giannisdaras / spaCyIRL_slides
Slides from my talk on spaCy IRL, regarding sparse attention.
☆11Updated 5 years ago
Related projects ⓘ
Alternatives and complementary repositories for spaCyIRL_slides
- ULMFiT + Siamese Network for Sentence Vectors☆35Updated 6 years ago
- Auxiliary GAN for WE post-specialisation☆23Updated 5 years ago
- numeric fused-head identification and resolution☆33Updated 5 years ago
- Easy-to-use text representations extraction library based on the Transformers library.☆32Updated 2 years ago
- Code and data for the WSDM '19 paper "Crosslingual Document Embedding as Reduced-Rank Ridge Regression (Cr5)"☆30Updated 5 years ago
- PyTorch source code of NAACL 2019 paper "An Embarrassingly Simple Approach for Transfer Learning from Pretrained Language Models"☆96Updated last year
- Code for processing brain data☆12Updated 5 years ago
- Training Transformer-XL on 128 GPUs☆140Updated 4 years ago
- A PyTorch implementation of the Transformer model from "Attention Is All You Need".☆59Updated 5 years ago
- ☆31Updated 4 years ago
- [NeurIPS 2020] Official Implementation: "SMYRF: Efficient Attention using Asymmetric Clustering".☆47Updated last year
- A 🤗-style implementation of BERT using lambda layers instead of self-attention☆70Updated 4 years ago
- Reversible tokenization in Python.☆61Updated 6 years ago
- Extended Wikilinks dataset description☆14Updated 6 years ago
- Obtaining word embeddings from a WordNet ontology☆49Updated 11 months ago
- Code for EMNLP 2018 paper "Auto-Encoding Dictionary Definitions into Consistent Word Embeddings"☆37Updated 6 years ago
- ☆64Updated 4 years ago
- Unsupervised Multilingual Word Embeddings (EMNLP 2018)☆81Updated 2 years ago
- A tutorial on how to implement models for natural language inference using PyTorch and TorchText. [IN PROGRESS]☆25Updated 4 years ago
- Example using Polyaxon to experiment with pre-training spaCy☆65Updated 3 years ago
- SCoPE: Sentence Content Paragraph Embeddings☆18Updated 5 years ago
- diagNNose is a Python library that facilitates a broad set of tools for analysing hidden activations of neural models.☆81Updated last year
- ☆21Updated 6 years ago
- The accompanying code for "Are We Modeling the Task or the Annotator? An Investigation of Annotator Bias in Natural Language Understandin…☆21Updated 5 years ago
- A handy Python function that prints your model training loss change like stock index.☆25Updated 5 years ago
- http://nlp.seas.harvard.edu/2018/04/03/attention.html☆63Updated 3 years ago
- Explorations in building seq2seq models using PyTorch and fast.ai☆14Updated 5 years ago
- This repository contains the code for running the character-level Sandwich Transformers from our ACL 2020 paper on Improving Transformer …☆55Updated 3 years ago
- Differentiable lower bound for BLEU score.☆12Updated 5 years ago