serrano-s / attn-tests
Checking the interpretability of attention on text classification models
☆48Updated 5 years ago
Alternatives and similar repositories for attn-tests:
Users that are interested in attn-tests are comparing it to the libraries listed below
- Code for EMNLP 2019 paper "Attention is not not Explanation"☆58Updated 3 years ago
- Encoder-Agnostic Adaptation for Conditional Language Generation☆79Updated 9 months ago
- This repository contains the code for running the character-level Sandwich Transformers from our ACL 2020 paper on Improving Transformer …☆55Updated 4 years ago
- ☆63Updated 3 years ago
- The implementation of "Neural Machine Translation without Embeddings", NAACL 2021☆33Updated 3 years ago
- ☆47Updated 4 years ago
- ☆17Updated 4 years ago
- PyTorch implementation of A Surprisingly Effective Fix for Deep Latent Variable Modeling of Text (EMNLP 2019)☆48Updated 5 years ago
- A framework for training and evaluating AI models on a variety of openly available dialogue datasets.☆36Updated 4 years ago
- Language Model Baselines for PyTorch☆42Updated 4 years ago
- a Pytorch implementation of the Reformer Network (https://openreview.net/pdf?id=rkgNKkHtvB)☆53Updated 2 years ago
- Code for "A Multi-Task Approach for Disentangling Syntax and Semantics in Sentence Representations" (NAACL 2019)☆67Updated 4 years ago
- Code for papers "A Surprisingly Robust Trick for Winograd Schema Challenge" and "WikiCREM: A Large Unsupervised Corpus for Coreference Re…☆71Updated 2 years ago
- Companion site for "Analysis Methods in Neural Language Processing: A Survey"☆66Updated 5 years ago
- Boolean Question Answering with multi-task learning and uses large LM embeddings like BERT, RoBERTa☆18Updated 5 years ago
- ☆12Updated 6 years ago
- Code for "Variational Sequential Labelers for Semi-Supervised Learning" (EMNLP 2018)☆34Updated 6 years ago
- ☆31Updated 5 years ago
- Factorization of the neural parameter space for zero-shot multi-lingual and multi-task transfer☆39Updated 4 years ago
- Code for bidirectional sequence generation (BiSon) for generating from BERT pre-trained models.☆51Updated 5 years ago
- Assessing syntactic abilities of BERT☆148Updated 5 years ago
- TextGraphs-13 Shared Task on Multi-Hop Inference Explanation Regeneration☆43Updated 5 years ago
- Tool for Evaluating Adversarial Perturbations on Text☆61Updated 3 years ago
- DisCo Transformer for Non-autoregressive MT☆77Updated 2 years ago
- ☆46Updated 5 years ago
- ☆53Updated 4 years ago
- Implementation of ICLR 2020 paper "Revisiting Self-Training for Neural Sequence Generation"☆46Updated 2 years ago
- Demo for method introduced in "Beyond Word Importance: Contextual Decomposition to Extract Interactions from LSTMs"☆56Updated 4 years ago
- PyTorch code for meta seq2seq learning☆43Updated 5 years ago
- Pytorch implementation of Bert and Pals: Projected Attention Layers for Efficient Adaptation in Multi-Task Learning (https://arxiv.org/ab…☆82Updated 5 years ago