vyraun

GEM-metrics

Automatic metrics for GEM tasks

BIG-bench

Beyond the Imitation Game collaborative benchmark for measuring and extrapolating the capabilities of language models

dlp

Code for "On Dimensional Linguistic Properties of the Word Embedding Space".

DNI-tensorflow

DNI (Decoupled Neural Interfaces using Synthetic Gradients) Implementation with Tensorflow.

Finding-Memo

Code for "Extractive Memorization in Constrained Sequence Generation Tasks"

Half-Size

Code for "Effective Dimensionality Reduction for Word Embeddings".

hallucinations

Code for "The Curious Case of Hallucinations in Neural Machine Translation".

long-tailed

Code for "On Long-Tailed Phenomena in NMT".

Megalodon

Various ML/DL Resources organised at a single place.

seq2set-keras

An Implementation of Seq2Set (Pointer Network) in Keras.

vyraun/Megalodon

Various ML/DL Resources organised at a single place.

vyraun/Half-Size

Code for "Effective Dimensionality Reduction for Word Embeddings".

vyraun/long-tailed

Code for "On Long-Tailed Phenomena in NMT".

vyraun/dlp

Code for "On Dimensional Linguistic Properties of the Word Embedding Space".

vyraun/hallucinations

Code for "The Curious Case of Hallucinations in Neural Machine Translation".

vyraun/Finding-Memo

Code for "Extractive Memorization in Constrained Sequence Generation Tasks"

vyraun/blindspots

Seq2Seq Blindspots

vyraun/literalness

Code for "Do GPTs Produce Less Literal Translations?"

vyraun/assignment_2

Low Resource Machine Translation.

vyraun/awesome-align

A word aligner based on multilingual encoders

vyraun/bert_score

BERT score for text generation

vyraun/biaffine-ner

Named Entity Recognition as Dependency Parsing

vyraun/BIG-bench

Beyond the Imitation Game collaborative benchmark for enormous language models

vyraun/bin

bin files

vyraun/bleurt

BLEURT is a metric for Natural Language Generation based on transfer learning.

vyraun/CMC

pytorch implementation of "Contrastive Multiview Coding", "Momentum Contrast for Unsupervised Visual Representation Learning", and "Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination"

vyraun/cookbook

The Unicode Cookbook for Linguists

vyraun/espresso

Espresso: A Fast End-to-End Neural Speech Recognition Toolkit

vyraun/fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

vyraun/infotabs

vyraun/LM_NE_bias

Named Entity Biases in Pre-trained Language Models

vyraun/loss_dropper

vyraun/transformers

🤗Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0.

vyraun/TVCaption

PyTorch implementation of MMT on TVCaption dataset

vyraun/whisper

vyraun/Wikilingua

Multilingual abstractive summarization dataset extracted from WikiHow.

vyraun/wit

WIT (Wikipedia-based Image Text) Dataset is a large multimodal multilingual dataset comprising 37M+ image-text sets with 11M+ unique images across 100+ languages.

vyraun/wmt-format-tools

Tools for formatting WMT hypothesis and test sets in XML

vyraun/wmt21-news-systems

vyraun/xtreme

XTREME is a benchmark for the evaluation of the cross-lingual generalization ability of pre-trained multilingual models that covers 40 typologically diverse languages and includes nine tasks.