Queering NLP: A Non-Heteronormative Approach to Quantifying and Investigating Sentiment Bias against LGBTQ+ Identities in Word Embeddings
Name: Bang Nguyen
Major: Computer Science
Minor: Statistical & Data Sciences and Communication Studies
Advisor: Professor Kowshik Bhowmik; Professor Thomas Montelione (second reader)
To view Bang’s Independent Study, please click the button below (Wooster log-in credentials required)Bang Nguyen’s Independent Study
Posted in Comments Enabled, Independent Study, Symposium 2022 on April 26, 2022.
3 responses to “Queering NLP: A Non-Heteronormative Approach to Quantifying and Investigating Sentiment Bias against LGBTQ+ Identities in Word Embeddings”
Related Areas of Study
Statistical & Data Sciences
Use statistics, math, and computer science to gain insights into data and solve real-world problems.Major Minor
Solve complex problems with creative solutions using computer programming and applicationsMajor Minor
Be an effective listener, writer, and speaker who can think critically and connect with audiencesMajor Minor
Bang, I enjoyed talking to you about your study (and will come talk some more this afternoon). I look forward to hopefully hearing (in the future) how context affects or doesn’t affect your results. I agree that training models based on biased data will only breathe a more biased world. I look forward to seeing you help solve some of these problems in the future!
[…] There you will find 53133 more Infos: wooster.edu/2022/04/26/bang-nguyen/ […]