Papers by Jan-Peter Calliess
Bayesian Topic Regression for Causal Inference (2021.emnlp-main)
Copied to clipboard
| Challenge: | a Bayesian topic regression model uses text and numerical information to model outcome variables. |
| Approach: | They propose a Bayesian Topic Regression model that uses both text and numerical information to model an outcome variable. |
| Outcome: | The proposed model recovers ground truth with lower bias than any benchmark model when text and numerical features are correlated. |