i-machine-think / diagNNoseLinks
diagNNose is a Python library that facilitates a broad set of tools for analysing hidden activations of neural models.
☆82Updated 2 years ago
Alternatives and similar repositories for diagNNose
Users that are interested in diagNNose are comparing it to the libraries listed below
Sorting:
- Replication code for "With Little Power Comes Great Responsibility"☆39Updated 5 years ago
- 🐸 KERMIT - A lightweight library to encode and interpret Universal Syntactic Embeddings☆58Updated 2 years ago
- ☆75Updated 4 years ago
- Code and Data for Evaluation WG☆42Updated 3 years ago
- This is a repository with the code for the EMNLP 2020 paper "Information-Theoretic Probing with Minimum Description Length"☆71Updated last year
- Statistics on multilingual datasets☆17Updated 3 years ago
- How Contextual are Contextualized Word Representations?☆42Updated 5 years ago
- Factorization of the neural parameter space for zero-shot multi-lingual and multi-task transfer☆39Updated 5 years ago
- As good as new. How to successfully recycle English GPT-2 to make models for other languages (ACL Findings 2021)☆48Updated 4 years ago
- A 🤗-style implementation of BERT using lambda layers instead of self-attention☆69Updated 5 years ago
- Hyperparameter Search for AllenNLP☆140Updated 10 months ago
- A program to choose transfer languages for cross-lingual learning☆73Updated 3 months ago
- The Benchmark of Linguistic Minimal Pairs☆160Updated 3 years ago
- Implementation of experiments in paper "Learning from Rules Generalizing Labeled Exemplars" to appear in ICLR2020 (https://openreview.net…☆50Updated 2 years ago
- Code for the paper "Do Massively Pretrained Language Models Make Better Storytellers?"☆75Updated 3 years ago
- To analyze and remove gender bias in coreference resolution systems☆78Updated 8 months ago
- Code for the Shortformer model, from the ACL 2021 paper by Ofir Press, Noah A. Smith and Mike Lewis.☆147Updated 4 years ago
- Code for EMNLP 2019 paper "Attention is not not Explanation"☆58Updated 4 years ago
- QED: A Framework and Dataset for Explanations in Question Answering☆119Updated 4 years ago
- ☆21Updated 3 years ago
- A Diagnostic Study of Explainability Techniques for Text Classification☆69Updated 5 years ago
- A benchmark for understanding and evaluating rationales: http://www.eraserbenchmark.com/☆101Updated 3 years ago
- A Python library that encapsulates various methods for neuron interpretation and analysis in Deep NLP models.☆106Updated 2 years ago
- Code for "Rissanen Data Analysis: Examining Dataset Characteristics via Description Length" by Ethan Perez, Douwe Kiela, and Kyungyhun Ch…☆36Updated 4 years ago
- Language Modelling Makes Sense - WSD (and more) with Contextual Embeddings☆96Updated 2 years ago
- Rationales for Sequential Predictions☆40Updated 3 years ago
- Code for the paper: Don't Settle for Average, Go for the Max: Fuzzy Sets and Max-Pooled Word Vectors, ICLR 2019.☆43Updated 3 years ago
- A highly sophisticated sequence-to-sequence model for code generation☆40Updated 4 years ago
- Efficient-Sentence-Embedding-using-Discrete-Cosine-Transform☆17Updated 5 years ago
- Code for the paper "Implicit Representations of Meaning in Neural Language Models"☆55Updated 2 years ago