TY - GEN
T1 - Conditional word embedding and hypothesis testing via bayes-by-backprop
AU - Han, Rujun
AU - Spirling, Arthur
AU - Gill, Michael
AU - Cho, Kyunghyun
N1 - Funding Information:
KC thanks the support by eBay, TenCent, NVIDIA and CIFAR. RH thanks the support by MINDS research group at Information Sciences Institute of University of California.
Publisher Copyright:
© 2018 Association for Computational Linguistics
PY - 2018
Y1 - 2018
N2 - Conventional word embedding models do not leverage information from document meta-data, and they do not model uncertainty. We address these concerns with a model that incorporates document covariates to estimate conditional word embedding distributions. Our model allows for (a) hypothesis tests about the meanings of terms, (b) assessments as to whether a word is near or far from another conditioned on different covariate values, and (c) assessments as to whether estimated differences are statistically significant.
AB - Conventional word embedding models do not leverage information from document meta-data, and they do not model uncertainty. We address these concerns with a model that incorporates document covariates to estimate conditional word embedding distributions. Our model allows for (a) hypothesis tests about the meanings of terms, (b) assessments as to whether a word is near or far from another conditioned on different covariate values, and (c) assessments as to whether estimated differences are statistically significant.
UR - http://www.scopus.com/inward/record.url?scp=85081721692&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85081721692&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85081721692
T3 - Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018
SP - 4890
EP - 4895
BT - Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018
A2 - Riloff, Ellen
A2 - Chiang, David
A2 - Hockenmaier, Julia
A2 - Tsujii, Jun'ichi
PB - Association for Computational Linguistics
T2 - 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018
Y2 - 31 October 2018 through 4 November 2018
ER -