Papers by Emaad Manzoor
Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond (2022.tacl-1)
Copied to clipboard
Amir Feder, Katherine A. Keith, Emaad Manzoor, Reid Pryzant, Dhanya Sridhar, Zach Wood-Doughty, Jacob Eisenstein, Justin Grimmer, Roi Reichart, Margaret E. Roberts, Brandon M. Stewart, Victor Veitch, Diyi Yang
| Challenge: | causality has not had the same importance in natural language processing, says aaron e. smith . he says research on causality in NLP remains scattered across domains without unified definitions . |
| Approach: | They propose to consolidate research on causality in NLP across academic areas . they explore potential uses of causal inference to improve robustness, fairness, interpretability . |
| Outcome: | The proposed method is a unified overview of causal inference for the NLP community. |
Detecting Attackable Sentences in Arguments (2020.emnlp-main)
Copied to clipboard
| Challenge: | Prior work in NLP studies focus on argument quality and making counterarguments toward the main claim, without investigating what parts of an argument are attackable for successful persuasion. |
| Approach: | They propose to use machine learning to find attackable sentences in online arguments by analyzing driving reasons for attacks and identifying relevant characteristics of sentences. |
| Outcome: | The proposed model can detect attackable sentences significantly better than baselines and comparably well to laypeople. |
Status Biases in Deliberation Online: Evidence from a Randomized Experiment on ChangeMyView (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Status is widely used to incentivize user engagement, but visible status indicators could inadvertently bias online deliberation to favor high-status users. |
| Approach: | They propose to quantify status biases in online deliberation using a ChangeMyView platform and to test whether status visibility can inadvertently bias it to favor high-status users. |
| Outcome: | The proposed method increases the persuasion rate of moderate-status users by 84% and lowers the per-su-sion rate for high-statuse users by 41% relative to the control group. |