DGMs for NLP. A roadmap.

TensorFlow implementation of On the Sentence Embeddings from Pre-trained Language Models (EMNLP 2020)

HugeCTR is a high efficiency GPU framework designed for Click-Through-Rate (CTR) estimating training

Multi-Task Deep Neural Networks for Natural Language Understanding

Source code and dataset for ACL 2019 paper "ERNIE: Enhanced Language Representation with Informative Entities"

Tools to download and cleanup Common Crawl data

A Span-Extraction Dataset for Chinese Machine Reading Comprehension (CMRC 2018)

Source code for "Efficient Training of BERT by Progressively Stacking"

This dataset contains 108,463 human-labeled and 656k noisily labeled pairs that feature the importance of modeling structure, context, and word order information for the problem of paraphrase ident…

A toolkit for evaluating the linguistic knowledge and transferability of contextual representations. Code for "Linguistic Knowledge and Transferability of Contextual Representations" (NAACL 2019).

An optimizer that trains as fast as Adam and as good as SGD.

Stanford NLP Python library for tokenization, sentence segmentation, NER, and parsing of many human languages

Deep neural models for core NLP tasks (Pytorch version)

BERT-NER (nert-bert) with google bert https://github.com/google-research.

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.

Library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.

An open-source NLP research library, built on PyTorch.

TensorFlow code and pre-trained models for BERT

A datasets and methods survey about task-oriented dialogue, including recent datasets and SOTA leaderboards.

Pre-trained ELMo Representations for Many Languages

Twpipe is a pipeline toolkit that parses raw tweets into universal dependencies.

A collection of English tweets annotated in Universal Dependencies.

A Gadio infomation mining tool for fans of g-cores.com.

Tensorflow implementation of contextualized word representations from bi-directional language models

Abstract Meaning Representation (AMR) reader

JAMR Parser and Generator

Implementation of Reinforcement Learning Algorithms. Python, OpenAI Gym, Tensorflow. Exercises and Solutions to accompany Sutton's Book and David Silver's course.