Unsupervised Word Segmentation for Neural Machine Translation and Text Generation

Reformer, the efficient Transformer, in Pytorch

brat rapid annotation tool (brat) - for all your textual annotation needs

LAnguage Model Analysis

Sequence-to-sequence framework with a focus on Neural Machine Translation based on PyTorch

ChatLLaMA 📢 Open source implementation for LLaMA-based ChatGPT runnable in a single GPU. 15x faster training process than ChatGPT

🌊HMTL: Hierarchical Multi-Task Learning - A State-of-the-Art neural network model for several NLP tasks based on PyTorch and AllenNLP

A Theano framework for building and training neural networks

Reference BLEU implementation that auto-downloads test sets and reports a version string to facilitate cross-lab comparisons

Simple transformer implementation from scratch in pytorch.

Elasticsearch with BERT for advanced document search.

A data pipeline framework for machine learning

This is not youtube-dl

A simple OpenAI Gym environment for single and multi-agent reinforcement learning

NBoost is a scalable, search-api-boosting platform for deploying transformer models to improve the relevance of search results on different platforms (i.e. Elasticsearch)

MeInGame: Create a Game Character Face from a Single Portrait, AAAI 2021

A framework to learn cross-lingual word embedding mappings

BERTweet: A pre-trained language model for English Tweets (EMNLP-2020)

Official code for "RealFusion: 360° Reconstruction of Any Object from a Single Image" (CVPR 2023)

Neural Machine Translation with Keras

Bitextor generates translation memories from multilingual websites

[ICLR 2023] SeaFormer: Squeeze-enhanced Axial Transformer for Mobile Semantic Segmentation

[unmaintained] Make seq2seq for keras work

eXtensible Neural Machine Translation

Morfessor is a tool for unsupervised and semi-supervised morphological segmentation

This is a package in Python which implements a tokenizer, stemmer for Hindi language

linguistics tree drawing to SVG in python, aimed at Jupyter