is one of the most popular tools to deal with such large-scale sparse data. This paper presents a novel dual coordinate descent method for linear SVM with L1-and L2-loss functions. The proposed method is simple and reaches an ε-accurate solution in O(log(1/ε)) iterations. Experiments indicate that our method is much faster than state of the art solvers such as Pegasos, TRON, SVMperf, and a recent primal coordinate descent implementation.

1 January 2023
Verified
Conference Paper
Open access
PDF file
YWYixin Wan
Yixin Wan
GPGeorge Pu
George Pu
JSJiao Sun
Jiao Sun
AGAparna Garimella
Aparna Garimella
KCKai-Wei Chang
Kai-Wei Chang
NPNanyun Peng
Nanyun Peng
Yixin Wan, George Pu, Jiao Sun, Aparna Garimella, Kai-Wei Chang, Nanyun Peng. Findings of the Association for Computational Linguistics: EMNLP 2023. 2023.

1 January 2023
Verified
Conference Paper
Open access
PDF file
AKAmita Kamath
Amita Kamath
JHJack Hessel
Jack Hessel
KCKai-Wei Chang
Kai-Wei Chang
Amita Kamath, Jack Hessel, Kai-Wei Chang. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 2023.

1 August 2023
Verified
Conference Paper
Open access
PDF file
HZHonghua Zhang
Honghua Zhang
LLLiunian Harold Li
Liunian Harold Li
TMTao Meng
Tao Meng
KCKai-Wei Chang
Kai-Wei Chang
GBGuy Van Den Broeck
Guy Van Den Broeck
Logical reasoning is needed in a wide range of NLP tasks. Can a BERT model be trained end-to-end to solve logical reasoning problems presented in natural language? We attempt to answer this question in a confined problem space where there exists a set of parameters that perfectly simulates logical reasoning. We make observations that seem to contradict each other: BERT attains near-perfect accuracy on in-distribution test examples while failing to generalize to other data distributions over the exact same problem space. Our study provides an explanation for this paradox: instead of learning to emulate the correct reasoning function, BERT has, in fact, learned statistical features that inherently exist in logical reasoning problems. We also show that it is infeasible to jointly remove statistical features from data, illustrating the difficulty of learning to reason in general. Our result naturally extends to other neural models (e.g. T5) and unveils the fundamental difference between learning to reason and learning to achieve high performance on NLP benchmarks using statistical features.

1 January 2023
Verified
Conference Paper
Open access
PDF file
WAWasi Uddin Ahmad
Wasi Uddin Ahmad
GTGolam Rahman Tushar
Golam Rahman Tushar
SCSaikat Chakraborty
Saikat Chakraborty
KCKai-Wei Chang
Kai-Wei Chang
Wasi Uddin Ahmad, Md Golam Rahman Tushar, Saikat Chakraborty, Kai-Wei Chang. Findings of the Association for Computational Linguistics: ACL 2023. 2023.