CREDENCE: Counterfactual Explanations for Document Ranking

02/10/2023
by   Joel Rorseth, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/16/2019

Counterfactual Visual Explanations

A counterfactual query is typically of the form 'For situation X, why wa...
research
08/20/2019

Counterfactual Distribution Regression for Structured Inference

We consider problems in which a system receives external perturbations f...
research
05/12/2021

Multi-Field Models in Neural Recipe Ranking – An Early Exploratory Study

Explicitly modelling field interactions and correlations in complex docu...
research
01/22/2022

On the Robustness of Counterfactual Explanations to Adverse Perturbations

Counterfactual explanations (CEs) are a powerful means for understanding...
research
11/18/2020

Non-Linear Multiple Field Interactions Neural Document Ranking

Ranking tasks are usually based on the text of the main body of the page...
research
09/25/2022

Answer-Set Programs for Repair Updates and Counterfactual Interventions

We briefly describe – mainly through very simple examples – different ki...
research
01/04/2023

Counterfactual Explanations for Land Cover Mapping in a Multi-class Setting

Counterfactual explanations are an emerging tool to enhance interpretabi...

Please sign up or login with your details

Forgot password? Click here to reset