Projects sharing features with Textacy

Library for translating between 200 languages. Built on 🤗 transformers.

CoreNLP is a Java natural language processing library designed to convert raw human language text into structured data. It utilizes a suite of linguistic annotators to analyze text through a pipeline, extracting grammatical structures, sentiment, and linguistic patterns. The project includes a coreference resolution engine that links multiple mentions of the same entity to maintain contextual consistency across documents. It also provides tools for named entity recognition to categorize people, companies, and locations, and a part-of-speech tagger to assign grammatical categories and base for

spaCy is a Python natural language processing framework designed for industrial-scale text processing. It converts raw text into structured data for machine learning pipelines through a combination of statistical language model trainers, transformer-based text processors, and syntactic dependency parsers. The project enables the integration of pretrained transformer architectures to perform complex linguistic analysis and multi-task learning. It also provides a specialized system for neural named entity recognition to identify and categorize key entities within text. The framework covers a b

Haystack is an orchestration framework designed for building complex search and generative AI pipelines. It functions as an agentic workflow engine, enabling the construction of automated sequences that allow AI agents to perform multi-step reasoning and data analysis. The framework utilizes a modular, component-based architecture that connects processing steps into directed acyclic graphs. By employing a provider-agnostic integration layer, it decouples core logic from specific external AI services and vector databases, allowing for the flexible exchange of underlying technologies. This desi

Transformers is a comprehensive library for machine learning that provides a unified interface for training, fine-tuning, and deploying transformer-based models. It supports a wide range of tasks, including text classification, language modeling, question answering, and sequence-to-sequence translation, while offering specialized architectures for both text and vision processing. The framework includes tools for managing the entire model lifecycle, from data preprocessing and tokenization to distributed training and inference. The library features extensive support for model optimization and

PyNLPl, pronounced as 'pineapple', is a Python library for Natural Language Processing. It contains various modules useful for common, and less common, NLP tasks. PyNLPl can be used for basic tasks such as the extraction of n-grams and frequency lists, and to build simple language model. There are also more complex data types and algorithms. Moreover, there are parsers for file formats common in NLP (e.g. FoLiA/Giza/Moses/ARPA/Timbl/CQL). There are also clients to interface with various NLP specific servers. PyNLPl most notably features a very extensive library for working with FoLiA XML (Form

A Python library for Interpretable Machine Learning in Text Classification using the SS3 model, with easy-to-use visualization tools for Explainable AI :octocat:

snips-nlu is a Python library and natural language understanding engine designed to convert unstructured text into structured data. It identifies user intents and extracts associated entities from natural language sentences to enable machine-readable command processing. The engine functions as a multilingual parser capable of processing text across multiple languages. It maps identified entities to canonical values or standardized ISO formats, such as timestamps, to ensure data consistency. The project covers intent classification and named entity recognition, utilizing sequence labeling and

Fairseq is a deep learning research toolkit and sequence-to-sequence framework built on PyTorch. It provides a system for training and deploying models that map input sequences to output sequences, with a primary focus on neural machine translation and speech recognition. The toolkit allows for the generation of text sequences through search algorithms such as beam search and nucleus sampling. It includes capabilities for producing synthetic parallel training data by translating monolingual text using reverse sequence models. The framework supports large scale model training through multi-de

Flair is a natural language processing framework for training and applying models for sequence labeling and text classification. It provides a system for generating word embeddings and identifying semantic entities within text. The framework includes a dedicated system for zero and few-shot learning, enabling text classification and entity extraction using minimal training examples by leveraging pre-trained knowledge. Its capabilities cover named entity recognition, sentiment analysis, and the training of specialized models using custom datasets. It also includes tooling for the visual highl

A Multilingual Latent Dirichlet Allocation (LDA) Pipeline with Stop Words Removal, n-gram features, and Inverse Stemming, in Python.

Sockeye is an open-source sequence-to-sequence framework for Neural Machine Translation built on PyTorch. It implements distributed training and optimized inference for state-of-the-art models, powering Amazon Translate and other MT applications. Recent developments and changes are tracked in…

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.

Tools, wrappers, etc... for data science with a concentration on text processing

This project is a high-performance library for converting raw text into tokens and IDs for machine learning models. It functions as a fast text encoder and a text preprocessing pipeline designed to transform strings into numerical representations with high throughput for research and production. The library includes a subword tokenizer trainer used to analyze text datasets and create custom vocabularies using algorithms such as byte-pair encoding and wordpiece. It provides capabilities for subword vocabulary training and text alignment, allowing character offsets to be tracked during normaliz

AllenNLP is a PyTorch-based research library and deep learning language toolkit designed for developing and training neural network architectures for linguistic tasks. It provides a distributed training system that coordinates data and gradients across multiple GPUs and a framework for integrating pretrained transformer architectures. The system distinguishes itself with a dedicated algorithmic bias mitigation tool used to identify and reduce bias in linguistic model predictions. It also includes model influence analysis to interpret predictions by calculating the influence of specific traini

Beautiful visualizations of how language differs among document types.

Basic Utilities for PyTorch Natural Language Processing (NLP)

TextAttack 🐙 is a Python framework for adversarial attacks, data augmentation, and model training in NLP https://textattack.readthedocs.io/en/master/

YSDA course in Natural Language Processing

lecture notes for probabilistic topic models using ipython notebook

Implementation of various topic models

Chat with your favourite LLaMA models in a native macOS app

This project is a quantized fine-tuning framework for large language models. It implements a low-rank adaptation library and a four-bit quantizer to reduce the GPU memory requirements needed to train large models. The framework utilizes four-bit quantization and low-rank adapters to enable model training on consumer-grade hardware. It further reduces the memory footprint through double quantization and a paged optimizer that offloads states to system RAM. The system supports distributed training across multiple GPUs to handle larger parameter scales and includes utilities for custom dataset

ANEE is an experimental dynamic inference wrapper for pretrained Transformer language models (currently GPT-2). Instead of always running all layers, ANEE exposes an energy_budget and performs early exit inside the model’s forward pass.