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 Constrained Latent Variable Model for Coreference Resolution
TL;DR: The authors proposed the Latent Left Linking model (L 3 M), a linguistically motivated latent structured prediction approach to coreference resolution, which admits efficient inference and can be augmented with knowledge-based constraints; they also present a fast stochastic gradient based learning.
Supplementary Material: A Constrained Latent Variable Model for Coreference Resolution
TL;DR: The Latent Left Linking model (L 3 M), a novel, principled, and linguistically motivated latent structured prediction approach to coreference resolution, is described and it is shown that L 3 M admits efficient inference and can be augmented with knowledge-based constraints.
Posted Content
The Woman Worked as a Babysitter: On Biases in Language Generation
TL;DR: This paper introduced the notion of the regard towards a demographic, and used the varying levels of regard towards different demographics as a defining metric for bias in NLG, and analyzed the extent to which sentiment scores are a relevant proxy metric for regard.
Proceedings Article
Multi-Task Learning for Document Ranking and Query Suggestion
TL;DR: In this paper, a multi-task learning framework is proposed to jointly learn document ranking and query suggestion for web search, which consists of two major components, a document ranker and a query recommender.
Posted Content
Quantifying and Reducing Stereotypes in Word Embeddings
TL;DR: A novel gender analogy task is created and combined with crowdsourcing to systematically quantify the gender bias in a given embedding, and an efficient algorithm is developed that reduces gender stereotype using just a handful of training examples while preserving the useful geometric properties of the embedding.