i-machine-think / diagNNoseLinks
diagNNose is a Python library that facilitates a broad set of tools for analysing hidden activations of neural models.
β82Updated last year
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"β39Updated 5 years ago
- πΈ KERMIT - A lightweight library to encode and interpret Universal Syntactic Embeddingsβ58Updated 2 years ago
- Implementation of experiments in paper "Learning from Rules Generalizing Labeled Exemplars" to appear in ICLR2020 (https://openreview.netβ¦β50Updated 2 years ago
- β75Updated 4 years ago
- Factorization of the neural parameter space for zero-shot multi-lingual and multi-task transferβ39Updated 5 years ago
- Statistics on multilingual datasetsβ17Updated 3 years ago
- This is a repository with the code for the EMNLP 2020 paper "Information-Theoretic Probing with Minimum Description Length"β71Updated last year
- Repository collecting resources and best practices to improve experimental rigour in deep learning research.β27Updated 2 years ago
- β62Updated 3 years ago
- Code and Data for Evaluation WGβ42Updated 3 years ago
- A Diagnostic Study of Explainability Techniques for Text Classificationβ68Updated 5 years ago
- As good as new. How to successfully recycle English GPT-2 to make models for other languages (ACL Findings 2021)β48Updated 4 years ago
- Rationales for Sequential Predictionsβ40Updated 3 years ago
- To analyze and remove gender bias in coreference resolution systemsβ79Updated 5 months ago
- A π€-style implementation of BERT using lambda layers instead of self-attentionβ69Updated 5 years ago
- Code associated with the paper "Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists"β50Updated 3 years ago
- How Contextual are Contextualized Word Representations?β41Updated 5 years ago
- A benchmark for understanding and evaluating rationales: http://www.eraserbenchmark.com/β99Updated 2 years ago
- β21Updated 2 years ago
- Code for "Rissanen Data Analysis: Examining Dataset Characteristics via Description Length" by Ethan Perez, Douwe Kiela, and Kyungyhun Chβ¦β36Updated 4 years ago
- Hyperparameter Search for AllenNLPβ139Updated 7 months ago
- A Word Sense Disambiguation system integrating implicit and explicit external knowledge.β69Updated 4 years ago
- Collection of academic works in natural language processing, computational linguistics, and computational cognitive science that study thβ¦β22Updated last year
- Code for the Shortformer model, from the ACL 2021 paper by Ofir Press, Noah A. Smith and Mike Lewis.β147Updated 4 years ago
- This repository contains the code for "BERTRAM: Improved Word Embeddings Have Big Impact on Contextualized Representations".β64Updated 5 years ago
- Code accompanying our papers on the "Generative Distributional Control" frameworkβ118Updated 2 years ago
- Code for EMNLP 2019 paper "Attention is not not Explanation"β58Updated 4 years ago
- Implementation of Marge, Pre-training via Paraphrasing, in Pytorchβ76Updated 4 years ago
- Learning the Difference that Makes a Difference with Counterfactually-Augmented Dataβ170Updated 4 years ago
- A python tool for building large scale Wikipedia-based Information Retrieval datasetsβ46Updated 4 years ago