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
Posted Content
Gender Bias in Contextualized Word Embeddings
TL;DR: It is shown that a state-of-the-art coreference system that depends on ELMo inherits its bias and demonstrates significant bias on the WinoBias probing corpus and two methods to mitigate such gender bias are explored.
Proceedings ArticleDOI
GPT-GNN: Generative Pre-Training of Graph Neural Networks
TL;DR: GPT-GNN as discussed by the authors introduces a self-supervised attributed graph generation task to pre-train a GNN so that it can capture the structural and semantic properties of the graph.
Journal ArticleDOI
Large Linear Classification When Data Cannot Fit in Memory
TL;DR: This work proposes and analyzes a block minimization framework for data larger than the memory size, and investigates two implementations of the proposed framework for primal and dual SVMs, respectively.
Posted Content
Learning Gender-Neutral Word Embeddings
TL;DR: A novel training procedure for learning gender-neutral word embeddings that preserves gender information in certain dimensions of word vectors while compelling other dimensions to be free of gender influence is proposed.
Proceedings Article
Automatic Perturbation Analysis for Scalable Certified Robustness and Beyond
Kaidi Xu,Zhouxing Shi,Huan Zhang,Yihan Wang,Kai-Wei Chang,Minlie Huang,Bhavya Kailkhura,Xue Lin,Cho-Jui Hsieh +8 more
TL;DR: This work develops an automatic framework to enable perturbation analysis on any neural network structures, by generalizing existing LiRPA algorithms such as CROWN to operate on general computational graphs and yields an open-source library for the community to applyLiRPA to areas beyond certified defense without much LiR PA expertise.