gentaiscool

end2end-asr-pytorch

End-to-End Automatic Speech Recognition on PyTorch

code-switching-papers

A curated list of research papers and resources on code-switching

lstm-attention

Attention-based bidirectional LSTM for Classification Task (ICASSP)

few-shot-lm

The source code of "Language Models are Few-shot Multilingual Learners" (MRL @ EMNLP 2021)

indonesian-nlp

A curated list of research papers and resources on Indonesian languages

meta-emb

Multilingual Meta-Embeddings for Named Entity Recognition (RepL4NLP & EMNLP 2019)

gentaiscool.github.io

My website

matrix_fact

Matrix Factorization Library

xnli-dataset

acl-anthology

Data and software for building the ACL Anthology.

aclpub2

al-folio

A beautiful, simple, clean, and responsive Jekyll theme for academics

BIG-bench

Beyond the Imitation Game collaborative benchmark for enormous language models

calcs2023

calcs2023_ingest

calcs2023_test

DataLab

The unified platform for data-related resources.

DeepSpeed

DeepSpeed is a deep learning optimization library that makes distributed training easy, efficient, and effective.

do-we-need-attention

GitHubGraduation-2021

Join the GitHub Graduation Yearbook and "walk the stage" on June 5.

lm-evaluation-harness

A framework for few-shot evaluation of autoregressive language models.

mesh-transformer-jax

Model parallel transformers in JAX and Haiku

NER-datasets

Datasets to train supervised classifiers for Named-Entity Recognition in different languages (Portuguese, German, Dutch, French, English)

NL-Augmenter

NL-Augmenter 🦎 → 🐍 A Collaborative Repository of Natural Language Transformations

nusa-datasets

PromptPapers

Must-read papers on prompt-based tuning for pre-trained language models.

promptsource

Toolkit for creating, sharing and using natural language prompts.

seqeval

A Python framework for sequence labeling evaluation(named-entity recognition, pos tagging, etc...)

transformers

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

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.