This is a repository with the code for the ACL 2019 paper "Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned" and the ACL 2021 paper "Analyzing Source and Target Contributions to NMT Predictions".
☆319Aug 2, 2021Updated 4 years ago
Alternatives and similar repositories for the-story-of-heads
Users that are interested in the-story-of-heads are comparing it to the libraries listed below
Sorting:
- Code for the paper "Are Sixteen Heads Really Better than One?"☆175Apr 1, 2020Updated 5 years ago
- Code and Data release for "Improving Multilingual Translation by Representation and Gradient Regularization" (Yang et al. EMNLP 2021), an…☆13Aug 12, 2024Updated last year
- ☆472Apr 4, 2021Updated 4 years ago
- This is a repository with the code for the EMNLP 2020 paper "Information-Theoretic Probing with Minimum Description Length"☆71Aug 20, 2024Updated last year
- ☆21May 5, 2020Updated 5 years ago
- This is a repository with the data and code for the ACL 2019 paper "When a Good Translation is Wrong in Context: ..." and the EMNLP 2019 …☆98May 12, 2020Updated 5 years ago
- Code for Evaluating Explanations for Reading Comprehension with Realistic Counterfactuals.☆18Apr 25, 2021Updated 4 years ago
- Measuring the Mixing of Contextual Information in the Transformer☆34May 27, 2023Updated 2 years ago
- Effective Attention Sheds Light On Interpretability - Findings of ACL2021☆11May 16, 2021Updated 4 years ago
- ☆88Apr 16, 2024Updated last year
- ☆20Jan 16, 2024Updated 2 years ago
- Contrastive Attention Mechanism for Abstractive Text Summarization☆40Jan 14, 2020Updated 6 years ago
- ☆18Oct 6, 2022Updated 3 years ago
- Official Code for Towards Transparent and Explainable Attention Models paper (ACL 2020)☆35Jun 22, 2022Updated 3 years ago
- This repository contains the code for "How many data points is a prompt worth?"☆48Apr 7, 2021Updated 4 years ago
- Soft Contextual Data Augmentation☆39Jul 25, 2024Updated last year
- ☆13Feb 7, 2023Updated 3 years ago
- [NeurIPS 2020] "The Lottery Ticket Hypothesis for Pre-trained BERT Networks", Tianlong Chen, Jonathan Frankle, Shiyu Chang, Sijia Liu, Ya…☆142Dec 30, 2021Updated 4 years ago
- ☆16Jan 14, 2022Updated 4 years ago
- Implementation of unregularized, l1 regularized and l2 regularized linear regression using numpy and without sklearn☆12Oct 4, 2019Updated 6 years ago
- ☆38Apr 23, 2019Updated 6 years ago
- Understanding the Difficulty of Training Transformers☆332May 31, 2022Updated 3 years ago
- ☆44Sep 16, 2020Updated 5 years ago
- ☆17Apr 28, 2022Updated 3 years ago
- BertViz: Visualize Attention in Transformer Models☆7,954Jan 8, 2026Updated 2 months ago
- Transformer training code for sequential tasks☆609Sep 14, 2021Updated 4 years ago
- A tool for holistic analysis of language generations systems☆471Sep 22, 2025Updated 5 months ago
- Code for the paper "Latent Relation Language Models" at AAAI-20.☆41Sep 22, 2025Updated 5 months ago
- Supplementary material for "When and Why Are Pre-trained Word Embeddings Useful for Neural Machine Translation?" at NAACL 2018☆123Sep 22, 2025Updated 5 months ago
- ☆25Oct 22, 2022Updated 3 years ago
- A supplementary code for Beyond Vector Spaces: Compact Data Representation as Differentiable Weighted Graphs.☆47Nov 2, 2019Updated 6 years ago
- Measuring if attention is explanation with ROAR☆22Mar 3, 2023Updated 3 years ago
- Variable-order CRFs with structure learning☆17Aug 1, 2024Updated last year
- Survey on machine learning.☆14Nov 28, 2020Updated 5 years ago
- A Unified Library for Parameter-Efficient and Modular Transfer Learning☆2,804Mar 1, 2026Updated 2 weeks ago
- Code for the paper "Inoculation by Fine-Tuning: A Method for Analyzing Challenge Datasets", to be presented at NAACL 2019.☆20Apr 4, 2019Updated 6 years ago
- Momentum Decoding: Open-ended Text Generation as Graph Exploration☆19Jan 27, 2023Updated 3 years ago
- Source code for "Importance-based Neuron Allocation for Multilingual Neural Machine Translation"☆12Sep 15, 2021Updated 4 years ago
- jiant is an nlp toolkit☆1,674Jul 6, 2023Updated 2 years ago