Papers by Sebastian Ebert
“Will You Find These Shortcuts?” A Protocol for Evaluating the Faithfulness of Input Salience Methods for Text Classification (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing work on faithfulness evaluation is not conclusive and does not provide a clear answer as to how different methods are to be compared. |
| Approach: | They propose a protocol for faithfulness evaluation that makes use of partially synthetic data to obtain ground truth for feature importance ranking. |
| Outcome: | The proposed method is based on partially synthetic data and is compared with lexical shortcuts on a range of datasets and LSTM models. |
We Need To Talk About Random Splits (2021.eacl-main)
Copied to clipboard
| Challenge: | argued that random splits, like standard splits lead to overly optimistic performance estimates. |
| Approach: | They argue that random splits, like standard splits lead to overly optimistic performance estimates. |
| Outcome: | The proposed method leads to more realistic performance estimates than standard splits. |
Don’t Search for a Search Method — Simple Heuristics Suffice for Adversarial Text Attacks (2021.emnlp-main)
Copied to clipboard
| Challenge: | Recent research has focused on adversarial text attacks on neural networks for natural language processing. |
| Approach: | They implement an algorithm inspired by zeroth order optimization-based attacks and compare it with benchmark results in TextAttack. |
| Outcome: | The proposed algorithm outperforms other black-box adversarial text attacks. |