INK-USC / DIGLinks
Discretized Integrated Gradients for Explaining Language Models (EMNLP 2021)
☆27Updated 3 years ago
Alternatives and similar repositories for DIG
Users that are interested in DIG are comparing it to the libraries listed below
Sorting:
- Code for Evaluating Explanations for Reading Comprehension with Realistic Counterfactuals.☆18Updated 4 years ago
- ☆24Updated 3 years ago
- EMNLP 2021 - Frustratingly Simple Pretraining Alternatives to Masked Language Modeling☆31Updated 3 years ago
- A dataset for realistic evaluation of noisy label methods☆14Updated last year
- ☆24Updated 2 years ago
- Code for paper "Leakage-Adjusted Simulatability: Can Models Generate Non-Trivial Explanations of Their Behavior in Natural Language?"☆21Updated 4 years ago
- ☆24Updated last year
- Pytorch implementation of DiffMask☆55Updated last year
- NAACL 2022: Can Rationalization Improve Robustness? https://arxiv.org/abs/2204.11790☆27Updated 2 years ago
- ☆34Updated 3 years ago
- Implementation for https://arxiv.org/abs/2005.00652☆28Updated 2 years ago
- Codebase for running (conditional) probing experiments☆22Updated 2 years ago
- [EMNLP 2020] Collective HumAn OpinionS on Natural Language Inference Data☆36Updated 3 years ago
- Code for "Understanding Neural Abstractive Summarization Models via Uncertainty" (EMNLP20)☆30Updated 4 years ago
- Code Repo for "Differentiable Open-Ended Commonsense Reasoning" (NAACL 2021)☆32Updated last year
- Code associated with the paper: "Few-Shot Self-Rationalization with Natural Language Prompts"☆13Updated 3 years ago
- ☆25Updated last year
- Debiasing Methods in Natural Language Understanding Make Bias More Accessible: Code and Data☆14Updated 3 years ago
- Code and datasets for the EMNLP 2020 paper "Calibration of Pre-trained Transformers"☆59Updated last year
- Code Repo for the ACL21 paper "Common Sense Beyond English: Evaluating and Improving Multilingual LMs for Commonsense Reasoning"☆22Updated 3 years ago
- EMNLP'2020: Look at the First Sentence: Position Bias in Question Answering☆29Updated 4 years ago
- ☆63Updated 3 years ago
- ReCross: Unsupervised Cross-Task Generalization via Retrieval Augmentation☆24Updated 3 years ago
- Code for the paper "Learning Variational Word Masks to Improve the Interpretability of Neural Text Classifiers"☆17Updated 4 years ago
- ☆11Updated 3 years ago
- ☆39Updated 3 years ago
- ☆26Updated 4 years ago
- Source code for ICLR 2021 paper : Pre-training Text-to-Text Transformers for Concept-Centric Common Sense☆27Updated 3 years ago
- ACL 2021 paper "Style is NOT a single variable: Case Studies for Cross-Style Language Understanding " by Dongyeop Kang and Eduard Hovy☆14Updated 3 years ago
- Common Sense or World Knowledge? Investigating Adapter-Based Knowledge Injection into Pretrained Transformers☆20Updated 4 years ago