1 citations · 1 across the 4 of their papers we have counts for
4 papers
Learning from Sufficient Rationales: Analysing the Relationship Between Explanation Faithfulness and Token-level Regularisation Strategies
Jonathan Kamp, Lisa Beinborn, Antske Fokkens
Human explanations of natural language, rationales, form a tool to assess whether models learn a label for the right reasons or rely on dataset-specific shortcuts. Sufficiency is a…
The Role of Syntactic Span Preferences in Post-Hoc Explanation Disagreement
Jonathan Kamp, Lisa Beinborn, Antske Fokkens
Post-hoc explanation methods are an important tool for increasing model transparency for users. Unfortunately, the currently used methods for attributing token importance often yie…
Dynamic Top-k Estimation Consolidates Disagreement between Feature Attribution Methods
Jonathan Kamp, Lisa Beinborn, Antske Fokkens
Feature attribution scores are used for explaining the prediction of a text classifier to users by highlighting a k number of tokens. In this work, we propose a way to determine th…
Perturbations and Subpopulations for Testing Robustness in Token-Based Argument Unit Recognition
Jonathan Kamp, Lisa Beinborn, Antske Fokkens
Argument Unit Recognition and Classification aims at identifying argument units from text and classifying them as pro or against. One of the design choices that need to be made whe…