Awesome Nlp

💥 Fast State-of-the-Art Tokenizers optimized for Research and Production

Pre-Training with Whole Word Masking for Chinese BERT（中文BERT-wwm系列模型）

Leveraging BERT and c-TF-IDF to create easily interpretable topics.

State of the Art Natural Language Processing

Top2Vec learns jointly embedded topic, document and word vectors.

Rust native ready-to-use NLP pipelines and transformer-based models (BERT, DistilBERT, GPT2,...)

A model library for exploring state-of-the-art deep learning topologies and techniques for optimizing Natural Language Processing neural networks

Kashgari is a production-level NLP Transfer learning framework built on top of tf.keras for text-labeling and text-classification, includes Word2Vec, BERT, and GPT2 Language Embedding.

A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across 15+ diverse IR datasets.

:house_with_garden: Fast & easy transfer learning for NLP. Harvesting language models for the industry. Focus on Question Answering.

Korean BERT pre-trained cased (KoBERT)

Portuguese pre-trained BERT models

PhoBERT: Pre-trained language models for Vietnamese (EMNLP-2020 Findings)

Pre-trained Transformers for Arabic Language Understanding and Generation (Arabic BERT, Arabic GPT2, Arabic ELECTRA)

Revisiting Pre-trained Models for Chinese Natural Language Processing (MacBERT)

The first-ever vast natural language processing benchmark for Indonesian Language. We provide multiple downstream tasks, pre-trained IndoBERT models, and a starter code! (AACL-IJCNLP 2020)

📖 Korean NLU Benchmark

BETO - Spanish version of the BERT model

Fast and production-ready question answering in Node.js

🤗 ParsBERT: Transformer-based Model for Persian Language Understanding

IndoLEM is a comprehensive Indonesian NLU benchmark, comprising three pillars NLP task: morpho-syntax, semantic, and discourse. Presented in COLING 2020.