K
Kai-Wei Chang
Researcher at University of California, Los Angeles
Publications - 262
Citations - 23031
Kai-Wei Chang is an academic researcher from University of California, Los Angeles. The author has contributed to research in topics: Computer science & Word embedding. The author has an hindex of 42, co-authored 183 publications receiving 17271 citations. Previous affiliations of Kai-Wei Chang include Boston University & Amazon.com.
Papers
More filters
Proceedings ArticleDOI
GeoMLAMA: Geo-Diverse Commonsense Probing on Multilingual Pre-Trained Language Models
TL;DR: A frame-work for geo-diverse commonsense probing on multilingual PLMs (mPLMs) is introduced and a corresponding benchmark Geo -diverse Commonsense M ultilingual La nguage M odels A nalysis (G EO ML AMA) dataset is benchmarked.
Proceedings Article
A Credit Assignment Compiler for Joint Prediction
TL;DR: In this paper, a credit assignment compiler is proposed to reduce the complexity of learning-to-search and the running time by transforming the search space into an arbitrary imperative program, which can be defined by an arbitrary program.
Posted Content
Distributed Training of Structured SVM
TL;DR: An efficient algorithm for distributedly training structured support vector machines based on a distributed block-coordinate descent method is proposed and both theoretical and experimental results indicate that the method is efficient.
Proceedings ArticleDOI
Summarize and Generate to Back-translate: Unsupervised Translation of Programming Languages
TL;DR: It is shown that the proposed framework performsably to state-of-the-art methods, if not exceed their translation performance between Java 032 and Python languages.
Proceedings Article
Neuro-Symbolic Entropy Regularization
TL;DR: A loss is proposed, neuro-symbolic entropy regularization, that encourages the model to confidently predict a valid object and seamlessly integrates with other neuro-Symbolic losses that elimi-nate invalid predictions.