7th place solution to the Gendered Pronoun Resolution competition https://www.kaggle.com/c/gendered-pronoun-resolution/overview

Fine tuning of BERT with parsing of GAP data for kaggle competition https://www.kaggle.com/c/gendered-pronoun-resolution

Repo for counting stars and contributing. Press F to pay respect to glorious developers.

Shared repository for open-sourced projects from the Google AI Language team.

Code for paper Fine-tune BERT for Extractive Summarization

Models built with TensorFlow

pytorch implementation of "Get To The Point: Summarization with Pointer-Generator Networks"

reimplementing Neural Summarization by Extracting Sentences and Words

The PyTorch Implementation of SummaRuNNer

「2018 JDDC」 对话大赛亚军解决方案

Pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE)

TensorFlow Tutorials with YouTube Videos

100 Must-Read NLP Papers

Pre-training of Deep Bidirectional Transformers for Language Understanding: pre-train TextCNN

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

An Architecture Combining Convolutional Neural Network (CNN) and Linear Support Vector Machine (SVM) for Image Classification

TensorFlow code and pre-trained models for BERT

Sentence2vec by Rock

100+ Chinese Word Vectors 上百种预训练中文词向量

A Library for Field-aware Factorization Machines

This repo contains the code for the paper Neural Factor Graph Models for Cross-lingual Morphological Tagging.

Library for fast text representation and classification.

Deep Learning for humans

HackDelft

A pytorch (pytorch-1.0) CUDA version with pretrained GoogleNews word embeddings. Supports Python 2.7 and 3.6. In addition to GPU/CUDA, it also supports running on CPU.

Topic Modelling for Humans