PLN | 🇬🇧 NLP

https://editorialia.com/wp-content/uploads/2020/07/textattack-a-framework-for-adversarial-attacks-data-augmentation-and-adversarial-training-in-nlp.jpg

TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP

This paper introduces TextAttack, a Python framework for adversarial attacks, data augmentation, and adversarial training in NLP. TextAttack builds attacks from four components: a goal function, a set of constraints, a transformation, and a search method. TextAttack’s modular design enables researchers to easily construct attacks from combinations of novel and existing components. TextAttack provides implementations of 16 adversarial attacks from the literature and supports a variety of models and datasets, including BERT and other transformers, and all GLUE tasks.

https://editorialia.com/wp-content/uploads/2020/06/microsoft-nlp-best-practices.jpg

Microsoft NLP Best Practices

This repository contains examples and best practices for building NLP systems, provided as Jupyter notebooks and utility functions. The focus of the repository is on state-of-the-art methods and common scenarios that are popular among researchers and practitioners working on problems involving text and language

https://editorialia.com/wp-content/uploads/2020/06/the-super-duper-nlp-repo-the-big-bad-nlp-database.jpg

The Super Duper NLP Repo & The Big Bad NLP Database

A database housing more than 100 Colab notebooks running ML code for various NLP tasks. Colab is an excellent destination to experiment with the latest models as it comes with a free GPU/TPU housed in Google’s back-end servers… And a collection of more than 400 NLP datasets that it include papers.

https://editorialia.com/wp-content/uploads/2020/03/stanza2-2.png

Stanza – una biblioteca de Python NLP para muchos idiomas humanos

El diseño del kit de herramientas permite trabajar en paralelo entre más de 70 idiomas, utilizando el formalismo de Dependencias Universales. Stanza está construido con componentes de red neuronal de alta precisión, que también permiten una capacitación y evaluación eficientes con sus propios datos anotados.

https://editorialia.com/wp-content/uploads/2020/06/natural-language-processing-succinctly.jpg

Natural Language Processing Succinctly

AI assistants represent a significant frontier for development. But the complexities of such systems pose a significant barrier for developers. In Natural Language Processing Succinctly, author Joseph Booth will guide readers through designing a simple system that can interpret and provide reasonable responses to written English text. With this foundation, readers will be prepared to tackle the greater challenges of natural language development. (Syncfusion).

https://editorialia.com/wp-content/uploads/2020/06/natural-language-processing-with-python.jpg

Natural Language Processing with Python

This book will help you gain practical skills in natural language processing using the Python programming language and the Natural Language Toolkit (NLTK) open source library.

https://www.microsoft.com/en-us/research/blog/turing-nlg-a-17-billion-parameter-language-model-by-microsoft/

Turing-NLG: A 17-billion-parameter language model by Microsoft

Turing Natural Language Generation (T-NLG) is a 17 billion parameter language model by Microsoft that outperforms the state of the art on many downstream NLP tasks. We present a demo of the model, including its freeform generation, question answering, and summarization capabilities, to academics for feedback and research purposes.