YilunZhou / ExSumLinks
Code repository for the NAACL 2022 paper "ExSum: From Local Explanations to Model Understanding"
☆64Updated 3 years ago
Alternatives and similar repositories for ExSum
Users that are interested in ExSum are comparing it to the libraries listed below
Sorting:
- Interpretable and efficient predictors using pre-trained language models. Scikit-learn compatible.☆43Updated 5 months ago
- Weakly Supervised End-to-End Learning (NeurIPS 2021)☆156Updated 2 years ago
- 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.☆82Updated 3 years ago
- A python package for benchmarking interpretability techniques on Transformers.☆214Updated 10 months ago
- Measuring if attention is explanation with ROAR☆22Updated 2 years ago
- Interactive Weak Supervision: Learning Useful Heuristics for Data Labeling☆31Updated 4 years ago
- Framework for zero-shot learning with knowledge graphs.☆113Updated 2 years ago
- Ensembling Hugging Face transformers made easy☆63Updated 2 years ago
- RATransformers 🐭- Make your transformer (like BERT, RoBERTa, GPT-2 and T5) Relation Aware!☆41Updated 2 years ago
- A diff tool for language models☆43Updated last year
- ☆53Updated 2 years ago
- ☆139Updated last year
- Code associated with the paper "Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists"☆49Updated 3 years ago
- ☆21Updated 3 years ago
- Embedding Recycling for Language models☆39Updated 2 years ago
- The Python library with command line tools to interact with Dynabench(https://dynabench.org/), such as uploading models.☆55Updated 3 years ago
- Library for creating causal chains using language models.☆79Updated 2 years ago
- Repo for training MLMs, CLMs, or T5-type models on the OLM pretraining data, but it should work with any hugging face text dataset.☆93Updated 2 years ago
- Google's BigBird (Jax/Flax & PyTorch) @ 🤗Transformers☆49Updated 2 years ago
- ☆18Updated 3 years ago
- Experiments on GPT-3's ability to fit numerical models in-context.☆14Updated 3 years ago
- ☆40Updated 2 years ago
- diagNNose is a Python library that facilitates a broad set of tools for analysing hidden activations of neural models.☆82Updated last year
- Ranking of fine-tuned HF models as base models.☆36Updated 3 months ago
- Self-training with Weak Supervision (NAACL 2021)☆161Updated 2 years ago
- ☆22Updated 3 years ago
- ☆37Updated 4 years ago
- Topic clustering library built on Transformer embeddings and cosine similarity metrics.Compatible with all BERT base transformers from hu…☆43Updated 4 years ago
- Shared code for training sentence embeddings with Flax / JAX☆27Updated 4 years ago
- Code for Language-Interfaced FineTuning for Non-Language Machine Learning Tasks.☆129Updated 9 months ago