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 Article
A Corpus to Learn Refer-to-as Relations for Nominals
Wasi Uddin Ahmad,Kai-Wei Chang +1 more
TL;DR: It is argued that good word and phrase embeddings should contain information for identifying refer-to-as relationship and construct a corpus from Wikipedia to generate coreferential neural embeddeddings for nominals.
Proceedings Article
GENEVA: Benchmarking Generalizability for Event Argument Extraction with Hundreds of Event Types and Argument Roles
TL;DR: The GENEVA dataset as mentioned in this paper is a large and diverse EAE ontology, which is created by transforming FrameNet, a comprehensive semantic role labeling (SRL) dataset for EAE, by exploiting the similarity between these two tasks.
A Discriminative Latent Variable Model for Clustering of Streaming Data with Application to Coreference Resolution
TL;DR: A latent variable structured prediction model, called the Latent Left-linking Model (L3M), for discriminative supervised clustering of items that follow a streaming order is presented and it is shown that L 3 M outperforms several existing structured predictionbased techniques for coreference as well as several state-of-the-art, albeit ad hoc, approaches.
Journal ArticleDOI
ABC-KD: Attention-Based-Compression Knowledge Distillation for Deep Learning-Based Noise Suppression
TL;DR: In this article , a knowledge distillation (KDNN) based approach was proposed to solve the problem of large-scale DNS models, where high-performing DNS models are usually large in size, causing deployment difficulties.
Peer Review
Understanding and Mitigating Spurious Correlations in Text Classification with Neighborhood Analysis
TL;DR: In this paper , the authors examine the implications of spurious correlations through a novel perspective called neighborhood analysis and propose a metric to detect spurious tokens and also propose a family of regularization methods to mitigate spurious correlations in text classification.