Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

The official code of LM-Debugger, an interactive tool for inspection and intervention in transformer-based language models.

[NeurIPS 2022] DataMUX: Data Multiplexing for Neural Networks

Explain, analyze, and visualize NLP language models. Ecco creates interactive visualizations directly in Jupyter notebooks explaining the behavior of Transformer-based language models (like GPT2, B…

Course materials for Dartmouth course: Human Memory (PSYC 51.09)

[EMNLP 2021] SimCSE: Simple Contrastive Learning of Sentence Embeddings https://arxiv.org/abs/2104.08821

🧑‍🏫 60 Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gan…

multi_task_NLP is a utility toolkit enabling NLP developers to easily train and infer a single model for multiple tasks.

Standardized Serverless ML Inference Platform on Kubernetes

Trankit is a Light-Weight Transformer-based Python Toolkit for Multilingual Natural Language Processing

Implementation of Marge, Pre-training via Paraphrasing, in Pytorch

中文分词 词性标注 命名实体识别 依存句法分析 成分句法分析 语义依存分析 语义角色标注 指代消解 风格转换 语义相似度 新词发现 关键词短语提取 自动摘要 文本分类聚类 拼音简繁转换 自然语言处理

Fuzzy string matching, grouping, and evaluation.

⚫ A spaCy pipeline and model for NLP on unstructured legal text.

甲言，专注于古代汉语(古汉语/古文/文言文/文言)处理的NLP工具包，支持文言词库构建、分词、词性标注、断句和标点。Jiayan, the 1st NLP toolkit designed for Classical Chinese, supports lexicon construction, tokenizing, POS tagging, sentence segmentation a…

The world's cleanest AutoML library ✨ - Do hyperparameter tuning with the right pipeline abstractions to write clean deep learning production pipelines. Let your pipeline steps have hyperparameter …

Library for Knowledge Intensive Language Tasks

Making BERT stretchy. Semantic Elasticsearch with Sentence Transformers

🚪✊Knock Knock: Get notified when your training ends with only two additional lines of code

A relation-aware semantic parsing model from English to SQL

Top2Vec learns jointly embedded topic, document and word vectors.

DeText: A Deep Neural Text Understanding Framework for Ranking and Classification Tasks

Python library for building highly effective data science workflows

Pytorch library for fast transformer implementations

A very simple framework for state-of-the-art Natural Language Processing (NLP)

A set of methods for finding an appropriate number of topics in a text collection

Text preprocessing, representation and visualization from zero to hero.

Google search from Python (unofficial).

Trax — Deep Learning with Clear Code and Speed