i13harada1s

mbrs

A library for minimum Bayes risk (MBR) decoding

gpt-neox

An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries

t5x

seqio

Task-based datasets, preprocessing, and evaluation for sequence models.

praxis

rationale-alignment

trans-encoder

Trans-Encoder: Unsupervised sentence-pair modelling through self- and mutual-distillations

PromCSE

Code for "Improved Universal Sentence Embeddings with Prompt-based Contrastive Learning and Energy-based Learning (EMNLP 2022)"

DiffCSE

Code for the NAACL 2022 long paper "DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings"

kwja

An integrated Japanese analyzer based on foundation models

SentEval

A python tool for evaluating the quality of sentence embeddings.

orbax

Orbax provides common checkpointing and persistence utilities for JAX users

n-grammer-flax

Implementation of N-Grammer in Flax

jax-rl

JAX implementations of core Deep RL algorithms

ott

Optimal transport tools implemented with the JAX framework, to get differentiable, parallel and jit-able computations.

Contrastive-Learning-NLP-Papers

Paper List for Contrastive Learning for Natural Language Processing

konoha

🌿 An easy-to-use Japanese Text Processing tool, which makes it possible to switch tokenizers with small changes of code.

jax

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

daachorse

🐎 A fast implementation of the Aho-Corasick algorithm using the compact double-array data structure in Rust.

gcd

TUPE

Transformer with Untied Positional Encoding (TUPE). Code of paper "Rethinking Positional Encoding in Language Pre-training". Improve existing models like BERT.

attach-juxtapose-parser

Code for the paper "Strongly Incremental Constituency Parsing with Graph Neural Networks"

vaporetto

🛥 Vaporetto: Very accelerated pointwise prediction based tokenizer

fairseq-tagging

a Fairseq fork for sequence tagging/labeling tasks

compare-mt

A tool for holistic analysis of language generations systems

camembert_finetune

NLP-progress

Repository to track the progress in Natural Language Processing (NLP), including the datasets and the current state-of-the-art for the most common NLP tasks.

language-models-are-knowledge-graphs-pytorch

Language models are open knowledge graphs ( non official implementation )

awd-lstm-lm

LSTM and QRNN Language Model Toolkit for PyTorch

PILM

Language model with phrase induction