PhD student @ChicagoHAI @CUBoulder. On the job market.
Jan 4, 2022 • 9 tweets • 4 min read
(1/n) Very happy to share our survey paper “Towards a Science of Human-AI Decision Making: A Survey of Empirical Studies”, joint work with @chachaachen, @QVeraLiao, @alison_m_smith, & @ChenhaoTan!
Brief summary:
(2/n) Given the promise of AI in improving human decision making, how should we study human-AI decision making with human-subjects studies? What are the current trends📈? What are the gaps ⚠️ and recommendations ✅ for the field to produce more useful scientific knowledge?
Nov 6, 2019 • 5 tweets • 3 min read
Unsupervised Domain Adaptation of Contextualized Embeddings for Sequence Labeling by @XiaochuangHan and @jacobeisenstein
Link: aclweb.org/anthology/D19-…
Code: github.com/xhan77/AdaptaB… #emnlp2019
Since BERT is trained on Wikipedia, Han and Eisenstein are interested in scenarios wheee labeled data exists only for canonical source domain, and target domain is distinct from both pretraining and labeled source domain. #emnlp2019
Nov 4, 2019 • 12 tweets • 3 min read
Why should we study bias and fairness in NLP? Tutorial session led by Margaret Mitchell, @vinodkpg, @kaiwei_chang & @bluevincent. #emnlp2019
Human biases in data! 1) selection data: a) selection does not reflect a random sample, gender bias in Wikipedia and britannica; b) turkers are mainly from n America; 2) biased data representation: a) some groups are less represented less positively than others;
Since BERT is trained on Wikipedia, Han and Eisenstein are interested in scenarios wheee labeled data exists only for canonical source domain, and target domain is distinct from both pretraining and labeled source domain.