R.I.P.
👻
Ghosted
CREDENCE: Counterfactual Explanations for Document Ranking
February 10, 2023 · Declared Dead · 🏛 IEEE International Conference on Data Engineering
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
Joel Rorseth, Parke Godfrey, Lukasz Golab, Mehdi Kargar, Divesh Srivastava, Jaroslaw Szlichta
arXiv ID
2302.04983
Category
cs.IR: Information Retrieval
Citations
8
Venue
IEEE International Conference on Data Engineering
Last Checked
3 months ago
Abstract
Towards better explainability in the field of information retrieval, we present CREDENCE, an interactive tool capable of generating counterfactual explanations for document rankers. Embracing the unique properties of the ranking problem, we present counterfactual explanations in terms of document perturbations, query perturbations, and even other documents. Additionally, users may build and test their own perturbations, and extract insights about their query, documents, and ranker.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
📜 Similar Papers
In the same crypt — Information Retrieval
R.I.P.
👻
Ghosted
LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation
R.I.P.
👻
Ghosted
Graph Convolutional Neural Networks for Web-Scale Recommender Systems
🌅
🌅
Old Age
Neural Graph Collaborative Filtering
R.I.P.
👻
Ghosted
Self-Attentive Sequential Recommendation
R.I.P.
👻
Ghosted
DeepFM: A Factorization-Machine based Neural Network for CTR Prediction
Died the same way — 👻 Ghosted
R.I.P.
👻
Ghosted
Language Models are Few-Shot Learners
R.I.P.
👻
Ghosted
PyTorch: An Imperative Style, High-Performance Deep Learning Library
R.I.P.
👻
Ghosted
XGBoost: A Scalable Tree Boosting System
R.I.P.
👻
Ghosted